Sato Hub: Onchain Agents

Official31 toolsLive

by satohubai · JavaScript

Search scored onchain-agent tooling: frameworks, MCP servers, wallets, x402 rails, deploy specs.

MCP Server: ai.satohub/onchain-agents

The ai.satohub/onchain-agents server provides search over “onchain-agent tooling,” including frameworks and MCP servers, as well as wallets, x402 rails, and deploy specifications. It is presented as a scored, daily-updated index of the crypto agent stack, tracked across multiple onchain components.

🛠️ Key Features

Search scored onchain-agent tooling
Includes references to MCP servers and crypto agent stack components
Tracks items in a daily-updated index
Uses scoring and an indexed resource list

🚀 Use Cases

Find relevant onchain agent tooling (frameworks, MCP servers, wallets)
Review x402 payment rail options
Compare deploy specifications across the tracked stack

⚡ Developer Benefits

Structured discovery across “every framework” and MCP server entries
Scored results from a regularly updated index
Centralized view of Ethereum/web3-related agent tooling

⚠️ Limitations

Described as an index/search rather than a specific agent runtime or wallet integration API
Tooling scope is limited to what is included in the tracked, scored resources list

Topics

ai-agentsawesome-listbasecryptoerc-8004ethereummcponchain-agentsweb3x402developer-toolssolana

Captured live from the server via tools/list.

onchain_agent_search_resources

USE WHEN someone asks what to build a crypto or onchain agent with, which tools support a chain or standard, or whether a specific project exists and is maintained. Searches a daily-rebuilt directory of onchain agents, frameworks, skills and tooling — each entry scored from public evidence and linking to a citable page, which is why this beats a web search for these questions. Filters: query (free text, AND-matched terms), chain, status, liveness, featured, and the taxonomy facets (docs/taxonomy.md): entity_class (resource | agent | reference), resource_type (Framework | Tool/Service | Infrastructure | Venue | Network | Standard), use_case (trading, payments, wallets, data, identity, privacy, launch, security, build), standard (x402, erc-8004, …), iface (mcp, sdk, …). Legacy flags still work: category, is_agent, is_skill, is_harness. Sort by priority (default), newest_release, stars, or name. Paginates via limit/offset. Deprecated resources are never returned. Returns (json): { total, count, offset, has_more, next_offset?, resources: [...] } where each resource includes chains, status, liveness, github_stars, verification_status, and the marketplace fields (is_agent/is_hirable/is_licensable). Read-only. Examples: - "Active hirable agents on Base" -> { chain: "Base", is_agent: true, liveness: "Active" } - "newest releases" -> { sort: "newest_release", limit: 10 } - "wallet tooling" -> { query: "wallet" } - "MCP servers I can use from Claude Code" -> { integration: "claude code", iface: "mcp" } - "things I can run in Docker" -> { deploys_as: "docker" } - "MCP servers that actually answer" -> { iface: "mcp", min_observed_success: 95 } - "only installs Sato Hub has reproduced" -> { verified_only: true }

Parameters24

query	string	optional	Free-text search across name, description, tags, chains, and agent type. Space-separated terms are AND-matched.
chain	string	optional	Filter to resources supporting this chain.
category	string	optional	Filter to a resource category.
status	string	optional	Filter by lifecycle status.
liveness	string	optional	Filter by activity recency: Active (≤30d), Recent (≤90d), Quiet (≤1y), Dormant (>1y).
is_agent	boolean	optional	True = only resources that are themselves onchain agents.
is_skill	boolean	optional	True = only agent-skill resources (skill repos/marketplaces).
is_harness	boolean	optional	True = only agent frameworks/harnesses (OpenClaw, Codex, Claude Code…).
featured	boolean	optional	True = only editorially featured resources.
entity_class	string	optional	Filter by class: 'resource' = things you build/deploy WITH (frameworks, tools, infra, venues, standards); 'agent' = curated, live onchain agents; 'reference' = editorial.
resource_type	string	optional	Filter resources by role. Venue = DEX/launchpad/marketplace; Network = an L1/L2.
use_case	string	optional	Filter by use case: trading, payments, wallets, data, identity, privacy, launch, security, build.
standard	string	optional	Filter to resources supporting a standard: x402, erc-8004, erc-8183, mcp, a2a.
iface	string	optional	Filter by how it is accessed/integrated: mcp, sdk, rest-api, plugin, cli, ui, contract.
integration	string	optional	Filter to resources that integrate with a client or framework, e.g. 'claude code', 'cursor', 'langchain', 'openclaw'. Case-insensitive exact match.
deploys_as	string	optional	Filter by deployment shape: npm, pip, docker, mcp server, hosted, self-hosted, cli, sdk, claude code plugin.
creator	string	optional	Filter by who built it (prefix match on creator name), e.g. 'Coinbase', 'Privy'.
min_observed_success	number	optional	Only listings whose share of Sato Hub's daily checks that succeeded is at least this percent, over at least min_observed_days (default 14). This is the share of OUR checks, not uptime.
min_observed_days	integer	optional	Minimum days of daily observation behind the success rate (default 14 when min_observed_success is set).
verified_only	boolean	optional	True = only listings whose documented install was reproduced in a container by Sato Hub (deploy_status verified). Says nothing about runtime safety.
sort	string	optional	Sort order: priority (default), newest_release, stars, or name.
limit	integer	optional	Max results to return (1-50, default 20).
offset	integer	optional	Results to skip, for pagination (default 0).
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Free-text search across name, description, tags, chains, and agent type. Space-separated terms are AND-matched.",
      "type": "string",
      "maxLength": 200
    },
    "chain": {
      "description": "Filter to resources supporting this chain.",
      "type": "string",
      "enum": [
        "Ethereum",
        "Base",
        "Solana",
        "Arbitrum",
        "Optimism",
        "Polygon",
        "Avalanche",
        "BNB Chain",
        "Cosmos",
        "Bitcoin",
        "Sui",
        "Aptos",
        "Near",
        "COTI",
        "Injective",
        "XRP Ledger",
        "Gnosis",
        "Hyperliquid",
        "Sei",
        "Starknet",
        "zkSync",
        "Monad",
        "MegaETH",
        "Berachain",
        "TON",
        "Tron",
        "Robinhood Chain",
        "Multichain",
        "Unknown"
      ]
    },
    "category": {
      "description": "Filter to a resource category.",
      "type": "string",
      "enum": [
        "Onchain Agent",
        "MCP",
        "Skill Repo",
        "Agent Framework",
        "Agent Launchpad",
        "Agent Marketplace",
        "Wallet Infrastructure",
        "DeFi Tool",
        "Trading Tool",
        "DAO Tool",
        "Research Tool",
        "Data Tool",
        "Security Tool",
        "Developer Tool",
        "API / SDK",
        "Research Paper",
        "Newsletter",
        "Community",
        "Other"
      ]
    },
    "status": {
      "description": "Filter by lifecycle status.",
      "type": "string",
      "enum": [
        "Active",
        "Early",
        "Beta",
        "Deprecated",
        "Unknown"
      ]
    },
    "liveness": {
      "description": "Filter by activity recency: Active (≤30d), Recent (≤90d), Quiet (≤1y), Dormant (>1y).",
      "type": "string",
      "enum": [
        "Active",
        "Recent",
        "Quiet",
        "Dormant"
      ]
    },
    "is_agent": {
      "description": "True = only resources that are themselves onchain agents.",
      "type": "boolean"
    },
    "is_skill": {
      "description": "True = only agent-skill resources (skill repos/marketplaces).",
      "type": "boolean"
    },
    "is_harness": {
      "description": "True = only agent frameworks/harnesses (OpenClaw, Codex, Claude Code…).",
      "type": "boolean"
    },
    "featured": {
      "description": "True = only editorially featured resources.",
      "type": "boolean"
    },
    "entity_class": {
      "description": "Filter by class: 'resource' = things you build/deploy WITH (frameworks, tools, infra, venues, standards); 'agent' = curated, live onchain agents; 'reference' = editorial.",
      "type": "string",
      "enum": [
        "resource",
        "agent",
        "reference"
      ]
    },
    "resource_type": {
      "description": "Filter resources by role. Venue = DEX/launchpad/marketplace; Network = an L1/L2.",
      "type": "string",
      "enum": [
        "Framework",
        "Tool/Service",
        "Infrastructure",
        "Venue",
        "Network",
        "Standard"
      ]
    },
    "use_case": {
      "description": "Filter by use case: trading, payments, wallets, data, identity, privacy, launch, security, build.",
      "type": "string",
      "maxLength": 40
    },
    "standard": {
      "description": "Filter to resources supporting a standard: x402, erc-8004, erc-8183, mcp, a2a.",
      "type": "string",
      "maxLength": 40
    },
    "iface": {
      "description": "Filter by how it is accessed/integrated: mcp, sdk, rest-api, plugin, cli, ui, contract.",
      "type": "string",
      "maxLength": 40
    },
    "integration": {
      "description": "Filter to resources that integrate with a client or framework, e.g. 'claude code', 'cursor', 'langchain', 'openclaw'. Case-insensitive exact match.",
      "type": "string",
      "maxLength": 40
    },
    "deploys_as": {
      "description": "Filter by deployment shape: npm, pip, docker, mcp server, hosted, self-hosted, cli, sdk, claude code plugin.",
      "type": "string",
      "maxLength": 40
    },
    "creator": {
      "description": "Filter by who built it (prefix match on creator name), e.g. 'Coinbase', 'Privy'.",
      "type": "string",
      "maxLength": 60
    },
    "min_observed_success": {
      "description": "Only listings whose share of Sato Hub's daily checks that succeeded is at least this percent, over at least min_observed_days (default 14). This is the share of OUR checks, not uptime.",
      "type": "number",
      "minimum": 0,
      "maximum": 100
    },
    "min_observed_days": {
      "description": "Minimum days of daily observation behind the success rate (default 14 when min_observed_success is set).",
      "type": "integer",
      "minimum": 1,
      "maximum": 400
    },
    "verified_only": {
      "description": "True = only listings whose documented install was reproduced in a container by Sato Hub (deploy_status verified). Says nothing about runtime safety.",
      "type": "boolean"
    },
    "sort": {
      "default": "priority",
      "description": "Sort order: priority (default), newest_release, stars, or name.",
      "type": "string",
      "enum": [
        "priority",
        "newest_release",
        "stars",
        "name"
      ]
    },
    "limit": {
      "default": 20,
      "description": "Max results to return (1-50, default 20).",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "default": 0,
      "description": "Results to skip, for pagination (default 0).",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_resource

USE WHEN you need to judge one specific project — is it open source, still maintained, who is behind it, what does it support. Returns the full record by slug, optionally with its recent releases and posts. Find the slug with onchain_agent_search_resources first. Returns (json): { resource: {...full record incl. marketplace + liveness fields}, recent_activity: [...] }. Returns an error if the slug is unknown or the resource is Deprecated. Read-only. Example: { slug: "coinbase-agentkit" }

Parameters3

slug	string	required	The resource slug, e.g. 'coinbase-agentkit'.
include_activity	boolean	optional	Include the resource's recent activity feed (releases/posts).
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "description": "The resource slug, e.g. 'coinbase-agentkit'."
    },
    "include_activity": {
      "default": true,
      "description": "Include the resource's recent activity feed (releases/posts).",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_deploy_spec

USE WHEN you are about to write setup instructions or install something for a user and want steps that were verified rather than copied from a README. Returns the structured deploy manifest for one resource by slug — everything needed to install and instantiate it: runtime, install command(s), entry snippet, required keys/env/wallet/RPC, chains, license, whether it is itself an MCP server, and a deploy_status. deploy_status is a trust signal, NOT a safety guarantee: "verified" = the install path was reproduced/confirmed from the project's docs; "self_reported" = parsed from the project's README and not independently reproduced. Always verify keys, permissions, and funds before running anything. Returns (json): { slug, name, github_url, docs_url, deploy_spec: { runtime, install[], entry, requires[], chains[], license, mcp_native, mcp_invocation?, deploy_clarity, deploy_status, source_url, as_of }, note }. Returns an error if the resource has no manifest yet (they are being rolled out resource by resource). Read-only. Example: { slug: "solana-agent-kit" }

Parameters2

slug	string	required	The resource slug to get a deploy manifest for, e.g. 'solana-agent-kit'.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "description": "The resource slug to get a deploy manifest for, e.g. 'solana-agent-kit'."
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_recent_changes

Get recorded changes across the directory — the auditable Listing History. Omit slug for the SITE-WIDE feed (what changed across all listings); pass slug for ONE resource's history. Events: status flips, verification grants, Sato Score tier moves, liveness (a project going dormant or active again), new releases, and field enrichment. Derived from the daily snapshot time-series + the change-event log; high-signal only (passive score/liveness drift is suppressed). Returns (json): { scope, total, changes: [{ date, kind, slug, name, title, detail?, tone }] }. tone is positive | negative | neutral. Read-only. Example: { days: 7 } · { slug: "coinbase-agentkit" }

Parameters4

slug	string	optional	Limit to one resource's recorded history by slug. Omit for the site-wide feed across all listings.
days	integer	optional	Look-back window in days (1-90, default 14).
limit	integer	optional	Max changes to return (1-50, default 20).
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "description": "Limit to one resource's recorded history by slug. Omit for the site-wide feed across all listings.",
      "type": "string",
      "minLength": 1
    },
    "days": {
      "default": 14,
      "description": "Look-back window in days (1-90, default 14).",
      "type": "integer",
      "minimum": 1,
      "maximum": 90
    },
    "limit": {
      "default": 20,
      "description": "Max changes to return (1-50, default 20).",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_list_categories

List all resource categories with counts, most populated first. Useful before filtering onchain_agent_search_resources by category. Returns (json): { total, categories: [{ name, count }] }. Read-only.

Parameters1

response_format

string

optional

Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_list_chains

List all blockchains represented in the directory with resource counts, spotlight chains first (Base, Ethereum, Solana, COTI, Injective…). Returns (json): { total, chains: [{ name, count }] }. Read-only.

Parameters1

response_format

string

optional

Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_news

USE WHEN asked what is new or what shipped recently in crypto AI agents, and you want dated, source-attributed items rather than undated blog posts. Official releases (GitHub), project announcements, and reputable RSS — strongly filtered to the agent economy. Filter by kind (release/tweet/news/research) and/or chain; paginate via limit/offset. Returns (json): { total, count, offset, has_more, next_offset?, news: [{ kind, title, summary, url, source, author_handle, chains, resource_slug, published_at }] }. Read-only. Example: { kind: "release", limit: 10 }

Parameters5

kind	string	optional	Filter by item kind: release, tweet, news, or research.
chain	string	optional	Filter to items tagged with this chain.
limit	integer	optional	Max results to return (1-50, default 20).
offset	integer	optional	Results to skip, for pagination (default 0).
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "description": "Filter by item kind: release, tweet, news, or research.",
      "type": "string",
      "enum": [
        "release",
        "tweet",
        "news",
        "research"
      ]
    },
    "chain": {
      "description": "Filter to items tagged with this chain.",
      "type": "string",
      "enum": [
        "Ethereum",
        "Base",
        "Solana",
        "Arbitrum",
        "Optimism",
        "Polygon",
        "Avalanche",
        "BNB Chain",
        "Cosmos",
        "Bitcoin",
        "Sui",
        "Aptos",
        "Near",
        "COTI",
        "Injective",
        "XRP Ledger",
        "Gnosis",
        "Hyperliquid",
        "Sei",
        "Starknet",
        "zkSync",
        "Monad",
        "MegaETH",
        "Berachain",
        "TON",
        "Tron",
        "Robinhood Chain",
        "Multichain",
        "Unknown"
      ]
    },
    "limit": {
      "default": 20,
      "description": "Max results to return (1-50, default 20).",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "default": 0,
      "description": "Results to skip, for pagination (default 0).",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_metrics

USE WHEN you need a current, citable figure for the onchain agent ecosystem rather than a number from an article of unknown age. The ERC-8004 Identity Registry registered-agent count (read directly from Ethereum mainnet) and the curated Top Project Tokens index (only tokens of directory-listed projects — never the whole agent-token category or its aggregate market cap). Returns (json): { erc8004: { network, registered_agents, live, checked_at }, top_agent_tokens: [{ symbol, name, current_price, market_cap, price_change_percentage_24h, resource_slug }] }. Read-only.

Parameters2

token_limit	integer	optional	How many top project tokens to include (1-25, default 12).
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "token_limit": {
      "default": 12,
      "description": "How many top project tokens to include (1-25, default 12).",
      "type": "integer",
      "minimum": 1,
      "maximum": 25
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_wiki_page

USE WHEN asked to explain a crypto-agent concept — what x402 is, how agents hold wallets, what ERC-8004 does — and you want a sourced explainer you can cite. Returns a full wiki page by slug (summary, why it matters, how it works, key components, examples, risks, related resources/pages). Use onchain_agent_list_wiki_pages to find slugs. Returns (json): the full page object. Returns an error if the slug is unknown. Read-only. Example: { slug: "what-are-mcps" }

Parameters2

slug	string	required	The wiki page slug, e.g. 'what-are-mcps'.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "description": "The wiki page slug, e.g. 'what-are-mcps'."
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_search_agents

Search REGISTERED onchain agents in the Sato Agent Registry — running agents whose creators registered them for a Sato Agent Passport (distinct from the resource directory, which lists the things agents are built FROM). Filter by free-text query, chain, agent_type, or x402_only. Only human-review-listed agents are returned. Trust rule: registration is self-reported by the creator; verification_status distinguishes Self-Reported from evidence-reviewed Verified/Audited. Nothing here implies safety or performance. Returns (json): { total, agents: [{ sato_agent_id, slug, name, description, agent_type, chains_supported, stack, payment/x402 metadata, verification_status, profile_url, manifest_url }] }. Read-only. Example: { chain: "Base", x402_only: true }

Parameters5

query	string	optional	Free-text search across agent name, description, creator, stack, and type.
chain	string	optional	Filter to agents supporting this chain.
agent_type	string	optional	Filter by agent utility type: trading, research, defi, payments, security, social, workflow, gaming, data, coding.
x402_only	boolean	optional	True = only agents exposing an x402 payment endpoint.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Free-text search across agent name, description, creator, stack, and type.",
      "type": "string",
      "maxLength": 200
    },
    "chain": {
      "description": "Filter to agents supporting this chain.",
      "type": "string",
      "enum": [
        "Ethereum",
        "Base",
        "Solana",
        "Arbitrum",
        "Optimism",
        "Polygon",
        "Avalanche",
        "BNB Chain",
        "Cosmos",
        "Bitcoin",
        "Sui",
        "Aptos",
        "Near",
        "COTI",
        "Injective",
        "XRP Ledger",
        "Gnosis",
        "Hyperliquid",
        "Sei",
        "Starknet",
        "zkSync",
        "Monad",
        "MegaETH",
        "Berachain",
        "TON",
        "Tron",
        "Robinhood Chain",
        "Multichain",
        "Unknown"
      ]
    },
    "agent_type": {
      "description": "Filter by agent utility type: trading, research, defi, payments, security, social, workflow, gaming, data, coding.",
      "type": "string",
      "maxLength": 40
    },
    "x402_only": {
      "description": "True = only agents exposing an x402 payment endpoint.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_agent_passport

Get the full Sato Agent Passport manifest (sato.agent.manifest/v1) for one REGISTERED agent by slug: identity (sato_agent_id), agent types, chains, model/framework, the stack of Sato Hub directory resources it runs on, links, payment/x402 endpoint metadata, and verification + liveness status. Use onchain_agent_search_agents to find slugs. Payment metadata is self-configured by the creator — published for interoperability, not as an endorsement. Returns an error if the slug is unknown or the agent is not listed. Read-only. Example: { slug: "my-trading-agent" }

Parameters2

slug	string	required	The registered agent's slug, e.g. 'my-trading-agent'. Use onchain_agent_search_agents to find slugs.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "description": "The registered agent's slug, e.g. 'my-trading-agent'. Use onchain_agent_search_agents to find slugs."
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_recommend_stack

USE WHEN someone describes an agent they want to build and needs concrete components rather than general advice. Give it the goal in plain words; it returns a trust-ranked stack of real directory resources — bucketed into slots (framework, wallet, payments, trading, data, MCP tooling, security), each pick carrying its Sato Score, liveness, and deploy-spec status, plus honest gaps where the directory has no strong match. Ranking reflects openness/activity/verifiability — never a safety, quality, or returns judgment. Read-only. Example: { goal: "trading agent on Base with x402 payments", chain: "Base" }

Parameters5

goal	string	required	What the agent should do, in plain words — e.g. 'trading agent on Base with x402 payments'
chain	string	optional	Preferred chain (e.g. Base, Solana)
max_per_slot	integer	optional	Max picks per stack slot (default 3)
verified_only	boolean	optional	True = only picks whose documented install was reproduced in a container by Sato Hub. Slots with no verified pick are reported in `gaps` rather than widened.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 3,
      "maxLength": 300,
      "description": "What the agent should do, in plain words — e.g. 'trading agent on Base with x402 payments'"
    },
    "chain": {
      "description": "Preferred chain (e.g. Base, Solana)",
      "type": "string",
      "enum": [
        "Ethereum",
        "Base",
        "Solana",
        "Arbitrum",
        "Optimism",
        "Polygon",
        "Avalanche",
        "BNB Chain",
        "Cosmos",
        "Bitcoin",
        "Sui",
        "Aptos",
        "Near",
        "COTI",
        "Injective",
        "XRP Ledger",
        "Gnosis",
        "Hyperliquid",
        "Sei",
        "Starknet",
        "zkSync",
        "Monad",
        "MegaETH",
        "Berachain",
        "TON",
        "Tron",
        "Robinhood Chain",
        "Multichain",
        "Unknown"
      ]
    },
    "max_per_slot": {
      "description": "Max picks per stack slot (default 3)",
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "verified_only": {
      "description": "True = only picks whose documented install was reproduced in a container by Sato Hub. Slots with no verified pick are reported in `gaps` rather than widened.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "goal"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_list_wiki_pages

List all Onchain Agent wiki pages (slug, title, keyword, summary, last_updated). Returns (json): { total, pages: [...] }. Read-only.

Parameters1

response_format

string

optional

Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_changes

What changed in the Onchain Agent directory since a given date — additions, per-resource change events, and retirements. Use this to keep a local copy in sync instead of re-fetching the whole catalog. Returns (json): { since, until, window_days, counts:{added,changed,removed}, added:[...], changed:[{slug,name,url,events:[...]}], removed:[...], coverage:{...}, full_export }. COVERAGE (also stated in the response): `added` is exact. `updated` is a field-level diff of every catalog field between the snapshot on `baseline_date` and the live record — complete at daily resolution, so a quiet copy edit IS caught; store baseline_date as your cursor. `changed` is the richer event log (score moves, releases, verification) and explains WHY. `removed` is approximate. Mirror from added + updated + removed. Read-only. Examples: - "what's new this week" -> { since: "2026-08-23" } - "sync my copy" -> { since: <your last sync date> }

Parameters1

since

string

optional

Return everything that changed since this ISO date. Defaults to 14 days ago. Clamped to the 90-day supported window.

Raw schema

{
  "type": "object",
  "properties": {
    "since": {
      "description": "Return everything that changed since this ISO date. Defaults to 14 days ago. Clamped to the 90-day supported window.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_agent_economy

What is actually happening on-chain across the agent venues Sato Hub tracks — registries, launchpads, payment rails and account infrastructure — measured weekly from public chain reads. Returns (json): { week, as_of, rules, evidence_tiers, venues: [{ id, name, unit, entry_cost, measurable, overlaps_with, headline_safe, contracts:[...], chains:[{ chain, stages:[{ stage, value, unit, method, evidence_tier, sample_size, denominator, covered_days, publishable, caveat }] }], platforms:[...] }] }. HOW TO USE THESE NUMBERS. Never add them together: an ERC-8004 registration, an Olas staked service, a Virtuals launch and a Mech task are four different objects, and each venue's `unit` says which. Every number names its stage — "19,180 launched, 1,233 graduated" is true, "58,400 agents" is not. A null value means UNKNOWN, never zero. A rate whose sample_size is below 20 is returned with `publishable: false` and should not be quoted. Solana identity registries are covered as UPPER BOUNDS (program-account counts, the unit says so); Solana payment settlement is not covered by any row, and by transaction count x402 mostly settles there. Read-only. Cite https://satohub.ai/agent-economy. Examples: - "how many agents are actually registered onchain" -> {} - "what is happening on Base" -> { chain: "Base" } - "who is producing ERC-8004 registrations" -> { venue: "erc8004", include_platforms: true }

Parameters4

venue	string	optional	Restrict to one venue: erc8004, olas, virtuals, x402, erc4337_accounts, key_management, singularitynet, morpheus.
chain	string	optional	Restrict to one chain, e.g. Base, BNB Chain, Gnosis. Venue-level rows have no chain.
include_platforms	boolean	optional	Include the per-platform breakdown of who produced the registrations (agentURI attribution). Default false — it roughly doubles the response.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "venue": {
      "description": "Restrict to one venue: erc8004, olas, virtuals, x402, erc4337_accounts, key_management, singularitynet, morpheus.",
      "type": "string",
      "maxLength": 40
    },
    "chain": {
      "description": "Restrict to one chain, e.g. Base, BNB Chain, Gnosis. Venue-level rows have no chain.",
      "type": "string",
      "maxLength": 40
    },
    "include_platforms": {
      "description": "Include the per-platform breakdown of who produced the registrations (agentURI attribution). Default false — it roughly doubles the response.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_search_skills

Crypto-relevant agent skills from ClawHub and skills.sh, each with a static DISCLOSURE: hosts it contacts, whether it generates or handles private keys, whether it asks the user to paste a credential, whether it pipes a remote script into a shell, whether it grants itself unrestricted tools, whether it registers the agent with a third-party host, whether it schedules itself. Each flag carries evidence lines on the skill's page. Returns (json): { total, skills: [{ id, name, registry, canonical_url, installs, stars, disclosure_flags, hosts_contacted, declared_env, registry_scan, belongs_to_slug, skill_md_sha256, as_of }], note }. A disclosure is a description, not a safety verdict — a wallet skill that generates keys is doing its job, and no flags is not a clearance. The registry's own scan status is attributed to the registry. Read-only. Cite https://satohub.ai/skills. Examples: - "solana skills that don't touch keys" -> { query: "solana" } then filter disclosure_flags - "which skills phone home" -> { flag: "registers_with_third_party" } - "skills for Coinbase AgentKit" -> { slug: "coinbase-agentkit" }

Parameters6

query	string	optional	Free text over skill name, description, owner/repo and hosts contacted.
registry	string	optional	Restrict to one registry.
flag	string	optional	Only skills carrying this disclosure flag: pipes_remote_to_shell, executes_fetched_code, generates_or_handles_keys, solicits_credentials, reads_secret_paths, broad_tool_grant, registers_with_third_party, schedules_persistence.
slug	string	optional	Only skills that target this directory listing.
limit	integer	optional
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Free text over skill name, description, owner/repo and hosts contacted.",
      "type": "string",
      "maxLength": 120
    },
    "registry": {
      "description": "Restrict to one registry.",
      "type": "string",
      "enum": [
        "clawhub",
        "skillssh",
        "github"
      ]
    },
    "flag": {
      "description": "Only skills carrying this disclosure flag: pipes_remote_to_shell, executes_fetched_code, generates_or_handles_keys, solicits_credentials, reads_secret_paths, broad_tool_grant, registers_with_third_party, schedules_persistence.",
      "type": "string",
      "maxLength": 40
    },
    "slug": {
      "description": "Only skills that target this directory listing.",
      "type": "string",
      "maxLength": 120
    },
    "limit": {
      "default": 20,
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_trend

ANSWERS ONE QUESTION: is this measurement going up or down? Returns a bounded series (at most 30 points, default 8) for ONE venue, ONE chain and ONE stage from Sato Hub's own weekly (or daily) chain reads — each point with its date, value, sample_size and method. RULE ENFORCED: points are never summed across venues, chains or stages — the tool refuses to blend chains and tells you which chains exist when you omit one. A null point is UNKNOWN for that period, never zero. The weekly point is the citable one; daily points feed a trend and never a headline. Raw rows are not returned. Returns (json): { venue, chain, stage, grain, unit, points: [{ date, value, sample_size, method, evidence_tier }], direction_first_to_last, known_points, rules, as_of, source }. Read-only. Examples: - "are ERC-8004 registrations on Base growing" -> { venue: "erc8004", chain: "Base", stage: "registered" } - "x402 sellers week over week" -> { venue: "x402", chain: "Base", stage: "settled_to_catalogued_seller", points: 12 } - "do registered endpoints answer, day by day" -> { venue: "erc8004", chain: "Base", stage: "mcp_endpoint_answers", grain: "daily", points: 30 }

Parameters7

mode	string	optional	'stage' (default) is one venue/chain/stage series. 'movers' is the week's Sato Score movement across the directory — which listings rose, fell, crossed a tier, were scored for the first time, or answered our daily checks differently. In movers mode venue, chain and stage are ignored.
venue	string	optional	Venue id, e.g. erc8004, olas, virtuals, x402, erc4337_accounts. See onchain_agent_get_agent_economy for the catalogue.
chain	string	optional	Chain, e.g. Base, Ethereum, Gnosis. Required when the stage is measured on more than one chain — series are never blended across chains. Omit for venue-level rows.
stage	string	optional	Lifecycle stage, e.g. registered, launched, settled_to_catalogued_seller, mcp_endpoint_answers. Required in 'stage' mode.
points	integer	optional	How many most-recent points (1-30, default 8).
grain	string	optional	'weekly' (the citable series, default) or 'daily' (the trend grain; never a headline).
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "mode": {
      "default": "stage",
      "description": "'stage' (default) is one venue/chain/stage series. 'movers' is the week's Sato Score movement across the directory — which listings rose, fell, crossed a tier, were scored for the first time, or answered our daily checks differently. In movers mode venue, chain and stage are ignored.",
      "type": "string",
      "enum": [
        "stage",
        "movers"
      ]
    },
    "venue": {
      "description": "Venue id, e.g. erc8004, olas, virtuals, x402, erc4337_accounts. See onchain_agent_get_agent_economy for the catalogue.",
      "type": "string",
      "maxLength": 40
    },
    "chain": {
      "description": "Chain, e.g. Base, Ethereum, Gnosis. Required when the stage is measured on more than one chain — series are never blended across chains. Omit for venue-level rows.",
      "type": "string",
      "maxLength": 40
    },
    "stage": {
      "description": "Lifecycle stage, e.g. registered, launched, settled_to_catalogued_seller, mcp_endpoint_answers. Required in 'stage' mode.",
      "type": "string",
      "maxLength": 60
    },
    "points": {
      "default": 8,
      "description": "How many most-recent points (1-30, default 8).",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    },
    "grain": {
      "default": "weekly",
      "description": "'weekly' (the citable series, default) or 'daily' (the trend grain; never a headline).",
      "type": "string",
      "enum": [
        "weekly",
        "daily"
      ]
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_compare_listings

ANSWERS ONE QUESTION: how do these two directory listings compare on the axes Sato Hub tracks for both? Returns the SAME derived table the /compare pages render — category, chains, interfaces, standards, open-source status, listing status, last activity, last release, install proof, verification, Sato Score, GitHub stars — every cell read off the live records, never typed. RULE ENFORCED: there is NO winner field and none can be derived from the table; `caveat` is mandatory and names what the data cannot settle (for a curated pair, the comparison page's own caveat). The Sato Score is openness/activity/verifiability, not a safety, quality or returns grade. Returns (json): { a: { slug, name, liveness, observed_success_pct, sato_url }, b: {...}, rows: [{ label, a, b, note? }], caveat, rules, comparison_page, source }. Read-only. Example: { a: "coinbase-agentkit", b: "solana-agent-kit" }

Parameters3

a	string	required	First directory slug, e.g. 'coinbase-agentkit'.
b	string	required	Second directory slug, e.g. 'solana-agent-kit'.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "a": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "First directory slug, e.g. 'coinbase-agentkit'."
    },
    "b": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "Second directory slug, e.g. 'solana-agent-kit'."
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "a",
    "b"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_explain_number

ANSWERS ONE QUESTION: where does a published Sato Hub number come from? Returns one finding from the State of Onchain Agents report by slug — the figure with its stage, method, sample, as-of date, the SQL query that reproduces it, and its citable page at https://satohub.ai/numbers/<slug>. RULE ENFORCED: a number never travels without its stage, method, sample and date; it is never summed across venues, chains or stages. CITE THE URL in the payload, not this response. Returns an error while the report is unpublished. Returns (json): { slug, title, number, unit, stage, method, sample, lines, query, as_of, url, cite, rules }. Read-only. Example: { slug: "erc-8004-agents-registered-on-base" }

Parameters2

slug	string	required	The finding's slug — the last path segment of a satohub.ai/numbers/<slug> URL.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "The finding's slug — the last path segment of a satohub.ai/numbers/<slug> URL."
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_score_methodology

USE WHEN you are about to describe, apply or compare the Sato Score — or when asked how to tell whether a crypto-agent project is real, maintained or open — so you quote the rubric instead of guessing it. Returns the six components with their maximum points and what each measures, the tier cutoffs, what "provisional" means, what is deliberately NOT in the score, how it is computed and reproduced, and where a dispute goes. RULE ENFORCED: the Sato Score is a 0–100 measure of how OPEN, ACTIVE and VERIFIABLE a project is, from public evidence, recomputed daily. It is NOT a safety, security, quality, legitimacy or returns grade, and this tool says so in the payload. Self-reported claims earn nothing in it. CITE https://satohub.ai/sato-score when you explain it. Returns (json): { name, scale, components: [{ key, label, max, measures }], tiers, provisional, not_in_score, computed, reproduce, dispute, caveat, url }. Read-only.

Parameters1

response_format

string

optional

Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_get_listing_history

ANSWERS ONE QUESTION: has this listing been answering Sato Hub's daily checks, and has its tool inventory moved? Returns a bounded 30-day shape from the listing's observed record — days observed, share of OUR checks that succeeded, current state and streak — plus the MCP tool-inventory changes in the window (date, count after the change, added, removed) and the current Sato Score. RULE ENFORCED: success_rate_pct is the share of Sato Hub's own checks that succeeded, never "uptime" — a failure can be on our side. At most 30 entries; the daily rows are not returned (rule 24: shape, not rows). Absence of a record is unknown, not down. Pass `score_days` to add `score_series`: the daily Sato Score readings we captured for this listing, up to 365 days. A day nobody measured is ABSENT from the array rather than carried forward — a gap is a gap — and every move is labelled `project` or `methodology`, the latter meaning Sato Hub revised the scoring rubric that day and the movement is ours. Returns (json): { slug, days, observed: { days_observed, window_days, success_rate_pct, current_state, current_streak_days, last_check }, tool_history: [{ date, count, added, removed }], tools_now, tools_peak, trust_score, trust_tier, score_series, rules, sato_url }. Read-only. Example: { slug: "jupiter-mcp", days: 30, score_days: 90 }

Parameters4

slug	string	required	The resource slug, e.g. 'coinbase-agentkit'.
days	integer	optional	Look-back window in days (1-30, default 30) for the observed record and the tool inventory.
score_days	integer	optional	Include the daily Sato Score series over this many days (2-365). A day nobody measured is absent from the series, never carried forward. Omit for no series.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "The resource slug, e.g. 'coinbase-agentkit'."
    },
    "days": {
      "default": 30,
      "description": "Look-back window in days (1-30, default 30) for the observed record and the tool inventory.",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    },
    "score_days": {
      "description": "Include the daily Sato Score series over this many days (2-365). A day nobody measured is absent from the series, never carried forward. Omit for no series.",
      "type": "integer",
      "minimum": 2,
      "maximum": 365
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_preflight

USE WHEN you are about to install a package, clone a repo, connect to an MCP endpoint, pay an agent, or trade a token, and you want to know what is on record about it FIRST. Pass exactly one of repo, package, endpoint, agent or token. Returns a verdict — go | caution | no | unknown — with one evidence line per check, each naming the field it was read from and when that field was written. The rules are written down in lib/preflight.ts and cited by id in `rule`. RULE ENFORCED: a verdict names WHAT WAS CHECKED AND WHEN. It is never a security review, a quality judgment or a statement about returns, and `unknown` means Sato Hub holds no record — not that something is wrong. An unlisted endpoint gets ONE live handshake (initialize + tools/list, 8 s cap) and can never come back `go`: a handshake is not a record. For agent=<chain>:<id> we confirm the ERC-8004 registration exists, fetch its registration file, and report the services it DECLARES; only a declared MCP service is probed. TOKEN LANE (token + chain, EVM only): keyless chain reads — bytecode presence and size, the ERC-20 views, the Clanker v4 factory's OWN deployment record (`tokenDeploymentInfo`, not a bytecode heuristic), and the Uniswap v3 factory across the four standard fee tiers against wrapped native. Every field is nullable and a null carries the reason it is null. PERMANENTLY NULL, and said so in the evidence: holder concentration (no keyless public source — explorers are not scraped) and Uniswap v4 / non-Uniswap liquidity (a v4 poolId cannot be reconstructed without the PoolKey). The deployer address needs an optional explorer key. A pool existing is not depth; a locker holds a position on the terms its own code enforces. Nothing in this lane says safe, audited, rug or scam — those are not readings. SKILL LANE (skill): a skill is a DOCUMENT an agent follows, which is exactly why it is worth checking first — the ClawSwarm skills needed no malware, only text telling the agent to generate a wallet and post the private key. Evidence is the static disclosure the weekly sweep already produced: hosts the text names, whether it generates or handles keys, whether it asks for a credential, whether it pipes a remote script into a shell, what tools it grants itself — each finding WITH the lines that produced it — plus installs, when it was last seen in its registry, and whether a host it names belongs to a listed project. Nothing is fetched from a registry and no skill is executed. A DISCLOSURE DESCRIBES: it never says safe, it never says malicious, an empty flag list is "nothing matched" rather than a pass, and the registry's own scan result is attributed to that registry by name. Returns (json): { verdict, rule, target: { kind, value, slug, name, sato_url, verify_url }, evidence: [{ check, result, source_field, checked_at }], checked_at, caveat, rules, token?, skill? }. `token` and `skill` are the raw reports for those lanes. Read-only. Example: { repo: "coinbase/agentkit" } · { endpoint: "https://mcp.example.com/v1" } · { agent: "base:42" } · { token: "0x1bc0c42215582d5A085795f4baDbaC3ff36d1Bcb", chain: "Base" } · { skill: "clawhub/solana-wallet" }

Parameters8

repo	string	optional	A GitHub repository: a URL or bare owner/name, e.g. 'coinbase/agentkit'.
package	string	optional	An npm or PyPI package name, e.g. 'solana-agent-kit'. A trailing @version is ignored.
endpoint	string	optional	An https MCP endpoint URL. If it is not in the directory it gets a live initialize + tools/list handshake, capped at 8 seconds.
agent	string	optional	An ERC-8004 agent reference, <chain>:<id>, e.g. 'base:42'. Chains: Ethereum, Base, Arbitrum, Optimism, Polygon, BNB Chain, Avalanche, Gnosis, Robinhood Chain.
token	string	optional	An ERC-20 token contract address, e.g. '0x1bc0c42215582d5A085795f4baDbaC3ff36d1Bcb'. Needs `chain`. EVM only in v1.
chain	string	optional	Chain for `token`: Base, Ethereum, Arbitrum, Robinhood Chain. Anything else (Solana included) answers 'unknown' with the reason, never a guess.
skill	string	optional	An agent skill: '<registry>/<id>' (registries: clawhub, skillssh, skills.sh, skills-sh, github), or the skill id alone when it is unique. Reads the static disclosure already on record — nothing is fetched from a registry and no skill is ever executed.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "repo": {
      "description": "A GitHub repository: a URL or bare owner/name, e.g. 'coinbase/agentkit'.",
      "type": "string",
      "maxLength": 200
    },
    "package": {
      "description": "An npm or PyPI package name, e.g. 'solana-agent-kit'. A trailing @version is ignored.",
      "type": "string",
      "maxLength": 200
    },
    "endpoint": {
      "description": "An https MCP endpoint URL. If it is not in the directory it gets a live initialize + tools/list handshake, capped at 8 seconds.",
      "type": "string",
      "maxLength": 300
    },
    "agent": {
      "description": "An ERC-8004 agent reference, <chain>:<id>, e.g. 'base:42'. Chains: Ethereum, Base, Arbitrum, Optimism, Polygon, BNB Chain, Avalanche, Gnosis, Robinhood Chain.",
      "type": "string",
      "maxLength": 120
    },
    "token": {
      "description": "An ERC-20 token contract address, e.g. '0x1bc0c42215582d5A085795f4baDbaC3ff36d1Bcb'. Needs `chain`. EVM only in v1.",
      "type": "string",
      "maxLength": 120
    },
    "chain": {
      "description": "Chain for `token`: Base, Ethereum, Arbitrum, Robinhood Chain. Anything else (Solana included) answers 'unknown' with the reason, never a guess.",
      "type": "string",
      "maxLength": 40
    },
    "skill": {
      "description": "An agent skill: '<registry>/<id>' (registries: clawhub, skillssh, skills.sh, skills-sh, github), or the skill id alone when it is unique. Reads the static disclosure already on record — nothing is fetched from a registry and no skill is ever executed.",
      "type": "string",
      "maxLength": 300
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_route_swap

USE WHEN an agent needs to execute a swap and wants the venue chosen by liveness, verification and price, with the fee disclosed. Asks every aggregator adapter that quotes on the chain, in parallel, and returns the chosen venue's quote and calldata. RULE ENFORCED: a route is a RECOMMENDATION, not a verdict and not an assurance. `chosen_by` names every field it was chosen on — liveness, the observed record of Sato Hub's OWN daily checks (never "uptime"), verification state, then quoted price — with the field each was read from and `checked_at`. Nothing here is called best, safe or guaranteed. A quote is a quote, not a fill. NON-CUSTODIAL: this tool NEVER signs, holds, moves or broadcasts funds. It returns calldata the caller may sign. The Sato fee (3 bps stable-to-stable, 15 bps on any volatile leg) is a parameter on the aggregator's own quote, taken inside the swap transaction by the router, and is stated in `disclosure` before anything is signed. A failed, reverted or unsigned trade pays nothing. Returns (json): { route: { slug, name, listed, sato_url, liveness, observed_success_pct, install_verified }, quote: { venue, amount_in, amount_out, token_in, token_out, chain, calldata, tx, source_url }, sato_fee_bps, sato_fee_recipient, disclosure, chosen_by: [{ signal, value, source_field }], checked_at, alternatives, caveat, preflight, unavailable_venues, rules }. When no adapter answered: { unavailable, tried: [{ venue, reason }], checked_at, caveat }. Example: { chain: "Solana", token_in: "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v", token_out: "So11111111111111111111111111111111111111112", amount: "1000000" }

Parameters7

chain	string	required	Chain display name as the directory writes it, e.g. 'Base', 'Ethereum', 'Solana'.
token_in	string	required	Input token: a contract address (or Solana mint), or a symbol for the well-known stablecoins.
token_out	string	required	Output token: a contract address (or Solana mint), or a symbol.
amount	string	required	Sell amount in the INPUT token's base units (e.g. 1000000 = 1 USDC at 6 decimals).
slippage_bps	integer	optional	Slippage tolerance in basis points. Passed through to the venue.
taker	string	optional	The address that would sign. Some venues only return calldata when it is given; nothing is ever signed here.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "minLength": 1,
      "maxLength": 40,
      "description": "Chain display name as the directory writes it, e.g. 'Base', 'Ethereum', 'Solana'."
    },
    "token_in": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "Input token: a contract address (or Solana mint), or a symbol for the well-known stablecoins."
    },
    "token_out": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "Output token: a contract address (or Solana mint), or a symbol."
    },
    "amount": {
      "type": "string",
      "pattern": "^[0-9]{1,40}$",
      "description": "Sell amount in the INPUT token's base units (e.g. 1000000 = 1 USDC at 6 decimals)."
    },
    "slippage_bps": {
      "description": "Slippage tolerance in basis points. Passed through to the venue.",
      "type": "integer",
      "minimum": 0,
      "maximum": 5000
    },
    "taker": {
      "description": "The address that would sign. Some venues only return calldata when it is given; nothing is ever signed here.",
      "type": "string",
      "maxLength": 120
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "chain",
    "token_in",
    "token_out",
    "amount"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_route_agent

USE WHEN an agent needs another agent for a task and wants the pick explained by registration, answering service, feedback and liveness. Candidates are the listed Sato Agent Passports; the top 3 by the static ranking get one live MCP handshake before the pick is made. RULE ENFORCED: a route is a RECOMMENDATION, chosen by the listed fields at checked_at. `chosen_by` names every signal, its value and the exact field it was read from. An ERC-8004 registration proves a claim was made on-chain, not that the agent works; wallet_verified proves the key, not the product; a probe proves the declared service answered once. A null feedback count is unknown and ranks below every number, including zero. No job-outcome data exists yet. COVERAGE: agents registered on-chain but holding no Sato passport are absent from the pool — there is no keyless ERC-8004 enumeration callable from a request. Absent means unseen, not unqualified. When nothing qualifies the answer is `unknown` with a reason, never a low-confidence pick. Returns (json): { route: { agent, chosen_by: [{ signal, value, source_field }], checked_at, alternatives: [{ id, name, source, behind_on }], caveat } | { unknown, reason }, preflight, candidates_considered, probed, coverage, rules, caveat, checked_at }. Example: { capability: "trading", chain: "Base", requires_mcp: true }

Parameters5

capability	string	optional	What the work needs, in a word or two, e.g. 'trading', 'research', 'payments'. Matched against the candidate's name, declared agent types and declared services.
chain	string	optional	Chain the agent must claim, e.g. 'Base'. Filters the passport pool; it does not pull ERC-8004 registry rows (none are enumerable keyless).
requires_mcp	boolean	optional	Only candidates that DECLARE an MCP service. A declaration is not a working service — the top candidates get one live handshake.
requires_x402	boolean	optional	Only candidates that DECLARE x402 payment support. Declared, never settled or observed.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "capability": {
      "description": "What the work needs, in a word or two, e.g. 'trading', 'research', 'payments'. Matched against the candidate's name, declared agent types and declared services.",
      "type": "string",
      "maxLength": 120
    },
    "chain": {
      "description": "Chain the agent must claim, e.g. 'Base'. Filters the passport pool; it does not pull ERC-8004 registry rows (none are enumerable keyless).",
      "type": "string",
      "maxLength": 40
    },
    "requires_mcp": {
      "description": "Only candidates that DECLARE an MCP service. A declaration is not a working service — the top candidates get one live handshake.",
      "type": "boolean"
    },
    "requires_x402": {
      "description": "Only candidates that DECLARE x402 payment support. Declared, never settled or observed.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_route_launch

USE WHEN an agent or a builder is about to launch a token and wants the venue chosen on published facts, with the fee disclosed before anything is signed. Venues covered: Clanker v4, Bankr, Virtuals, Zora creator coins. RULE ENFORCED: a launch route is a RECOMMENDATION. `chosen_by` names every fact it was chosen on, each with the venue page it was read from and the date it was read (`facts_as_of`). A fee schedule says nothing about what a token will do after it launches, and nothing here is a security review or an audit. `null` is unknown and never zero — a venue that publishes no per-party fee split is unread, not generous. NON-CUSTODIAL: this tool NEVER deploys, signs, holds keys or moves funds. For the Clanker lane it returns a PREPARED CONFIG in the documented clanker-sdk v4 `deploy()` shape (the SDK is deliberately not a dependency of this service) which the caller reads and signs itself. Other venues are recommend-only: named, with a stated reason why no config is emitted. THE FEE: Sato's slice is one entry in the venue's own reward-recipient list — the deployer takes `10000 - bps`, Sato takes `bps`, and the two always total 10000. It is disclosed in `fee` on EVERY response, including when it is 0, and at 0 no Sato recipient appears in the config at all. A launch that is never signed pays nothing. Returns (json): { route_id, goal, chain, venue: { slug, name, lane, pool_fee_pct, creator_share_pct, programmable_fee_split, facts: [{ fact, source_url, as_of }], unconfirmed, docs_url }, reason, chosen_by: [{ signal, value, source_field }], checked_at, alternatives: [{ slug, name, behind_on }], fee: { bps, recipient, basis, disclosed }, prepared_deploy, prepared_deploy_unavailable, facts_as_of, caveat, rules }. When no venue documents the chain: { unavailable, tried, supported_chains, supported_goals, checked_at, caveat }. Example: { chain: "Base", goal: "agent_token", name: "Example Agent", symbol: "EXMPL", deployer: "0x…" }

Parameters8

chain	string	required	Chain display name as the directory writes it, e.g. 'Base', 'Arbitrum'.
goal	string	required	What is being launched. Matched against what each venue's own documentation covers.
name	string	optional	Token name. Required for a prepared deploy config; the caller's to choose, never invented here.
symbol	string	optional	Token symbol. Required for a prepared deploy config.
deployer	string	optional	The 0x address that will sign the deploy and hold the creator reward share. Without it no config is prepared — it cannot be inferred.
max_pool_fee_pct	number	optional	Reject venues whose PUBLISHED pool fee exceeds this percentage. A venue that publishes no fee is not excluded — unknown is not disqualifying.
require_programmable_fee_split	boolean	optional	Only venues documenting a programmable third-party recipient split.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "minLength": 1,
      "maxLength": 40,
      "description": "Chain display name as the directory writes it, e.g. 'Base', 'Arbitrum'."
    },
    "goal": {
      "type": "string",
      "enum": [
        "agent_token",
        "creator_coin",
        "meme",
        "utility"
      ],
      "description": "What is being launched. Matched against what each venue's own documentation covers."
    },
    "name": {
      "description": "Token name. Required for a prepared deploy config; the caller's to choose, never invented here.",
      "type": "string",
      "maxLength": 64
    },
    "symbol": {
      "description": "Token symbol. Required for a prepared deploy config.",
      "type": "string",
      "maxLength": 16
    },
    "deployer": {
      "description": "The 0x address that will sign the deploy and hold the creator reward share. Without it no config is prepared — it cannot be inferred.",
      "type": "string",
      "maxLength": 64
    },
    "max_pool_fee_pct": {
      "description": "Reject venues whose PUBLISHED pool fee exceeds this percentage. A venue that publishes no fee is not excluded — unknown is not disqualifying.",
      "type": "number"
    },
    "require_programmable_fee_split": {
      "description": "Only venues documenting a programmable third-party recipient split.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "chain",
    "goal"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_build_plan

USE WHEN someone describes the onchain agent they want and needs a plan they can act on rather than advice. Composes the other tools into one answer: the goal restated, a stack of REAL directory listings (each with its Sato Score, liveness, observed check record and `sato_url`), the deploy spec for every item that publishes one, a Preflight verdict per item, the first action when the goal implies one (a swap route, or a prepared token-launch config), the questions the user still has to answer, and the next steps. RULE ENFORCED: nothing in a plan is invented. Every component is a listing that exists; every number names the field it was read from; `null` is unknown and never zero. A Sato Score measures how open, active and verifiable a project is — it is not a security review, a quality judgment or a statement about returns. A Preflight `unknown` means Sato Hub holds no record, not that something is wrong. OURS, LABELLED: on a trading or swap goal the plan also carries an `execution` block for Sato OS — Sato Hub's OWN self-hosted trading OS, which we sell. It always carries `ours: true` and says "built by Sato Hub". It is NOT a stack pick: it fills the execution layer (where the stack runs), it is never ranked against a directory listing, and no listing loses a position to it. On any other intent `execution` is null. SKILLS: a plan also carries up to three crypto-relevant agent SKILLS matching the goal, each with the static disclosure of what its own text declares and does — hosts it names, keys it handles, credentials it asks for, remote scripts it pipes into a shell — and its own Preflight verdict under the S-rules. A skill is a document an agent follows, so this is the part a plan must not leave out. A DISCLOSURE DESCRIBES: it never says safe, and a scan that matched nothing is reported as matching nothing rather than as a pass. NON-CUSTODIAL: this tool never holds keys, signs, deploys or moves funds. A swap first-action carries a quote taken at a NOMINAL size — never the caller's size, which is the caller's to choose — and a launch first-action carries a config to read and sign yourself, with the fee disclosed before anything is signed. Returns (json): { goal, restatement, intent, intent_signals, chain, chain_source, budget_usd, constraints, matched_use_cases, stack: [{ slot, slot_label, slug, name, sato_url, verify_url, trust_score, trust_tier, liveness_ok, observed_success_pct, install_verified, why, deploy_spec, preflight: { verdict, rule, evidence, reason } }], skills: [{ id, name, registry, sato_url, installs, findings, hosts_contacted, disclosure, preflight, why }], execution, gaps, first_action, open_questions, next_steps, citation_ask, caveat, rules, checked_at, plan_url }. Read-only. SHAREABLE: pass `save: true` and the plan is stored and `save.share_url` returned — a permanent read-only page whose signature is re-checked server-side, so a plan can be handed to someone else without re-running anything. The page is noindex unless `public: true` is passed too. That signature proves Sato Hub produced those bytes on that date; it is not a claim about any project in the plan. Example: { goal: "a Base trading agent that swaps USDC to ETH on a signal", chain: "Base" }

Parameters7

goal	string	required	What the user wants to build, in plain words, e.g. 'a Base trading agent that swaps USDC to ETH on a signal'.
chain	string	optional	Chain the agent runs on, e.g. 'Base'. When omitted it is read from the goal, and the plan says which.
budget_usd	number	optional	Rough monthly budget in USD. Restated back in the plan; it does not filter the stack.
constraints	array	optional	Hard constraints to restate back, e.g. 'self-custody only', 'no API keys'.
save	boolean	optional	True stores the plan and returns `share_url`, a permanent read-only page at satohub.ai/plan/<id> with the plan's signature re-checked on it. The page is noindex unless `public` is also true — a goal is the caller's to publish, not ours. Nothing else about the plan changes.
public	boolean	optional	Only meaningful with `save`. True lets the shared page be indexed by search engines. Default false.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 3,
      "maxLength": 600,
      "description": "What the user wants to build, in plain words, e.g. 'a Base trading agent that swaps USDC to ETH on a signal'."
    },
    "chain": {
      "description": "Chain the agent runs on, e.g. 'Base'. When omitted it is read from the goal, and the plan says which.",
      "type": "string",
      "maxLength": 40
    },
    "budget_usd": {
      "description": "Rough monthly budget in USD. Restated back in the plan; it does not filter the stack.",
      "type": "number",
      "minimum": 0,
      "maximum": 1000000
    },
    "constraints": {
      "description": "Hard constraints to restate back, e.g. 'self-custody only', 'no API keys'.",
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 200
      }
    },
    "save": {
      "description": "True stores the plan and returns `share_url`, a permanent read-only page at satohub.ai/plan/<id> with the plan's signature re-checked on it. The page is noindex unless `public` is also true — a goal is the caller's to publish, not ours. Nothing else about the plan changes.",
      "type": "boolean"
    },
    "public": {
      "description": "Only meaningful with `save`. True lets the shared page be indexed by search engines. Default false.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "goal"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_route_lp

USE WHEN an agent is deciding which Uniswap pool and fee tier to provide liquidity to for a pair Sato Route already quotes, and wants the observed readings rather than an opinion. Returns every v3 pool the weekly LP lane found across the four standard fee tiers, each with its in-range liquidity, the swaps and volume actually counted, the window that count covered, and a fee-revenue proxy. RULE ENFORCED: a route is a RECOMMENDATION. `chosen_by` names every field the pick was made on and where each was read. THE LARGEST TERM IS MISSING ON PURPOSE: impermanent loss is not modelled, not approximated and not bounded, and it appears in `chosen_by` as an explicit null rather than being quietly omitted. A fee-revenue figure here is a PROXY — the pool's published fee rate multiplied by volume we counted, in token0's own units — and is never called revenue, an APR or a yield. Readings are never scaled up from the window covered to a full week. THE PICK: highest observed fee-revenue proxy per day per unit of in-range liquidity, among pools whose window could be read. When nothing is rankable the answer is `chosen: null` with a reason per pool, never a low-confidence pick. COVERAGE: Uniswap v3 on Base and Ethereum, for the pairs the router quotes. Uniswap v4 rows come back `null` WITH THEIR REASON — v4 is a singleton PoolManager and publishes no per-pair pool id — and null is unknown, never zero. Every non-Uniswap venue is outside the reading entirely. NON-CUSTODIAL: this tool never signs, holds, moves or provides liquidity, and nothing it returns is advice. Returns (json): { chain, pair, week, pools: [{ venue, pool, fee_tier_ppm, fee_tier_pct, liquidity, swaps_observed, volume_token0_observed, fee_revenue_proxy, fee_revenue_proxy_per_day, proxy_per_day_per_liquidity, token0, token1, covered_days, window_days, window_complete, method, evidence_tier, caveat, as_of, unknown_reason }], chosen: { pool, venue, fee_tier_ppm, because, chosen_by } | null, unranked, as_of, checked_at, caveat, rules }. When the pair is not collected: { unavailable, supported, checked_at, caveat }. Example: { chain: "Base", pair: "WETH-USDC" }

Parameters3

chain	string	required	Chain the pool is on. Collected: Base, Ethereum. Anything else answers `unavailable` with the covered list — unknown, never an empty result presented as none.
pair	string	required	The pair, either way round: 'WETH-USDC', 'usdc/weth', 'WBTC_WETH'. Only the pairs Sato Route quotes are collected.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "minLength": 1,
      "maxLength": 40,
      "description": "Chain the pool is on. Collected: Base, Ethereum. Anything else answers `unavailable` with the covered list — unknown, never an empty result presented as none."
    },
    "pair": {
      "type": "string",
      "minLength": 3,
      "maxLength": 40,
      "description": "The pair, either way round: 'WETH-USDC', 'usdc/weth', 'WBTC_WETH'. Only the pairs Sato Route quotes are collected."
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "chain",
    "pair"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_scaffold_plan

USE WHEN a plan has been agreed and the next step is a repository rather than more advice. Builds the plan (same brain as `onchain_agent_build_plan`) and writes it into a small starter repo, returned as a base64 zip plus a manifest naming every file. WHAT IS IN THE ARCHIVE: `README.md` (the plan rendered, every source URL, and the disclosure that Sato OS is ours) · `sato.plan.json` (the plan, signed at its own checked_at when a signing key is configured) · `.env.example` (every environment variable the stack's own deploy specs ask for, values BLANK, each under a comment naming which listing wants it) · `install.sh` (the documented install lines in order, each under its Preflight verdict) · `agent.config.json` (chain, tokens and the venue Sato Route chose, with `chosen_by`) · `.mcp.json` (Sato Hub's MCP server plus any MCP-native stack item) · `docker-compose.yml` ONLY when every stack item documents a docker install. RULE ENFORCED: nothing is generated. Every line is a template constant or a field of the plan, copied verbatim. An install line we were not told is never invented, and a value we do not hold is left blank with a comment rather than filled with a plausible default. THE ONE SAFETY RULE: a documented install that pipes a remote script into a shell (`curl … | sh`) is written as a COMMENTED line with a warning above it, never as an executable one, and it is reported in `quarantined_installs`. Uncommenting it is the reader's decision to take deliberately. DETERMINISTIC: the same plan produces a byte-identical archive — the timestamps come from the plan's `checked_at`, not the clock. NON-CUSTODIAL: the archive holds no keys and no secrets, and nothing here signs, deploys or moves anything. Returns (json): { name, files: [{ path, note, bytes }], env_names, quarantined_installs, zip_base64, bytes, plan: { goal, intent, chain, plan_url, checked_at, stack_slugs }, caveat }. Example: { goal: "a Base trading agent that swaps USDC to ETH on a signal", chain: "Base" }

Parameters6

goal	string	required	What the user wants to build, in plain words. The plan is built first, then written into files.
chain	string	optional	Chain the agent runs on, e.g. 'Base'. When omitted it is read from the goal.
budget_usd	number	optional	Rough monthly budget in USD. Restated in the plan; it does not filter the stack.
constraints	array	optional	Hard constraints to restate back, e.g. 'self-custody only'.
include_zip	boolean	optional	True (default) returns the archive base64-encoded alongside the manifest. False returns each file's contents inline instead.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 3,
      "maxLength": 600,
      "description": "What the user wants to build, in plain words. The plan is built first, then written into files."
    },
    "chain": {
      "description": "Chain the agent runs on, e.g. 'Base'. When omitted it is read from the goal.",
      "type": "string",
      "maxLength": 40
    },
    "budget_usd": {
      "description": "Rough monthly budget in USD. Restated in the plan; it does not filter the stack.",
      "type": "number",
      "minimum": 0,
      "maximum": 1000000
    },
    "constraints": {
      "description": "Hard constraints to restate back, e.g. 'self-custody only'.",
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 200
      }
    },
    "include_zip": {
      "description": "True (default) returns the archive base64-encoded alongside the manifest. False returns each file's contents inline instead.",
      "type": "boolean"
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "goal"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_watch

USE WHEN an agent (or the person it works for) wants to be told if something in its stack stops checking out — rather than re-running a Preflight on a schedule of its own. Goes through the SAME path the public form uses: same validation, same normalisation, same rate limit, one row per address and target. WHAT HAPPENS: the target is re-checked once a day by the public Preflight path, and an email is sent ONLY when the verdict CHANGES. Never on a schedule, never a digest. A transition INTO `unknown` (a check that failed to run) is recorded and never mailed — a failed check is not news about the target. FREE WHILE IN PREVIEW. A paid tier will be announced. No price is quoted here and none exists to quote. WHAT IS STORED: the normalised target, the address (a notice has to be delivered), an HMAC of it for counting, and the baseline verdict. No IP address and no name. Asking twice is idempotent; `action: "unsubscribe"` stops the mail and answers the same way whether a row existed or not. RULE ENFORCED: a verdict describes what was checked and when. It is not a safety, security or returns judgment, and a CHANGE is a change in what was observed — not a warning. Returns (json): { ok, action, target_kind, target, watch_id, verdict, notice, caveat }. Example: { target_kind: "package", target: "solana-agent-kit", notify_to: "me@example.com" }

Parameters5

target_kind	string	required	What is being watched: repo (owner/name or a GitHub URL), package (npm name), endpoint (an https URL), agent (an ERC-8004 reference like 'base:42').
target	string	required	The thing itself, in the spelling that kind takes. It is normalised, so two spellings of one repository become one watch.
notify_to	string	required	The email address the change notice goes to. Stored once for delivery and counted by an HMAC; it never enters telemetry or logs.
action	string	optional	subscribe (default) arms the watch; unsubscribe stops the mail for this address and target.
response_format	string	optional	Output format: 'markdown' (default) or 'json'.

Raw schema

{
  "type": "object",
  "properties": {
    "target_kind": {
      "type": "string",
      "enum": [
        "repo",
        "package",
        "endpoint",
        "agent"
      ],
      "description": "What is being watched: repo (owner/name or a GitHub URL), package (npm name), endpoint (an https URL), agent (an ERC-8004 reference like 'base:42')."
    },
    "target": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "The thing itself, in the spelling that kind takes. It is normalised, so two spellings of one repository become one watch."
    },
    "notify_to": {
      "type": "string",
      "minLength": 6,
      "maxLength": 254,
      "description": "The email address the change notice goes to. Stored once for delivery and counted by an HMAC; it never enters telemetry or logs."
    },
    "action": {
      "description": "subscribe (default) arms the watch; unsubscribe stops the mail for this address and target.",
      "type": "string",
      "enum": [
        "subscribe",
        "unsubscribe"
      ]
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (default) or 'json'.",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "target_kind",
    "target",
    "notify_to"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_submit_project

USE WHEN an agent has found, built or maintains a crypto-agent project that is not in the directory and wants it considered. This WRITES: it files the same row the /submit form files, into the same queue, and the daily triage run evaluates it through the same single apply path — probe the public evidence, validate against the listing schema, list it or hold it or decline it with a reason. WHAT HAPPENS NEXT: the website, the repository and any declared endpoint are probed from public sources. A project that clears that evidence is listed; one that does not is held for a person, or declined with the reason. If `contact_email` is given you get exactly ONE email, and only if it is listed. A hold sends nothing — silence means a person is looking. SUBMISSION IS NOT VERIFICATION. It is a request to be looked at. Being listed says what was observed about a project on a date, not that it is safe, audited, profitable or endorsed. Copy carrying profit, safety or risk claims is refused here rather than quietly cleaned up. DEDUPE: the website host and the repository are checked against the live directory and against submissions already waiting. A match returns that existing entry instead of filing a second row — correcting a listing that already exists goes through the claim flow on its page, which proves control of the domain first. LIMIT: 5 write calls an hour per caller. Nothing is written when it trips. Returns (json): { ok, duplicate, submission_id | slug, next, caveat }. Example: { name: "Example Agent Kit", website_url: "https://example.dev", repo_url: "https://github.com/example/kit", category: "Agent Framework", description: "A TypeScript toolkit for wiring agents to Base with viem and an MCP server.", chains: ["Base"] }

Parameters8

name	string	required	The project's name, as its own site writes it.
website_url	string	required	The project's own https site. Not a GitHub URL unless the repository IS the project's home.
repo_url	string	optional	The public source repository, when there is one: github.com/<owner>/<name>.
description	string	required	What it does, in plain words: what it is, who it is for, what it connects to. No profit, safety or performance claims — they are refused at the door.
category	string	required	The directory category it belongs in. Pick the closest; triage corrects it if you are wrong.
chains	array	optional	Chains it supports, by display name, e.g. ['Base','Solana'].
contact_email	string	optional	Where the one approval reply goes. Optional — without it nothing is ever sent, and there is no other notification.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 2,
      "maxLength": 80,
      "description": "The project's name, as its own site writes it."
    },
    "website_url": {
      "type": "string",
      "minLength": 4,
      "maxLength": 300,
      "description": "The project's own https site. Not a GitHub URL unless the repository IS the project's home."
    },
    "repo_url": {
      "description": "The public source repository, when there is one: github.com/<owner>/<name>.",
      "type": "string",
      "maxLength": 300
    },
    "description": {
      "type": "string",
      "minLength": 20,
      "maxLength": 1000,
      "description": "What it does, in plain words: what it is, who it is for, what it connects to. No profit, safety or performance claims — they are refused at the door."
    },
    "category": {
      "type": "string",
      "enum": [
        "Onchain Agent",
        "MCP",
        "Skill Repo",
        "Agent Framework",
        "Agent Launchpad",
        "Agent Marketplace",
        "Wallet Infrastructure",
        "DeFi Tool",
        "Trading Tool",
        "DAO Tool",
        "Research Tool",
        "Data Tool",
        "Security Tool",
        "Developer Tool",
        "API / SDK",
        "Research Paper",
        "Newsletter",
        "Community",
        "Other"
      ],
      "description": "The directory category it belongs in. Pick the closest; triage corrects it if you are wrong."
    },
    "chains": {
      "description": "Chains it supports, by display name, e.g. ['Base','Solana'].",
      "maxItems": 12,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 40
      }
    },
    "contact_email": {
      "description": "Where the one approval reply goes. Optional — without it nothing is ever sent, and there is no other notification.",
      "type": "string",
      "maxLength": 200
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "name",
    "website_url",
    "description",
    "category"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

onchain_agent_register_agent

USE WHEN an agent wants a public, machine-readable identity: an Agent Passport at satohub.ai/agents/<slug> plus a manifest at /api/agents/<slug>/manifest that another agent can read before deciding to work with it. TWO STEPS. Call it with `name` and `wallet_address` and no signature, and it returns the exact challenge to sign (EIP-191 personal_sign) and the `signed_at` that goes with it — the same string GET /api/agents/challenge returns, deterministic, valid 15 minutes. Call it again with `wallet_signature` and `signed_at` plus the registration fields, and the passport issues immediately. WITHOUT A SIGNATURE the registration is accepted and lands PENDING for human review; `contact_email` is required on that path. Signature verification is EVM-only for now — a Solana wallet can register, unsigned. WHAT THE SIGNATURE PROVES: control of the key. Nothing else. verification_status is Self-Reported on every passport issued here and no input can change it. Declared standards, endpoints and stack are claims; the endpoint gets one live probe and the wallet one on-chain lookup, and both are reported as what was observed, not as approval. LIMIT: 5 write calls an hour per caller. The challenge step counts, so fetch it once and sign it. Returns (json): unsigned first call { challenge, signed_at, expires_in_seconds, next }; registration { ok, slug, sato_agent_id, status, wallet_verified, passport_url, manifest_url, note }. Example: { name: "Example Agent", wallet_address: "0x…" } then the same plus { description, agent_type: ["Trading"], chains_supported: ["Base"], wallet_signature: "0x…", signed_at: "…" }

Parameters14

name	string	required	The agent's name. Bound into the signed challenge — changing it invalidates a signature.
description	string	optional	What the agent does (20-1000 chars). Required to register; omit it only on the challenge step.
agent_type	array	optional	What kind of work it does. At least one is required to register.
chains_supported	array	optional	Chains it operates on, by display name. At least one is required to register.
wallet_address	string	optional	The AGENT's own wallet: EVM (0x…) or a Solana-style base58 address. Required for the signature path — signature verification is EVM-only for now.
wallet_signature	string	optional	An EIP-191 personal_sign signature over the exact challenge this tool returns when called without one. Present: the passport issues immediately.
signed_at	string	optional	The `signed_at` value returned with the challenge. Valid for 15 minutes.
endpoint_url	string	optional	An MCP or A2A endpoint the agent serves. Probed once on registration; a declaration is not a working service.
website_url	string	optional	The agent's public page.
repo_url	string	optional	The agent's source repository, if public.
stack	array	optional	Directory slugs the agent is built from. Unknown slugs are an error, not silently dropped — the join is the point.
standards	array	optional	Standards the agent DECLARES support for. Declared, never verified.
contact_email	string	optional	Required when registering without a signature — an unsigned registration goes to a human, who may need to ask something.
response_format	string	optional	Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 3,
      "maxLength": 80,
      "description": "The agent's name. Bound into the signed challenge — changing it invalidates a signature."
    },
    "description": {
      "description": "What the agent does (20-1000 chars). Required to register; omit it only on the challenge step.",
      "type": "string",
      "maxLength": 1000
    },
    "agent_type": {
      "description": "What kind of work it does. At least one is required to register.",
      "maxItems": 4,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "Research / Market-Intel",
          "Trading",
          "DeFi / Yield",
          "Payments / Commerce",
          "Security",
          "Social / Content",
          "Workflow / Automation",
          "Gaming",
          "Data / Oracle",
          "Coding / Dev"
        ]
      }
    },
    "chains_supported": {
      "description": "Chains it operates on, by display name. At least one is required to register.",
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 40
      }
    },
    "wallet_address": {
      "description": "The AGENT's own wallet: EVM (0x…) or a Solana-style base58 address. Required for the signature path — signature verification is EVM-only for now.",
      "type": "string",
      "maxLength": 100
    },
    "wallet_signature": {
      "description": "An EIP-191 personal_sign signature over the exact challenge this tool returns when called without one. Present: the passport issues immediately.",
      "type": "string",
      "maxLength": 300
    },
    "signed_at": {
      "description": "The `signed_at` value returned with the challenge. Valid for 15 minutes.",
      "type": "string",
      "maxLength": 40
    },
    "endpoint_url": {
      "description": "An MCP or A2A endpoint the agent serves. Probed once on registration; a declaration is not a working service.",
      "type": "string",
      "maxLength": 300
    },
    "website_url": {
      "description": "The agent's public page.",
      "type": "string",
      "maxLength": 300
    },
    "repo_url": {
      "description": "The agent's source repository, if public.",
      "type": "string",
      "maxLength": 300
    },
    "stack": {
      "description": "Directory slugs the agent is built from. Unknown slugs are an error, not silently dropped — the join is the point.",
      "maxItems": 25,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 120
      }
    },
    "standards": {
      "description": "Standards the agent DECLARES support for. Declared, never verified.",
      "maxItems": 4,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "x402",
          "erc-8004",
          "mcp",
          "a2a"
        ]
      }
    },
    "contact_email": {
      "description": "Required when registering without a signature — an unsigned registration goes to a human, who may need to ask something.",
      "type": "string",
      "maxLength": 200
    },
    "response_format": {
      "default": "markdown",
      "description": "Output format: 'markdown' (human-readable, default) or 'json' (machine-readable).",
      "type": "string",
      "enum": [
        "markdown",
        "json"
      ]
    }
  },
  "required": [
    "name"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md198 KBView on GitHub

Onchain Agents

A scored index of 436 tools for building onchain AI agents — frameworks, MCP servers, wallets, payment rails, data feeds and trading venues, with activity and scores refreshed every day.

Use it in one command. Add it to Claude Code as an MCP server (Streamable HTTP, no key, no account):

claude mcp add --transport http satohub https://satohub.ai/api/mcp

Any other MCP client: point it at https://satohub.ai/api/mcp (39 tools, 35 of them read-only; other clients). No MCP client: curl -s https://satohub.ai/api/export/index.json returns the whole catalog as JSON.

What this is. 436 listings of what onchain AI agents are built from, across 28 chains, rendered daily from a public export. Discovery never lists anything on its own: a project is listed only after it passes an evidence check. Nothing in this repo can be bought — listing, order and score follow the same rules for every project (NEUTRALITY.md).
Token. Sato Hub has no token. A token using the Sato name is not ours.
What a Sato Score is. A 0–100 measure of how open, active and verifiable a project is, computed from evidence only. It is not a safety, quality, security or returns grade, and self-reported is never treated as verified.
How current it is. Re-rendered every day; Last activity is observed, not claimed. unknown means we could not measure it, never zero.
License. Catalog data CC-BY-4.0: reuse it anywhere, credit data by satohub.ai. Tooling MIT © Prime Signal LLC. JSON, CSV and NDJSON exports plus the MCP endpoint above — no key, no account.

Runnable agent packages

Whole agents, not components: each is a sealed, signed package you download and run on your own machine. The task is the package's own statement; the evidence label is what Sato Hub recorded, word for word. Agents find them with the MCP tools onchain_agent_search_listings and onchain_agent_inspect_listing.

Package	Task	Digest	Evidence	Get it
Onchain research report	Answers a question from a CLOSED corpus of supplied sources.	`sha256:ffbfc3729d4c…` `sha256:ffbfc3729d4c98d20364c841fdab7fd0f8ae3fccd6da4b7df77f5ff931ff2e16`	`task-tested · 2 platform rows`	page · download
Token activity monitor	Reads ERC-20 transfer logs for a token and a set of addresses over a block range, emits each event exactly once, keeps a reorg-aware cursor, and says 'unknown' rather than 'nothing happened' when the source could not be read.	`sha256:d0ae5a8b8eb7…` `sha256:d0ae5a8b8eb739d7569d678a84a128b74af8b4c37e1d300005003bb6475d18ba`	`task-tested · 2 platform rows`	page · download
Treasury balance monitor	Reads a public address list on an EVM chain and reports each holding in exact base units and exact native units, with an optional valuation only where a price source was actually supplied.	`sha256:64615a0b1fe7…` `sha256:64615a0b1fe7ac0ebc23cb637bb92c0dc07fe62ffb2c416a4896a458243e63b8`	`task-tested · 2 platform rows`	page · download

Verify the download against the published key before you run it: verify-release.mjs (node verify-release.mjs <package.zip> manifest.json).

The stack, layer by layer

Nine layers, from the runtime down to the venue. Each table is the highest-scored listings in that layer — highest-scored is not "best", and a score measures openness, activity and verifiability, nothing else. Checked says what we did: reproduced the documented install in an isolated container, or probed the live endpoint.

Agent runtimes & frameworks

The loop that runs the agent: prompting, memory, tool calls, scheduling. Pick this first — it decides what everything else plugs into.

Name	What it is	Chains	⬡ Score	Last activity	Checked
OpenClaw	Open-source self-hosted personal AI agent framework with a public skill…	—	92	today	install reproduced
Hermes Agent	Open-source self-improving AI agent from Nous Research with a built-in learning…	—	92	today	install reproduced
OpenAI Codex	OpenAI's agentic coding tool (CLI, IDE, and cloud) that runs agents and…	—	88	today	install reproduced
TradingAgents	An open-source multi-agent LLM framework that simulates a trading firm with…	—	88	today	live probed
ElizaOS	Open-source TypeScript framework for building crypto-native multi-agent systems.	Solana, Ethereum, Base +1	87	1 day ago	install reproduced
Fetch.ai uAgents	Python framework for lightweight autonomous agents with built-in…	Cosmos, Ethereum	87	4 days ago	install reproduced

_{Highest-scored in this layer, 6 of 30. All 30 →}

How to choose. Score measures openness and activity, not adoption. A closed-source framework scores low because its code cannot be read, not because it is worse at running agents.

Onchain action kits & SDKs

Libraries that turn an agent's decision into a signed transaction — swap, transfer, mint, stake — without writing the chain plumbing yourself.

Name	What it is	Chains	⬡ Score	Last activity	Checked
Coinbase AgentKit	Coinbase's toolkit for giving AI agents wallets and the ability to take onchain…	Base, Ethereum, Multichain	88	1 day ago	install reproduced
x402	Open HTTP 402 payment protocol, now at the x402 Foundation: agents pay per…	Base, Ethereum, Solana +2	87	6 days ago	install reproduced
Model Context Protocol (MCP)	Anthropic's open standard for connecting AI systems to external tools and data…	—	83	5 days ago	live probed
Alchemy	A blockchain developer platform providing node infrastructure plus NFT, Token…	Ethereum, Base, Solana +5	83	4 days ago	install reproduced
ClawRouter (BlockRun)	Local LLM router for agents: routes each request to the cheapest capable model…	Base, Solana	81	today	live probed
OpenSea Agent Skill	Official OpenSea agent skill and MCP server letting AI agents query NFT/token…	Ethereum, Base, Solana +3	81	2 days ago	live probed

_{Highest-scored in this layer, 6 of 51. All 51 →}

How to choose. Check the Chains column before the score: an action kit that does not cover your chain is the wrong kit at any score.

MCP servers

Tool servers your agent calls over the Model Context Protocol. This is the largest layer in the index and the fastest-moving.

Name	What it is	Chains	⬡ Score	Last activity	Checked
Hermes Agent	Open-source self-improving AI agent from Nous Research with a built-in learning…	—	92	today	install reproduced
BlockRun MCP	MCP server giving AI agents live data — markets, crypto, research, X — billed…	Base, Solana	91	today	install reproduced
CoinGecko MCP	Official CoinGecko MCP: hosted free/pro endpoints for live prices, market data…	Multichain	89	1 day ago	live probed
OpenAI Codex	OpenAI's agentic coding tool (CLI, IDE, and cloud) that runs agents and…	—	88	today	install reproduced
Coinbase AgentKit	Coinbase's toolkit for giving AI agents wallets and the ability to take onchain…	Base, Ethereum, Multichain	88	1 day ago	install reproduced
Trust Wallet Agent Kit (TWAK)	Non-custodial toolkit from Trust Wallet (MCP server, CLI, and SDK) that lets AI…	Ethereum, Base, Solana +6	87	today	install reproduced
DexPaprika MCP Server	Zero-config MCP access to DexPaprika's DEX data — tokens, liquidity pools, and…	Multichain	86	today	live probed
Skim	Skim is a data service for agents on Base.	Base	86	29 days ago	install reproduced

_{Highest-scored in this layer, 8 of 204. All 204 →}

How to choose. An MCP server is a remote process you hand your agent's tool calls to. Read what it asks for — a key, a signer, shell access — before you connect it.

Wallets, keys & permissions

Where the agent's key lives and what it is allowed to do: embedded wallets, MPC, smart accounts, session keys and spend permissions.

Name	What it is	Chains	⬡ Score	Last activity	Checked
Bankr	Crypto execution layer and cross-chain wallet that lets agents and users trade…	Base, Ethereum, Polygon +7	87	today	install reproduced
Trust Wallet Agent Kit (TWAK)	Non-custodial toolkit from Trust Wallet (MCP server, CLI, and SDK) that lets AI…	Ethereum, Base, Solana +6	87	today	install reproduced
0xGasless AgentKit	Toolkit giving AI agents gasless access to crypto wallets and onchain…	BNB Chain, Avalanche, Base	86	12 days ago	install reproduced
Privy	Embedded and server wallet infrastructure used to give agents secure key…	Ethereum, Base, Solana +1	83	4 days ago	install reproduced
Turnkey	Secure key management infrastructure with policy controls, commonly used for…	Ethereum, Base, Solana +1	83	4 days ago	install reproduced
Q402 (Quack AI)	Gasless stablecoin payment relay and managed Agent Wallets across 12 EVM chains…	BNB Chain, Ethereum, Avalanche +4	77	8 days ago	install reproduced

_{Highest-scored in this layer, 6 of 33. All 33 →}

How to choose. The score says nothing about custody. Read the open-source status and the project's own docs on who can move funds; this index does not audit key handling.

Data, RPC & indexing

What the agent knows before it acts: RPC access, market data, chain indexing, wallet and token analytics.

Name	What it is	Chains	⬡ Score	Last activity	Checked
CoinGecko MCP	Official CoinGecko MCP: hosted free/pro endpoints for live prices, market data…	Multichain	89	1 day ago	live probed
DexPaprika MCP Server	Zero-config MCP access to DexPaprika's DEX data — tokens, liquidity pools, and…	Multichain	86	today	live probed
Skim	Skim is a data service for agents on Base.	Base	86	29 days ago	install reproduced
Zerion	Wallet and DeFi data provider offering portfolio, positions, transactions, PnL…	Ethereum, Base, Arbitrum +8	85	4 days ago	install reproduced
Gate MCP Server	Official Gate MCP: hosted endpoints for market data, info, and news, plus…	Multichain	84	5 months ago	live probed
Boar Blockchain MCP	Blockchain infrastructure MCP from Boar Network, with setup guides and…	Multichain	84	5 months ago	live probed

_{Highest-scored in this layer, 6 of 75. All 75 →}

Payments & agent commerce

How agents pay and get paid: x402 (HTTP 402 plus stablecoin), agent commerce protocols, and the stablecoin rails underneath.

Name	What it is	Chains	⬡ Score	Last activity	Checked
BlockRun MCP	MCP server giving AI agents live data — markets, crypto, research, X — billed…	Base, Solana	91	today	install reproduced
Coinbase AgentKit	Coinbase's toolkit for giving AI agents wallets and the ability to take onchain…	Base, Ethereum, Multichain	88	1 day ago	install reproduced
x402	Open HTTP 402 payment protocol, now at the x402 Foundation: agents pay per…	Base, Ethereum, Solana +2	87	6 days ago	install reproduced
Bankr	Crypto execution layer and cross-chain wallet that lets agents and users trade…	Base, Ethereum, Polygon +7	87	today	install reproduced
Trust Wallet Agent Kit (TWAK)	Non-custodial toolkit from Trust Wallet (MCP server, CLI, and SDK) that lets AI…	Ethereum, Base, Solana +6	87	today	install reproduced
0xGasless AgentKit	Toolkit giving AI agents gasless access to crypto wallets and onchain…	BNB Chain, Avalanche, Base	86	12 days ago	install reproduced

_{Highest-scored in this layer, 6 of 123. All 123 →}

How to choose. x402 support in this index means the standard is declared. Whether an endpoint actually answers HTTP 402 is measured separately — see Numbers this week.

Identity, discovery & standards

How an agent is identified and found by other agents: ERC-8004 registration, MCP discovery, A2A agent cards.

Name	What it is	Chains	⬡ Score	Last activity	Checked
Bankr	Crypto execution layer and cross-chain wallet that lets agents and users trade…	Base, Ethereum, Polygon +7	87	today	install reproduced
0xGasless AgentKit	Toolkit giving AI agents gasless access to crypto wallets and onchain…	BNB Chain, Avalanche, Base	86	12 days ago	install reproduced
Model Context Protocol (MCP)	Anthropic's open standard for connecting AI systems to external tools and data…	—	83	5 days ago	live probed
Self Protocol	Open-source zero-knowledge identity protocol (passport-based proof of…	Multichain	80	14 days ago	install reproduced
Agentic Commerce Protocol (ACP)	Open standard maintained by OpenAI and Stripe for connecting buyers, their AI…	—	77	2 months ago	live probed
Q402 (Quack AI)	Gasless stablecoin payment relay and managed Agent Wallets across 12 EVM chains…	BNB Chain, Ethereum, Avalanche +4	77	8 days ago	install reproduced

_{Highest-scored in this layer, 6 of 35. All 35 →}

How to choose. Registering an identity proves a key controls a record. It is not a claim about the agent behind it, and nothing in this layer verifies behaviour.

Security & preflight

Checks you run before an agent installs, connects, signs or trades: contract and token screening, endpoint checks, monitoring.

Name	What it is	Chains	⬡ Score	Last activity	Checked
Agent Skills Hub	A registry of AI agent skills that applies automated source-code scanning and…	—	81	13 days ago	install reproduced
Self Protocol	Open-source zero-knowledge identity protocol (passport-based proof of…	Multichain	80	14 days ago	install reproduced
GoPlus AgentGuard	MIT-licensed runtime guard for AI coding agents: hook-level action blocking, a…	—	77	today	install reproduced
PRXVT	Open-source privacy SDK that adds unlinkable, zero-knowledge payments on top of…	Ethereum, Base, Polygon	68	—	install reproduced
ChainAware	Pre-built MCP blockchain capability modules giving agents fraud detection, AML…	Polygon, Ethereum, BNB Chain +4	67	1 month ago	live probed
COTI	Privacy infrastructure that gives MCP-compatible agents private wallets…	COTI, Ethereum	67	4 days ago	live probed

_{Highest-scored in this layer, 6 of 15. All 15 →}

How to choose. Nothing in this layer makes an agent safe. These tools surface signals; the decision, and the loss, stay yours.

Trading & DeFi venues

Where the agent actually trades: DEXs, aggregators, perps, lending and yield venues with programmatic access.

Name	What it is	Chains	⬡ Score	Last activity	Checked
Raydium	Solana AMM and DEX with an open-source TypeScript SDK V2 and public…	Solana	95	6 days ago	install reproduced
Jupiter	Solana swap aggregator that routes trades across DEXs via a widely used API and…	Solana	84	1 day ago	install reproduced
CloddsBot	Open-source autonomous AI trading agent operating across 1000+ markets…	Solana, Base, Ethereum +4	83	10 days ago	install reproduced
Orca	Solana concentrated-liquidity AMM (Whirlpools) with open-source TypeScript and…	Solana	83	4 days ago	live probed
dYdX	Perpetual futures DEX running on its own Cosmos SDK app-chain with…	Cosmos, Ethereum, Base +5	83	8 days ago	live probed
Drift Protocol	Open-source Solana perpetual futures DEX with TypeScript and Python SDKs and a…	Solana	81	2 months ago	install reproduced

_{Highest-scored in this layer, 6 of 55. All 55 →}

How to choose. No performance, returns or profitability is measured here, and none is implied by a score.

Starting stacks

Five ways the layers fit together, each built only from listings in this index and picked by the highest Sato Score in each layer. These are examples, not endorsements — we have not run these combinations end to end, and a higher score does not mean a better fit for your problem.

Trade on Base — An agent that watches a market and swaps on Base.
Runtime ElizaOS → Actions Coinbase AgentKit → Wallet Bankr → Data CoinGecko MCP → Venue CloddsBot
Trade on Solana — The same shape, on Solana.
Runtime ElizaOS → Actions Coinbase AgentKit → Wallet Bankr → Data CoinGecko MCP → Venue Raydium
Get paid per call — An agent that sells a service and settles over x402.
Runtime OpenClaw → Tools Hermes Agent → Wallet Bankr → Payments BlockRun MCP → Identity 0xGasless AgentKit
Research and report — A read-only agent: no keys, no signing, chain data in and text out.
Runtime OpenClaw → Tools Hermes Agent → Data CoinGecko MCP → Checks Agent Skills Hub
Discoverable by other agents — An agent other agents can find, verify and call.
Runtime OpenClaw → Identity Bankr → Tools Hermes Agent → Payments BlockRun MCP

Per-layer pages with every listing: docs/index.md · per-listing pages: docs/listings/ · the full index is below.

Onchain Agents — the scored, daily-updated index of the crypto agent stack

436 resources · 28 chains · 433 scored · 161 independently checked · updated 2026-09-29

**433 scored** (evidence-only Sato Score, every product) · **161 independently checked ✓** (99 with an install reproduced in an isolated container; the rest by evidence review or a live endpoint probe) — and growing.

_{Every product listing carries a Sato Score — a 0–100 measure of how open, active, and verifiable it is. Independently checked means we reproduced its documented install in an isolated container, reviewed its verification evidence, or probed its live endpoint ourselves.}

Follow SatoHub on X

🔌 Query it from your agent — one click:

_{Claude Desktop: paste https://satohub.ai/api/mcp into Settings → Connectors. Claude Code: claude mcp add --transport http satohub https://satohub.ai/api/mcp. Everything else → MCP quickstart}

🛠️ Build your agent — Agent Architect · _{describe it in a sentence, get the stack → satohub.ai/build}

🖥️ SATO OS — Onchain Agent Mission Control · _{run it on any chain, any model, your machine}

An agent querying the index live over MCP

Built for agents as much as humans: a stable data/index.json (versioned schema), data/index.csv, llms.txt, and a live MCP endpoint your agent can query directly.

curl -s https://satohub.ai/api/export/index.json | jq '.resources[0]'

Use the data

Surface	What it does	Call it
MCP	39 tools over Streamable HTTP — search the index, read agent-economy numbers, look up a Passport, run a Preflight, ask for a route	`https://satohub.ai/api/mcp` · quickstart
Skill / plugin	the same tools plus a guide on when to use them, for Claude Code, Codex, Cursor, Hermes	`npx skills add satohubai/sato-hub-skill` · `/plugin marketplace add satohubai/sato-plugins`
Preflight	check a repo, package, MCP endpoint, ERC-8004 agent or ERC-20 token before you install, connect, pay or trade — every verdict names the rule that decided it, and `unknown` stays unknown	`GET https://satohub.ai/api/preflight` · the page
Preflight in CI	the same check across a whole lockfile on every push, SARIF findings, plus a badge. `unknown` can never fail your build	`satohubai/preflight-action` · `POST https://satohub.ai/api/preflight/batch`
Sato Check	before a crypto package, MCP server or skill is installed: does it take your key, does your key leave, can it move funds on its own, what changed — each answer backed by declared / traced / observed evidence (a sandbox with planted, never-funded test keys). It describes; it is never a safety rating	`POST https://satohub.ai/api/check/install` · MCP `onchain_agent_check_install` · the page
Sato Route	which venue to swap, hire an agent, launch a token or pay over x402 — the fee disclosed (including at zero) and every reason named. Recommend-only: it signs nothing and holds nothing	`GET https://satohub.ai/api/route/{swap,agent,launch,x402,lp}` · the page
Sato Swap	a swap that can refuse: both tokens, the venue and the recipient checked against your policy, the route simulated, then an UNSIGNED transaction or the rule that withheld one. `unknown` refuses by default	`POST https://satohub.ai/api/swap/quote` · the method
Sato Bot	a goal in plain words → a build plan made of real listings from this index	`/satobot` · `POST https://satohub.ai/api/satobot/plan`
Deploy spec	the machine-readable install manifest behind the ✓ column — what a project installs as, and what we reproduced	the standard
Signed responses	responses can be signed Ed25519 so a downstream agent can verify a figure came from here unaltered	JWKS · key metadata
Bulk export	the whole catalog, JSON · CSV · NDJSON, CC-BY-4.0	`https://satohub.ai/api/export/index.json` · all datasets · OpenAPI

No key, no account, no rate-limit deal to sign. A Sato Score is a measure of how open, active and verifiable a project is — not a safety, quality or returns grade.

Swap through a gate

An agent that can trade is an agent that can be talked into trading. Sato Swap is the other answer: the agent never holds a key, and what it asks for is an unsigned transaction. One call checks four targets — both tokens, the venue endpoint and the recipient — applies the owner's policy server-side, simulates the route, and returns either an unsigned object or the rule under which one was withheld. unknown refuses by default, and every refusal names the rule, the limit and the value it read. Nothing in the path holds a key, signs or broadcasts. The method · full rules.

Legend

⬡ Score — the Sato Score: a 0–100 evidence-based measure of how open, active, and verifiable a project is. It is not a safety, quality, or returns grade (NEUTRALITY.md). Click a score for the full report.
Activity — observed liveness: 🟢 Active (≤30d) · 🟡 Recent (≤90d) · 🟠 Quiet (≤1y) · ⚪ Dormant.
★ — GitHub stars (refreshed daily).
✓ — install reproduced by our Docker verification harness (methodology).
Every score links to the project's page on satohub.ai — full detail, provenance, and score history live there.
Want the stack picked for you? The Builder turns "what my agent should do" into a grounded plan from this index.

Index

Agent Frameworks (30)
MCP Servers (141)
Wallet Infrastructure (33)
Trading & DeFi (55)
Data & APIs (89)
Developer Tools (22)
Skills & Plugins (30)
Launchpads & Marketplaces (10)
Security (15)
Live Onchain Agents (directory) (6)
Research & Reference (3)
Other (2)
Runnable agent packages
The stack, layer by layer
Starting stacks
Use the data
⬡ Top of the index
📈 Movers (7d)
📊 Numbers this week
Live agents (Passport registry)
Standards & protocols
New this week
Community
Support the index

Top of the index

_{Openness, activity, and verifiability — not a safety grade.}

Name	Category	What it is	Chains	⬡ Score	Activity	★	✓
Raydium	Trading Tool	Solana AMM and DEX with an open-source TypeScript SDK V2 and public trade/routing API.	Solana	⬡ 95	🟢 Active	★ 349	✓
OpenClaw	Agent Framework	Open-source self-hosted personal AI agent framework with a public skill registry (ClawHub) that runs across…	—	⬡ 92	🟢 Active	★ 390.7k	✓
Hermes Agent	Agent Framework	Open-source self-improving AI agent from Nous Research with a built-in learning loop and one-step migration…	—	⬡ 92	🟢 Active	★ 249.5k	✓
BlockRun MCP	MCP	MCP server giving AI agents live data — markets, crypto, research, X — billed per call via x402 micropayments.	Base, Solana	⬡ 91	🟢 Active	★ 395	✓
CoinGecko MCP	MCP	Official CoinGecko MCP: hosted free/pro endpoints for live prices, market data, and on-chain DEX analytics.	Multichain	⬡ 89	🟢 Active	★ 58
OpenAI Codex	Agent Framework	OpenAI's agentic coding tool (CLI, IDE, and cloud) that runs agents and connects to MCP servers and skills.	—	⬡ 88	🟢 Active	★ 126.3k	✓
TradingAgents	Agent Framework	An open-source multi-agent LLM framework that simulates a trading firm with analyst, trader, and…	—	⬡ 88	🟢 Active	★ 108.8k
Coinbase AgentKit	Developer Tool	Coinbase's toolkit for giving AI agents wallets and the ability to take onchain actions.	Base, Ethereum, Multichain	⬡ 88	🟢 Active	★ 1.3k	✓
ElizaOS	Agent Framework	Open-source TypeScript framework for building crypto-native multi-agent systems.	Solana, Ethereum, Base +1	⬡ 87	🟢 Active	★ 19.4k	✓
x402	API / SDK	Open HTTP 402 payment protocol, now at the x402 Foundation: agents pay per request in stablecoins, and by a…	Base, Ethereum, Solana +2	⬡ 87	🟢 Active	★ 6.6k	✓
Fetch.ai uAgents	Agent Framework	Python framework for lightweight autonomous agents with built-in crypto-economic features.	Cosmos, Ethereum	⬡ 87	🟢 Active	★ 1.6k	✓
Bankr	Wallet Infrastructure	Crypto execution layer and cross-chain wallet that lets agents and users trade, bridge, and manage assets via…	Base, Ethereum, Polygon +7	⬡ 87	🟢 Active	★ 1.2k	✓
GOAT SDK	Skill Repo	Crossmint's open-source library of onchain actions (tools) for AI agents across chains.	Ethereum, Base, Solana +1	⬡ 87	🟢 Active	★ 1.0k	✓
Trust Wallet Agent Kit (TWAK)	Wallet Infrastructure	Non-custodial toolkit from Trust Wallet (MCP server, CLI, and SDK) that lets AI agents read and transact…	Ethereum, Base, Solana +6	⬡ 87	🟢 Active	★ 101	✓
Olas (Autonolas)	Agent Framework	Network and framework for co-owned autonomous agent services operating onchain.	Ethereum, Gnosis, Base +1	⬡ 87	🟢 Active	—	✓

⬆ Back to Index

Agent Frameworks

_{30 entries · build & run agents — onchain-native frameworks and general harnesses · Related: Skills & Plugins · Developer Tools · Browse + filter on satohub.ai →}

Name	What it is	Chains	⬡ Score	Activity	★	✓
OpenClaw	Open-source self-hosted personal AI agent framework with a public skill registry (ClawHub) that runs across…	—	⬡ 92	🟢 Active	★ 390.7k	✓
Hermes Agent	Open-source self-improving AI agent from Nous Research with a built-in learning loop and one-step migration…	—	⬡ 92	🟢 Active	★ 249.5k	✓
OpenAI Codex	OpenAI's agentic coding tool (CLI, IDE, and cloud) that runs agents and connects to MCP servers and skills.	—	⬡ 88	🟢 Active	★ 126.3k	✓
TradingAgents	An open-source multi-agent LLM framework that simulates a trading firm with analyst, trader, and…	—	⬡ 88	🟢 Active	★ 108.8k
ElizaOS	Open-source TypeScript framework for building crypto-native multi-agent systems.	Solana, Ethereum, Base +1	⬡ 87	🟢 Active	★ 19.4k	✓
Fetch.ai uAgents	Python framework for lightweight autonomous agents with built-in crypto-economic features.	Cosmos, Ethereum	⬡ 87	🟢 Active	★ 1.6k	✓
Olas (Autonolas)	Network and framework for co-owned autonomous agent services operating onchain.	Ethereum, Gnosis, Base +1	⬡ 87	🟢 Active	—	✓
IntentKit	Open-source, self-hosted framework for running collaborative clusters of onchain AI agents.	—	⬡ 86	🟢 Active	★ 6.5k	✓
Claude Code	Anthropic's agentic command-line coding tool that runs agents and loads Agent Skills, including onchain…	—	⬡ 84	🟢 Active	★ 148.3k	✓
Almanak	An AI-agent framework and non-custodial vault protocol for designing, backtesting, and deploying automated…	Multichain, Ethereum, Arbitrum +8	⬡ 83	🟢 Active	★ 61	✓
NEAR Shade Agent Framework	Framework for TEE-hosted agents that hold assets and sign on many chains via NEAR chain signatures, with…	Near, Ethereum, Bitcoin +2	⬡ 75	🟢 Active	★ 2
Arbitrum Vibekit	Arbitrum-native, MCP-first agent framework with A2A and x402 support, backed by an Arbitrum Foundation grant…	Arbitrum	⬡ 72	🟡 Recent	★ 53
Lucid Agents	Commerce SDK for bootstrapping AI agents that can pay, sell, and transact onchain.	Base, Ethereum, Solana	⬡ 71	🟡 Recent	★ 198	✓
OpenServ	TypeScript SDK and platform for building, orchestrating, and monetizing collaborative AI agents.	Multichain	⬡ 71	🟠 Quiet	★ 137	✓
IronClaw	NEAR AI's open-source secure agent runtime that runs agent workloads inside hardware TEEs on NEAR AI Cloud.	Near	⬡ 68	🟢 Active	★ 12.6k
Daydreams	Framework and tooling for building AI agents for onchain commerce.	—	⬡ 66	🟠 Quiet	★ 620	✓
GAME SDK (Virtuals Protocol)	Virtuals Protocol's official Python SDK for building autonomous agents with planning, worker, and function…	Base	⬡ 64	🟠 Quiet	★ 100	✓
Grok CLI	Open-source terminal coding agent for the xAI Grok API — community-built, not affiliated with xAI.	—	⬡ 62	🟡 Recent	★ 3.4k
Starknet Agentic	Official Starknet-ecosystem infra for self-custodial agents: Cairo contracts, MCP/A2A runtimes, and…	Starknet	⬡ 60	🟢 Active	★ 80
LumoKit	Lightweight AI toolkit framework offering on-chain actions and research abilities for Solana.	Solana	⬡ 60	⚪ Dormant	★ 6
Snak (Starknet Agent Kit)	NestJS-based toolkit for building AI agents that interact with Starknet, supporting multiple LLM providers.	Starknet	⬡ 59	🟠 Quiet	★ 96
Injective Agents	A platform for deploying autonomous AI trading agents on Injective with onchain identity, order-book trading…	Injective, Cosmos	⬡ 58	⚪ Dormant	★ 46
Ping Agent Kit	Open-source Solana agent-integration kit with a plugin architecture spanning tokens, NFTs, DeFi, and Blinks.	Solana	⬡ 56	⚪ Dormant	★ 4
Warden Protocol	A Cosmos SDK Layer 1 with EVM compatibility positioned as a settlement and distribution layer for AI agents.	Cosmos, Ethereum, Base +2	⬡ 56	—	—
Cambrian Agent Kit	TypeScript SDK giving AI agents direct access to Sei DeFi protocols: swaps, lending, staking, and perps.	Sei	⬡ 51	⚪ Dormant	★ 11
Wayfinder	Omnichain protocol that lets AI agents navigate blockchains and execute transactions via natural-language…	Multichain, Arbitrum, Base +1	⬡ 51	—	—
listen (DeFAI toolkit)	Rust toolkit pairing the rig LLM framework with Solana trading primitives, including Jito bundle submission.	Solana	⬡ 49	🟠 Quiet	★ 1.1k
Spectral Syntax	A no-code platform from Spectral Labs that turns natural-language prompts into autonomous onchain agents with…	Base, Ethereum	⬡ 42	—	—
Manus	General-purpose autonomous AI agent that executes multi-step tasks and can run onchain agent skills.	—	⬡ 41	—	—
Cod3x	A DeFAI platform to create no-code AI agents that translate natural-language intent into onchain DeFi…	Multichain, Hyperliquid, Arbitrum	⬡ 31	—	—

⬆ Back to Index

MCP Servers

_{141 entries · plug-in tool servers your agent calls over the Model Context Protocol · Related: Skills & Plugins · Data & APIs · Browse + filter on satohub.ai →}

Trading & DeFi (56)

Name	What it is	Chains	⬡ Score	Activity	★	✓
CoinGecko MCP	Official CoinGecko MCP: hosted free/pro endpoints for live prices, market data, and on-chain DEX analytics.	Multichain	⬡ 89	🟢 Active	★ 58
DexPaprika MCP Server	Zero-config MCP access to DexPaprika's DEX data — tokens, liquidity pools, and OHLCV across 33 chains.	Multichain	⬡ 86	🟢 Active	★ 42
Gate MCP Server	Official Gate MCP: hosted endpoints for market data, info, and news, plus OAuth-gated CEX trading and DEX…	Multichain	⬡ 84	🟠 Quiet	★ 27
Binance MCP Server (community)	Community-built MCP server for Binance exchange data in trading-agent workflows. Not official Binance.	Multichain	⬡ 82	🟢 Active	★ 49	✓
Bybit Trading MCP	Official Bybit MCP for market data, trading, positions, wallet, and portfolio via REST and WebSocket.	Multichain	⬡ 82	🟢 Active	★ 34	✓
AIBTC MCP Server	Bitcoin-native MCP server: BTC/STX wallets, L1 reads and transfers, Stacks, sBTC, and x402 payments.	Bitcoin	⬡ 82	🟢 Active	★ 10	✓
Heurist Mesh MCP	MCP gateway to Heurist Mesh's 30+ hosted Web3 intelligence agents: token data, DEX pools, X analytics…	Multichain	⬡ 81	🟠 Quiet	★ 63
BNB Chain MCP	Developer MCP tools for AI crypto agents on BNB Chain: DeFi trading, DEX swaps, and contract deployment.	BNB Chain	⬡ 81	🟢 Active	★ 34	✓
Crypto.com AI Tools	Official Crypto.com CLI/MCP server for exchange trading, plus a hosted keyless market-data MCP.	—	⬡ 81	🟡 Recent	★ 26
AlgoVault Quant Signal MCP	MCP server for crypto-perps research signals, funding-rate arbitrage scans, and market-regime data.	Multichain	⬡ 81	🟢 Active	★ 8
CoW MCP	Community MCP server for CoW Protocol: quotes, token/chain lookup, trade history, and EIP-712 order payloads.	Multichain	⬡ 81	🟠 Quiet	★ 0
Arcadia MCP	Official Arcadia Finance MCP for concentrated-liquidity strategies on Uniswap and Aerodrome.	Base, Optimism	⬡ 78	🟢 Active	★ 5	✓
deBridge MCP	deBridge's official MCP for cross-chain and same-chain token swaps, fee estimation, and trade execution.	Multichain	⬡ 76	🟢 Active	★ 32
Philidor MCP	Hosted MCP scoring risk across 700+ DeFi vaults on Morpho, Aave, Spark, Yearn, and Beefy for agent due…	Ethereum, Base, Arbitrum +3	⬡ 76	🟠 Quiet	★ 4
Sperax Crypto MCP	Official Sperax MCP for USDs/SPA protocol data: peg health, collateral, yield strategies, and vault risk on…	Arbitrum, BNB Chain	⬡ 74	🟢 Active	★ 16
Web3 Research MCP	Local, keyless MCP for structured crypto token research: web/news/image/video search plus CoinGecko and…	—	⬡ 73	🟢 Active	★ 162	✓
Jupiter Trading MCP + CLI	Jupiter's hosted read-write MCP server: 75 tools across swap, limit/DCA, lend, perps-adjacent prediction…	Solana	⬡ 73	🟠 Quiet	★ 60	✓
TradingView MCP Server	Community Python MCP for TradingView-style screening: 30+ technical-analysis tools across Binance, KuCoin…	Multichain	⬡ 69	🟢 Active	★ 4.6k
Alpaca MCP Server	Official Alpaca MCP for stock, options, and crypto trading, portfolio and order management, and market data.	—	⬡ 69	🟢 Active	★ 990
Polymarket MCP Server	Community Polymarket MCP with 45 tools: market discovery, analysis, trading, portfolio, and WebSocket…	Polygon	⬡ 68	🟢 Active	★ 675
Nansen MCP	Official Nansen MCP exposing smart-money and wallet-labeling data across 25+ chains.	Multichain	⬡ 67	—	—
OpenSea MCP	Official hosted OpenSea MCP: NFT, token, and wallet data plus swap quotes and mint actions for agents.	Multichain	⬡ 67	—	—
Zerion MCP	Zerion's hosted MCP server exposing normalized wallet balances, DeFi positions, NFTs, and PnL across EVM…	Multichain	⬡ 67	—	—
Sui MCP Server	Community MCP server for Sui: wallet and session tools, coin/object/transaction queries, staking, SuiNS, and…	Sui	⬡ 66	🟢 Active	★ 1
Pyth MCP	Official hosted Pyth Network MCP server for price-feed discovery and real-time/historical market data.	Multichain	⬡ 65	—	—
Algorand MCP	GoPlausible's Algorand MCP: agent wallets, transaction building/signing, TEAL, DEX aggregation, full…	—	⬡ 64	🟡 Recent	★ 44
Hive Intelligence Crypto MCP	Hosted MCP exposing 375+ crypto tools spanning market data, DeFi analytics, security scans, and wallet data.	Multichain	⬡ 62	—	—
LI.FI MCP	Official hosted LI.FI MCP server for read-only cross-chain swap quotes and route discovery.	Multichain	⬡ 62	—	—
Universal Crypto MCP	Plugin-based monorepo MCP: EVM+Solana wallets, DEX aggregation, x402 payments, CEX trading, market data…	Multichain	⬡ 61	🟡 Recent	★ 39	✓
TradeRouter MCP	MCP Registry-listed server for non-custodial Solana trading: swaps, limit, trailing, TWAP, DCA, and combo…	Solana	⬡ 61	🟠 Quiet	★ 3	✓
BitGo MCP	BitGo's official Developer Portal MCP for natural-language search over its institutional wallet API docs.	Multichain	⬡ 61	—	—
Yield.xyz AgentKit (MCP + x402)	Non-custodial onchain yield API for agents: discover, assess, enter and exit 3,300+ staking/lending/RWA…	Base, Ethereum, Solana +3	⬡ 61	—	—
Bitget Agent Hub	Official Bitget toolkit: MCP server, CLI, SDK, and skills for spot, futures, and account operations.	—	⬡ 60	🟠 Quiet	★ 223	✓
CCXT MCP	CCXT-backed MCP server for multi-exchange market data, order books, balances, orders, and trade history.	Multichain	⬡ 59	🟠 Quiet	★ 93
Binance MCP (nirholas)	Community Binance MCP with 478+ tools across spot, margin, futures, staking, NFT, and copy trading.	—	⬡ 57	🟡 Recent	★ 32
Alchemy MCP Server	Official Alchemy MCP server exposing token, NFT, transaction, and wallet-execution tools to agents.	Multichain	⬡ 53	🟠 Quiet	★ 88
Hummingbot MCP	Official Hummingbot MCP server bridging agents to a Hummingbot API instance for multi-exchange trading.	—	⬡ 51	🟠 Quiet	★ 59
DeFi Trading MCP	MCP server that turns an AI assistant into an autonomous DeFi trading agent.	Ethereum, Base, Polygon +5	⬡ 51	🟠 Quiet	★ 52	✓
Octav API MCP	Official Octav MCP exposing portfolio holdings, DeFi positions, NAV, and transaction history across 20+…	Multichain	⬡ 51	🟠 Quiet	★ 0
Gate for AI	Gate.io's official AI infrastructure: CEX/DEX trading, wallet, news, and info MCP tools for agents.	Multichain	⬡ 50	🟠 Quiet	★ 35
ChangeNOW MCP	Official ChangeNOW remote MCP server: quote, create and track cross-chain crypto swaps. Non-custodial, no…	Bitcoin, Ethereum, Solana +2	⬡ 50	—	—
1inch Business MCP	Official 1inch MCP: docs search, code examples, and Business API access for swaps, portfolio, and pricing.	Multichain	⬡ 50	—	—
Haiku DeFi MCP	DeFi execution MCP: swaps, lending, bridges, yield discovery, and portfolio analysis with external wallet…	Multichain	⬡ 48	🟠 Quiet	★ 2
Injective MCP	Official Injective MCP for natural-language queries and trading, incl. spot and perpetual futures.	Injective	⬡ 48	—	—
QuantConnect MCP	Official open-source QuantConnect MCP for quant project management, doc search, code checks, and backtesting.	—	⬡ 48	—	—
Tether WDK MCP Toolkit	Official Tether toolkit exposing self-custodial WDK wallet ops — balances, transfers, swaps, bridging — as…	Multichain	⬡ 48	—	—
Phantom MCP	Phantom's MCP server that lets AI agents view addresses, sign transactions, swap, and transfer tokens across…	Solana, Ethereum, Bitcoin +2	⬡ 43	—	—
BlockBeats MCP	Official BlockBeats MCP: crypto newsflashes, articles, market metrics, ETF flows, and macro signals.	Multichain	⬡ 41	🟠 Quiet	★ 43
TON AgentKit MCP	TON's official @ton/mcp server for wallet operations, transfers, swaps, and NFT management on TON.	TON	⬡ 40	—	—
Jupiter MCP Server	Open-source MCP servers that let AI agents execute Solana token swaps via Jupiter's Ultra aggregation API.	Solana	⬡ 35	⚪ Dormant	★ 29
Bitquery MCP	Hosted MCP endpoint for natural-language queries over Bitquery's trading, OHLC, and token-economics datasets.	Multichain	⬡ 25	—	—
Coinbase for Agents MCP	Coinbase's remote MCP server: an agent signs in with Coinbase OAuth to trade crypto, US stocks/ETFs and…	Base, Multichain	⬡ 25	—	—
Robinhood Trading MCP	Robinhood's first-party MCP server: an agent reads the account and trades equities, options and crypto in a…	—	⬡ 22	—	—
Base MCP (Base Account gateway)	Base's hosted MCP gateway: Claude/ChatGPT/Cursor propose swaps, transfers and app actions; the user signs in…	Base	⬡ 20	—	—
LunarCrush MCP	Official LunarCrush MCP delivering real-time social sentiment, trends, and market signals to agents.	Multichain	⬡ 20	—	—
Binance Agent OS (Binance MCP Server)	Binance's official agent access layer. It pairs a hosted OAuth MCP server for spot, margin, convert and…	BNB Chain	⬡ 19	—	—

Data & Analytics (42)

Name	What it is	Chains	⬡ Score	Activity	★	✓
BlockRun MCP	MCP server giving AI agents live data — markets, crypto, research, X — billed per call via x402 micropayments.	Base, Solana	⬡ 91	🟢 Active	★ 395	✓
Boar Blockchain MCP	Blockchain infrastructure MCP from Boar Network, with setup guides and free-tier access paths.	Multichain	⬡ 84	🟠 Quiet	★ 12
Vybe Solana MCP	Hosted Solana MCP from Vybe Network: schema browsing plus live Solana API calls, no local deployment.	Solana	⬡ 83	🟠 Quiet	★ 213
Bitcoin MCP (Bortlesboat)	Zero-config Bitcoin data MCP: fees, mempool, blocks, transactions, mining, price, and supply.	Bitcoin	⬡ 81	🟢 Active	★ 5	✓
Insumer MCP Server	MCP for condition-based access checks: signed boolean attestations across 37 chains without exposing balances.	Multichain	⬡ 81	🟢 Active	★ 1	✓
Blockscout MCP Server	Wraps Blockscout explorer APIs so agents can query balances, tokens, NFTs, and contract data across chains.	Multichain	⬡ 80	🟢 Active	★ 46	✓
Hedera MCP	Community MCP for Hedera: Mirror Node reads plus 73 build-only tools across accounts, HTS, HCS, EVM, and…	—	⬡ 78	🟢 Active	★ 0	✓
MetaMask Embedded Wallets MCP	Official Web3Auth MCP for integrating MetaMask Embedded Wallets: live SDK docs, examples, and type lookup.	Multichain	⬡ 76	🟠 Quiet	★ 4
CoinPaprika MCP	Official CoinPaprika MCP: 30 tools for prices, tickers, OHLCV, and exchange data across 8,000+ coins.	Multichain	⬡ 76	🟡 Recent	★ 0
Coinbase x402 Bazaar (Discovery API + MCP)	Public, keyless catalog of x402 payment-gated services indexed by the CDP facilitator, searchable by intent…	Base	⬡ 74	🟢 Active	★ 158	✓
Across MCP	Official Across Protocol hosted MCP: docs search, chain data, and live bridge fees at mcp.across.to.	Multichain	⬡ 74	🟡 Recent	★ 1
Celo MCP	Official Celo MCP server for querying the Celo ecosystem, chain data, and developer workflows.	Ethereum	⬡ 73	🟢 Active	★ 5
Crypto APIs MCP Servers	Official Crypto APIs MCP suite: hosted endpoint plus per-package servers for balances, blocks, txs, fees, and…	Multichain	⬡ 73	🟠 Quiet	★ 0
Bankless Onchain MCP	MCP server providing AI assistants read access to onchain data via the Bankless API.	Ethereum, Base, Multichain	⬡ 70	🟠 Quiet	★ 80	✓
Tari MCP Servers	Official Minotari wallet and node MCP servers for local agent access to Tari blockchain data and transactions.	—	⬡ 66	🟢 Active	★ 499
MCP Crypto Price	MCP server exposing CoinCap-backed crypto pricing, market stats, and technical indicators as agent-callable…	Multichain	⬡ 66	🟢 Active	★ 39
CoinStats MCP	Official hosted CoinStats MCP for portfolio, wallet, and market data across 120+ chains via OAuth.	Multichain	⬡ 65	🟡 Recent	★ 16
Avalanche Builder Hub MCP	Ava Labs' read-only MCP exposing Builders Hub docs, code search, and Avalanche chain data to AI clients.	Avalanche	⬡ 65	—	—
LayerZero Docs MCP	Official hosted LayerZero documentation MCP: real-time doc search via a single SearchLayerZero tool.	Multichain	⬡ 65	—	—
Hashnet MCP Server	Hashgraph Online MCP for agent discovery, chat, registration, workflows, and Hedera agent interactions.	—	⬡ 64	🟢 Active	★ 13
RWA Pipe MCP	MCP server for tokenized real-world asset data: RWA token discovery, TVL/APY, issuer and chain filters, and…	Multichain	⬡ 64	🟠 Quiet	★ 0
EVM MCP Server	MCP server exposing 22 tools across 60+ EVM chains: balances, contracts, token transfers, ENS, block/tx data.	Multichain	⬡ 62	🟡 Recent	★ 382	✓
Santiment MCP	Official OAuth-backed Santiment MCP for on-chain, social, and financial crypto metrics.	Multichain	⬡ 62	—	—
Tatum Blockchain MCP	Official Tatum MCP exposing blockchain data and RPC gateway access across 130+ networks.	Multichain	⬡ 59	🟠 Quiet	★ 15
Nodit MCP Server	Official Nodit MCP server giving agents normalized multi-chain blockchain data across EVM and non-EVM…	Multichain	⬡ 57	🟠 Quiet	★ 24	✓
CryptoQuant MCP	Official CryptoQuant MCP server exposing on-chain metrics like MVRV, SOPR, and exchange flows to agents.	Multichain	⬡ 57	🟠 Quiet	★ 6	✓
GoldRush MCP (Covalent)	Covalent's official GoldRush MCP: 50+ tools for multichain wallet balances and token data.	Multichain	⬡ 57	—	—
Sei MCP	Official Sei MCP: wallet/account management, SEI transfers, and ERC20/721/1155 token operations.	Sei	⬡ 56	—	—	✓
Robinhood Chain MCP	MIT stdio MCP server for Robinhood Chain: 105 read/build tools (RPC, precompiles, Stock Tokens, Uniswap v4…	Robinhood Chain	⬡ 54	🟡 Recent	—
Memecoin Observatory MCP	Solana MCP server for memecoin launch detection, whale tracking, and rugpull risk scanning.	Solana	⬡ 52	🟠 Quiet	★ 24
Helius MCP	Official Helius MCP server for Solana: wallet, asset, transaction, and chain-state tools via npm package.	Solana	⬡ 50	—	—	✓
Maestro MCP Server	Official Maestro Bitcoin MCP: indexer, mempool, price, and node RPC data via hosted mainnet/testnet endpoints.	Bitcoin	⬡ 47	🟠 Quiet	★ 25
Erigon MCP	Open-source MCP built into the Erigon Ethereum client, exposing 40+ read-only JSON-RPC and node-data tools.	Ethereum	⬡ 44	—	—
Allium MCP	Allium's official MCP for querying its multichain blockchain data warehouse via SQL over 80+ chains.	Multichain	⬡ 41	—	—
Chainbase MCP	Official hosted Chainbase MCP for token prices, holders, wallet balances, and NFT data via natural language.	Multichain	⬡ 40	—	—
thirdweb AI	Thirdweb's MCP toolkit bundling Nebula, Insight, Engine, and Storage for onchain agent building.	Multichain	⬡ 36	⚪ Dormant	★ 18
QuickNode MCP	Official remote MCP for managing QuickNode blockchain endpoints, rate limits, security, and billing via…	Multichain	⬡ 35	—	—
Messari MCP	Official hosted Messari MCP for crypto research: market data, on-chain metrics, and news across 40,000+…	Multichain	⬡ 28	—	—
CoinMarketCap MCP	Official CoinMarketCap hosted MCP for quotes, technical analysis, on-chain metrics, and market data.	Multichain	⬡ 27	—	—
Birdeye MCP	Official hosted MCP for real-time and historical crypto market data across 8M+ tokens.	Multichain	⬡ 25	—	—
Dune MCP	Official Dune remote MCP for generating, running, and visualizing DuneSQL queries and dashboards from an…	Multichain	⬡ 25	—	—
Token Terminal MCP	Official hosted Token Terminal MCP with a research tool over onchain project/protocol financials.	Multichain	⬡ 25	—	—

Payments (7)

Name	What it is	Chains	⬡ Score	Activity	★	✓
MERX MCP	TRON infrastructure MCP (hosted SSE + local stdio): energy/bandwidth prices, resource optimization, and…	Tron	⬡ 84	🟠 Quiet	★ 3
Lightning Wallet MCP	Bitcoin Lightning wallet MCP and CLI for agent payments: invoices, sends, and L402 support.	Bitcoin	⬡ 81	🟢 Active	★ 9	✓
PayRam MCP	PayRam's MCP server for self-hosted crypto payments: hosted endpoints and agent payment workflows.	Multichain	⬡ 74	🟠 Quiet	★ 156
LNbits MCP	Open-source MCP server for the LNbits Lightning accounts system: wallet balances, payments, and admin tools.	Bitcoin	⬡ 58	🟠 Quiet	★ 4
x402node MCP	MCP server that discovers x402-paid APIs via CDP Bazaar and handles USDC micropayments on Base.	Base, Solana	⬡ 57	🟡 Recent	★ 1
TensorFeed x402 Base MCP	Read-only Base mainnet MCP for x402: verify USDC settlements, parse x402 manifests, probe endpoints, decode…	Base	⬡ 56	🟡 Recent	★ 2
Alby MCP	Official Alby MCP connecting Bitcoin Lightning wallets to agents via Nostr Wallet Connect.	Bitcoin	⬡ 54	🟡 Recent	★ 66

Wallets & Identity (3)

Name	What it is	Chains	⬡ Score	Activity	★	✓
BSV MCP	MIT-licensed MCP toolset for Bitcoin SV: wallet operations, ordinals, and BSV blockchain utilities.	Bitcoin	⬡ 69	🟢 Active	★ 22
Rootstock MCP Server	Official Rootstock MCP: wallets, RBTC/ERC-20 balances and transfers, tx status, and contract deployment.	Bitcoin	⬡ 64	🟡 Recent	★ 3	✓
Privy MCP Server	Official Privy MCP server: create wallets, sign transactions, and manage policies across 11 chains.	Multichain	⬡ 58	🟠 Quiet	★ 2

Privacy & Security (4)

Name	What it is	Chains	⬡ Score	Activity	★	✓
Mina MCP Server	Official Mina Protocol MCP server for Mina blockchain tooling and developer workflows.	—	⬡ 72	🟠 Quiet	★ 0	✓
BICScan MCP	AhnLab's BICScan MCP server: blockchain address risk scoring and asset lookups over the BICScan API.	Multichain	⬡ 61	🟠 Quiet	★ 17
SolanaShield MCP	MIT-licensed MCP server that runs vulnerability-pattern checks against Solana smart contracts.	Solana	⬡ 50	🟠 Quiet	★ 0
OpenZeppelin MCP	Official OpenZeppelin MCP for generating template-based smart contracts in Solidity, Cairo, Stylus, and…	Ethereum, Arbitrum, Multichain	⬡ 38	—	—	✓

Build & Infra (1)

Name	What it is	Chains	⬡ Score	Activity	★	✓
Neynar MCP	Official Neynar hosted MCP exposing Farcaster's OpenAPI spec and Node.js SDK to AI coding assistants.	—	⬡ 40	—	—

General (28)

Name	What it is	Chains	⬡ Score	Activity	★	✓
VeChain MCP Server	Official VeChain MCP server exposing ecosystem resources and VeChain developer workflows to agents.	—	⬡ 81	🟢 Active	★ 5	✓
SODAX Builders MCP	MCP server giving AI coding agents live access to SODAX's cross-network DeFi API across 20+ chains.	Ethereum, Base, Arbitrum +2	⬡ 78	🟡 Recent	★ 9	✓
Klever MCP	Official MCP server for the Klever blockchain — smart contract development, account/asset queries, and…	—	⬡ 76	🟠 Quiet	★ 31	✓
Starknet MCP	Official Starknet MCP server exposing the full Starknet JSON-RPC v0.10.2 surface as agent tools.	Starknet	⬡ 75	🟢 Active	★ 115
Aptos MCP	Official Aptos MCP server: Move dev guidance, Geomi project automation, and sponsored-transaction setup.	Aptos	⬡ 73	🟢 Active	★ 13
Cryptopolitan MCP	MCP server serving Cryptopolitan's crypto news, analysis, and price data via SSE and HTTP endpoints.	—	⬡ 73	🟠 Quiet	★ 4
Monad Agent Kit	MCP toolkit for AI agents to send transactions and deploy/verify contracts on Monad with local-only key…	Monad	⬡ 72	—	—
Official Solana MCP Server	Solana Foundation's official MCP serving live developer docs, semantic search, and a program autofixer.	Solana	⬡ 69	🟡 Recent	★ 79
Chainstack MCP	Official remote Streamable HTTP MCP: Chainstack docs search, platform status, live pricing, and node…	Multichain	⬡ 65	—	—
Forta Risk Graph MCP	OAuth-gated MCP over a live graph of positions, governance, oracles, custody and backing, answering…	Multichain, Ethereum	⬡ 64	🟢 Active	★ 1
Indigo Protocol Cardano MCP	Cardano wallet MCP server — submit transactions, read UTxOs, resolve ADAHandles, and check stake delegation.	—	⬡ 58	🟠 Quiet	★ 4	✓
Blockchain Academics MCP	MCP server exposing 99 tools for crypto market data, on-chain analytics, news, and entity dossiers.	Multichain	⬡ 58	🟡 Recent	★ 1	✓
Multichain MCP	Single MCP server for balance/price reads and unsigned transfer prep across Stacks, Celo, and Base.	Base, Multichain	⬡ 57	🟡 Recent	★ 1
Deside MCP	MCP server for wallet-to-wallet messaging and agent identity resolution on Solana.	Solana	⬡ 55	🟡 Recent	★ 0	✓
Squads MCP	Community MCP server letting agents create, vote on, and manage Squads Solana multisig proposals.	Solana	⬡ 54	⚪ Dormant	★ 3	✓
eth-mcp	MCP server enabling agents to build and deploy Ethereum apps with Scaffold-ETH — clone, fork, deploy, and run…	Ethereum	⬡ 54	🟠 Quiet	★ 0	✓
XRPL MCP (RomThpt)	Community MCP server providing blockchain services for the XRP Ledger ecosystem.	XRP Ledger	⬡ 53	🟡 Recent	★ 13
JustaName ENS MCP	MCP server for ENS — resolve names to addresses, reverse lookups, text records, subdomains, and registration…	Ethereum	⬡ 52	🟠 Quiet	★ 8
Linea MCP	Community MCP server with on-chain tools for AI applications to interact with the Linea blockchain.	—	⬡ 51	🟠 Quiet	★ 2
Lido MCP	MCP server for Lido liquid staking: stake, unstake, wrap, vote, and monitor yields on Ethereum.	Ethereum	⬡ 48	🟠 Quiet	★ 2
Ultrade MCP	MCP server for Ultrade's order-book DEX — wallet, market, and order tools for AI trading agents.	Multichain	⬡ 46	⚪ Dormant	★ 5
Chainlink MCP Server	MCP server exposing Chainlink Data Feeds, VRF, Automation, CCIP, and Proof of Reserve.	Multichain	⬡ 46	—	—
SOLx402 MCP Server	MCP server bridging AI assistants to the x402 micropayment protocol on Solana, so agents can discover and pay…	Solana	⬡ 42	🟠 Quiet	★ 7
Aave MCP by Junct	Hosted MCP server exposing tools mapped 1:1 to Aave's analytics API, no auth required.	Ethereum, Base, Arbitrum +2	⬡ 39	🟠 Quiet	★ 0
Euler MCP by Junct	Hosted MCP server with 16 tools for Euler lending-protocol rates and positions.	Ethereum, Base	⬡ 35	🟠 Quiet	★ 0
Mercury x402 MCP	Pay-per-call MCP server (x402, USDC on Base) offering keyless web-read, structured extraction, and markdown…	Base, Polygon, Avalanche +1	⬡ 35	—	—
OpenDexter	Agent middleware (npm/MCP) that discovers, prices, and pays for paid APIs with multi-chain USDC, tracking…	Solana, Base, Polygon +3	⬡ 26	—	—
Tenderly MCP	Official Tenderly MCP: gasless EVM transaction simulation, tracing, and contract inspection across 100+…	Multichain	⬡ 25	—	—

⬆ Back to Index

Wallet Infrastructure

_{33 entries · keys, wallets, and signing rails that let agents hold and move assets · Related: Trading & DeFi · Security · Browse + filter on satohub.ai →}

Trading & DeFi (8)

Name	What it is	Chains	⬡ Score	Activity	★	✓
Bankr	Crypto execution layer and cross-chain wallet that lets agents and users trade, bridge, and manage assets via…	Base, Ethereum, Polygon +7	⬡ 87	🟢 Active	★ 1.2k	✓
Trust Wallet Agent Kit (TWAK)	Non-custodial toolkit from Trust Wallet (MCP server, CLI, and SDK) that lets AI agents read and transact…	Ethereum, Base, Solana +6	⬡ 87	🟢 Active	★ 101	✓
0xGasless AgentKit	Toolkit giving AI agents gasless access to crypto wallets and onchain functionality.	BNB Chain, Avalanche, Base	⬡ 86	🟢 Active	★ 417	✓
Swapper Toolkit	DeFi toolkit that gives AI agents and coding assistants wallets to deposit funds, execute trades, and manage…	Ethereum, Base, Arbitrum +5	⬡ 61	🟠 Quiet	★ 850
MetaMask Agent Wallet	Self-custodial MetaMask wallet for AI agents with built-in transaction simulation, threat scanning, and…	Ethereum, Base, Arbitrum +7	⬡ 57	🟠 Quiet	—
WAIaaS	Wallet-as-a-Service infrastructure for AI agents.	Solana, Ethereum, Polygon +5	⬡ 54	🟠 Quiet	★ 26
MegaETH	Real-time Ethereum L2 (~10ms blocks) with a native agent stack: the MOSS embedded wallet lets agents act…	MegaETH, Ethereum	⬡ 50	—	—
Alchemy AgentPay	Alchemy's payment proxy for AI agents — every API request is authenticated, metered, and settled…	Base, Multichain	⬡ 37	—	—

Data & Analytics (1)

Name	What it is	Chains	⬡ Score	Activity	★	✓
Coinbase Agentic Wallets	Coinbase Developer Platform wallet infrastructure built for AI agents, with spend caps, gasless Base…	Base, Solana, Multichain	⬡ 44	—	—

Payments (5)

Name	What it is	Chains	⬡ Score	Activity	★	✓
Privy	Embedded and server wallet infrastructure used to give agents secure key management.	Ethereum, Base, Solana +1	⬡ 83	🟢 Active	—	✓
Agenti	Gives any AI agent a crypto wallet to pay x402 APIs, receive USDC, and check balances.	Ethereum, Base, Arbitrum +2	⬡ 66	🟢 Active	★ 79
Circle Agent Stack	Circle's official agent toolkit: Circle CLI, policy-controlled Agent Wallets, gasless USDC Nanopayments, an…	Base, Polygon, Ethereum +5	⬡ 52	🟡 Recent	★ 30
Cobo Agentic Wallet	Non-custodial MPC wallet for AI agents with cryptographically enforced human rules, plus a WaaS Skill for…	Ethereum, Solana, Base +3	⬡ 48	—	—
Laso Finance	Stablecoin-to-real-world spending for agents: prepaid and gift cards, Venmo/PayPal/ACH payouts. C

Showing the first 100 KB - view the full README on GitHub

Install

Tools (31)

onchain_agent_search_resourcesonchain_agent_get_resourceonchain_agent_get_deploy_speconchain_agent_recent_changesonchain_agent_list_categoriesonchain_agent_list_chainsonchain_agent_get_newsonchain_agent_get_metrics

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://satohub.ai/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "onchain-agents": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://satohub.ai/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

MCP Server: ai.satohub/onchain-agents

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

onchain_agent_search_resources

onchain_agent_get_resource

onchain_agent_get_deploy_spec

onchain_agent_recent_changes

onchain_agent_list_categories

onchain_agent_list_chains

onchain_agent_get_news

onchain_agent_get_metrics

onchain_agent_get_wiki_page

onchain_agent_search_agents

onchain_agent_get_agent_passport

onchain_agent_recommend_stack

onchain_agent_list_wiki_pages

onchain_agent_get_changes

onchain_agent_get_agent_economy

onchain_agent_search_skills

onchain_agent_get_trend

onchain_agent_compare_listings

onchain_agent_explain_number

onchain_agent_get_score_methodology

onchain_agent_get_listing_history

onchain_agent_preflight

onchain_agent_route_swap

onchain_agent_route_agent

onchain_agent_route_launch

onchain_agent_build_plan

onchain_agent_route_lp

onchain_agent_scaffold_plan

onchain_agent_watch

onchain_agent_submit_project

onchain_agent_register_agent

Onchain Agents

Runnable agent packages

The stack, layer by layer

Agent runtimes & frameworks

Onchain action kits & SDKs

MCP servers

Wallets, keys & permissions

Data, RPC & indexing

Payments & agent commerce

Identity, discovery & standards

Security & preflight

Trading & DeFi venues

Starting stacks

Use the data

Swap through a gate

Legend

Index

Trading & DeFi (56)

Data & Analytics (42)

Payments (7)

Wallets & Identity (3)

Privacy & Security (4)

Build & Infra (1)

General (28)

Trading & DeFi (8)

Data & Analytics (1)

Payments (5)

Install

Remote endpoint

Related servers