Agent Nexus

Official6 tools

by Strategiumfinancepartner · TypeScript

Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.

MCP Server: app.agentnexus/agent-nexus

The app.agentnexus/agent-nexus MCP server provides an agent-native registry to discover APIs, MCP servers, and CLIs, including live health checks. Its purpose is to maintain an up-to-date catalog of available capabilities for clients that rely on MCP integration.

🛠️ Key Features

Agent-native registry
API discovery
MCP server discovery
CLI discovery
Live health checks

🚀 Use Cases

Finding available APIs via a registry
Discovering MCP servers for integration
Locating CLIs from within an agent workflow
Verifying availability using live health checks

⚡ Developer Benefits

Centralized discovery of APIs, MCP servers, and CLIs
Health status information via live checks

⚠️ Limitations

No additional tool, topics, or README excerpt details were provided in the available source data.

Topics

agent-infrastructureagentic-aiai-agentsapi-registryllm-toolsmcpmcp-servermodel-context-protocolopenapitool-discovery

Captured live from the server via tools/list.

discover_capabilities

Map a plain-language goal (e.g. 'send a transactional email') to callable APIs, MCP servers or CLIs. Returns {need, coverage, count, uncovered, note, matches[]}; each match has slug, endpoint, auth, formats, rate limit, pricing and a 0-100 reliability score. Never empty on a valid need: if nothing fits, coverage='none' and matches[] lists reliable starting points. Errors: an invalid or too-short need fails input validation; a backend failure returns isError=true with the message. Rate limits: 100 calls/day anonymous, 1,000/day with a free key (POST /api/public/keys, no account), 50,000/day on Agent Pro. For a known keyword or slug, use search_registry.

Parameters4

need	string	required	What the agent is trying to accomplish, in plain language. 3-300 characters, required.
category	string	optional	Restrict to one interface layer ('api', 'mcp' or 'cli' — see list_categories). Default: omitted, searches all three.
min_reliability	integer	optional	Drop interfaces scoring below this 0-100 reliability value. Default 0 (no filter).
limit	integer	optional	Maximum number of matching interfaces to return, 1-20. Default 5.

Raw schema

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "minLength": 3,
      "maxLength": 300,
      "description": "What the agent is trying to accomplish, in plain language. 3-300 characters, required."
    },
    "category": {
      "description": "Restrict to one interface layer ('api', 'mcp' or 'cli' — see list_categories). Default: omitted, searches all three.",
      "type": "string",
      "enum": [
        "api",
        "mcp",
        "cli"
      ]
    },
    "min_reliability": {
      "default": 0,
      "description": "Drop interfaces scoring below this 0-100 reliability value. Default 0 (no filter).",
      "type": "integer",
      "minimum": 0,
      "maximum": 100
    },
    "limit": {
      "default": 5,
      "description": "Maximum number of matching interfaces to return, 1-20. Default 5.",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "need"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

search_registry

Keyword lookup in the Agent Nexus registry when you already know what to look for: a product name, vendor, slug or endpoint fragment, optionally narrowed to one category. Matches literal text only — it does not interpret a goal. To go from a plain-language need to a callable interface, use discover_capabilities instead; to walk the whole catalogue in order use list_entries, and for the full record of one known slug use get_entry. Returns {count, results[]} in summary form, and an empty results[] when nothing matches — that is a valid answer, not an error.

Parameters3

query	string	optional	Literal substring, max 120 chars, matched case-insensitively against name, summary, endpoint and slug — a product name ('resend'), a vendor, a slug fragment or a host ('api.stripe.com'). Single terms work best: the whole string is matched as one substring, so 'send email' finds nothing unless those words appear together. The characters % , ( ) are stripped. An empty query (the default) returns the first entries in name order, which is a browse, not a search.
category	string	optional	Optional filter, exactly one of 'api', 'mcp' or 'cli' (see list_categories). Combined with query as AND. Omit to search all three layers.
limit	integer	optional	Upper bound on entries returned, 1-50, default 10. Results are ordered by name, not by relevance, so a small limit on a broad keyword can hide better matches — raise it or use discover_capabilities when you are ranking candidates.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "default": "",
      "description": "Literal substring, max 120 chars, matched case-insensitively against name, summary, endpoint and slug — a product name ('resend'), a vendor, a slug fragment or a host ('api.stripe.com'). Single terms work best: the whole string is matched as one substring, so 'send email' finds nothing unless those words appear together. The characters % , ( ) are stripped. An empty query (the default) returns the first entries in name order, which is a browse, not a search.",
      "type": "string",
      "maxLength": 120
    },
    "category": {
      "description": "Optional filter, exactly one of 'api', 'mcp' or 'cli' (see list_categories). Combined with query as AND. Omit to search all three layers.",
      "type": "string",
      "enum": [
        "api",
        "mcp",
        "cli"
      ]
    },
    "limit": {
      "default": 10,
      "description": "Upper bound on entries returned, 1-50, default 10. Results are ordered by name, not by relevance, so a small limit on a broad keyword can hide better matches — raise it or use discover_capabilities when you are ranking candidates.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

get_entry

Fetch the full record of ONE approved registry entry whose exact slug you already have, e.g. from a previous discover_capabilities, search_registry or list_entries result. Read-only and idempotent: the same slug always returns the same entry until its health probe changes. Returns {entry} with endpoint, auth mode and parameters, input/output formats, rate limit, pricing, capabilities, docs URL, invocation example and the latest 6-hourly health probe — the detail level the listing tools omit. This is the single-record lookup: it takes no filters and no paging. If you do not have a slug, do not guess one — use search_registry for a keyword or discover_capabilities for a plain-language need; to walk the whole catalogue use list_entries. An unknown or unapproved slug is an error, not an empty result.

Parameters1

slug

string

required

Exact lowercase slug of one entry, 1-80 chars, as returned in the 'slug' field of any other tool, e.g. 'stripe-api' or 'github-mcp'. Case-sensitive, no URL and no display name; only entries with status 'approved' resolve.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1,
      "maxLength": 80,
      "description": "Exact lowercase slug of one entry, 1-80 chars, as returned in the 'slug' field of any other tool, e.g. 'stripe-api' or 'github-mcp'. Case-sensitive, no URL and no display name; only entries with status 'approved' resolve."
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

list_categories

Return the fixed taxonomy of Agent Nexus: the three interface layers it indexes ('api', 'mcp', 'cli'), each with a label, a one-line definition and its live count of approved entries. Read-only, idempotent and parameterless — call it once to learn the exact values accepted by the 'category' argument of search_registry, list_entries and discover_capabilities, and to size the catalogue before paging. It never returns entries themselves: use list_entries to enumerate a layer, search_registry for a keyword, discover_capabilities for a plain-language need.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

list_entries

Enumerate the whole approved catalogue in deterministic slug order, page by page — use this when you want everything (mirroring, auditing, building your own index), not when you are looking for something specific. Read-only and idempotent. Returns {total, page, per_page, pages, results[]}: read 'pages' from the first response and increment 'page' until you reach it; 'total' and 'pages' reflect the 'category' filter when one is set, so keep the filter identical across pages or the paging shifts. Entries come back in summary form; call get_entry with a slug for the full record. For a keyword use search_registry, for a plain-language need use discover_capabilities, and for the accepted category values call list_categories. Bulk mirror alternative: GET https://agentnexus.app/api/public/entries.ndjson streams the full catalogue in one request.

Parameters3

page	integer	optional	1-based page index. Start at 1 and increment until it equals the 'pages' value returned in the response; a page beyond the last one returns an empty results[] rather than an error.
per_page	integer	optional	How many entries to return in this page, 1-50, default 25. Changing it between calls changes 'pages' and re-slices the catalogue, so keep it constant while paging.
category	string	optional	Optional filter, exactly one of 'api', 'mcp' or 'cli' (see list_categories). Omit to page through all three layers. When set, 'total' and 'pages' count only that layer.

Raw schema

{
  "type": "object",
  "properties": {
    "page": {
      "default": 1,
      "description": "1-based page index. Start at 1 and increment until it equals the 'pages' value returned in the response; a page beyond the last one returns an empty results[] rather than an error.",
      "type": "integer",
      "minimum": 1,
      "maximum": 9007199254740991
    },
    "per_page": {
      "default": 25,
      "description": "How many entries to return in this page, 1-50, default 25. Changing it between calls changes 'pages' and re-slices the catalogue, so keep it constant while paging.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "category": {
      "description": "Optional filter, exactly one of 'api', 'mcp' or 'cli' (see list_categories). Omit to page through all three layers. When set, 'total' and 'pages' count only that layer.",
      "type": "string",
      "enum": [
        "api",
        "mcp",
        "cli"
      ]
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

submit_entry

Register a new interface (HTTP API, MCP server or CLI) in the Agent Nexus catalogue. Callers authenticate either as a signed-in member or with a free agent key (POST https://agentnexus.app/api/public/keys), which allows one submission per key and per source address per 24 hours. This is a write: it creates a pending row, it does NOT publish anything — every submission is reviewed by a human before it becomes discoverable, so nothing you send here is visible to other agents until it is approved. Nothing is overwritten or deleted, and re-submitting the same name creates a second pending row rather than updating the first. Five fields are required (name, category, summary, endpoint, auth_mode); everything else is optional but directly decides whether the entry is approved and how well it ranks: capabilities[] is what other agents are matched against, so list concrete verbs, and docs_url plus invocation_example are what a reviewer checks first. Rate limited to 20 submissions per hour for members and 1 per 24 hours per agent key and per source address, and the endpoint must answer a live health probe to keep a reliability score. Returns {slug, status}; poll GET https://agentnexus.app/api/public/submission?slug=<slug> for the decision, or pass contact_email to be emailed instead. Use list_my_submissions to review what you already submitted; use search_registry first to check the interface is not already listed.

Parameters16

name	string	required	Public product name as its vendor spells it, 1-80 chars, e.g. 'Resend' or 'GitHub MCP Server'. Do not add the category or a tagline here; the slug is derived from this name plus the category.
category	string	required	Which layer this interface belongs to: 'api' for an HTTP contract called directly, 'mcp' for a Model Context Protocol tool server, 'cli' for a command-line surface. Decides how endpoint is interpreted (URL vs command).
summary	string	required	One line an agent can rank on: what the interface does, 10-300 chars. State the capability, not the marketing (e.g. 'Send transactional email over HTTP with templates and delivery webhooks').
endpoint	string	required	How the interface is actually reached, max 500 chars. For category 'api' the base URL (https://api.example.com/v1); for 'mcp' the server URL (https://example.com/mcp) or stdio command; for 'cli' the install-and-run command (npx example-cli). Must be reachable: it is probed daily and a dead endpoint loses its reliability score.
auth_mode	string	required	How a caller authenticates, in a few words: 'none', 'Bearer API key', 'API key in query', 'OAuth 2.1', 'Basic auth'. Write 'none' rather than leaving it vague; auth_params carries the individual credentials.
capabilities	array	optional	Up to 12 lowercase hyphenated verbs an agent's need is matched against, e.g. ['send-email','list-templates','verify-address']. This is the single field that drives discovery: an entry with no capabilities is rarely returned. One action per item, 2-40 chars, no sentences.
auth_params	array	optional	Up to 10 individual credentials the caller must supply, each {name, location, required}. Leave empty when auth_mode is 'none'. Never include credential values here, only their names.
input_format	string	optional	MIME type or shape the interface accepts, e.g. 'application/json', 'multipart/form-data', 'command-line flags'. Empty string when not applicable.
output_format	string	optional	MIME type or shape the interface returns, e.g. 'application/json', 'text/csv', 'stdout text'. Empty string when not applicable.
rate_limit	string	optional	Published quota in the vendor's own words, e.g. '100 requests/minute', '10k calls/month on the free tier'. Leave empty rather than guessing.
pricing	string	optional	Cost in one short phrase, e.g. 'Free', 'Free tier then $20/month', 'Usage-based, $0.001/call'. Agents filter on this, so be concrete.
invocation_example	string	optional	One copy-pasteable call that works: a curl command, a JSON-RPC body or a CLI line, max 1000 chars. Never include a real credential — use a placeholder such as $API_KEY. This is what reviewers check first.
docs_url	string	optional	Absolute https URL of the developer documentation (not the marketing home page). Omit if none exists; submissions without it are approved more slowly.
tags	array	optional	Up to 8 short domain labels for browsing, e.g. ['email','messaging']. Domains, not actions — actions belong in capabilities[].
description	string	optional	Optional long form, max 4000 chars: what the interface does well, notable limits, quirks an agent should know before calling. Plain text; no HTML.
contact_email	string	optional	Optional. Where to email the moderation decision (approved or rejected, with the reason). Never published, never shared.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 80,
      "description": "Public product name as its vendor spells it, 1-80 chars, e.g. 'Resend' or 'GitHub MCP Server'. Do not add the category or a tagline here; the slug is derived from this name plus the category."
    },
    "category": {
      "type": "string",
      "enum": [
        "api",
        "mcp",
        "cli"
      ],
      "description": "Which layer this interface belongs to: 'api' for an HTTP contract called directly, 'mcp' for a Model Context Protocol tool server, 'cli' for a command-line surface. Decides how endpoint is interpreted (URL vs command)."
    },
    "summary": {
      "type": "string",
      "minLength": 10,
      "maxLength": 300,
      "description": "One line an agent can rank on: what the interface does, 10-300 chars. State the capability, not the marketing (e.g. 'Send transactional email over HTTP with templates and delivery webhooks')."
    },
    "endpoint": {
      "type": "string",
      "minLength": 1,
      "maxLength": 500,
      "description": "How the interface is actually reached, max 500 chars. For category 'api' the base URL (https://api.example.com/v1); for 'mcp' the server URL (https://example.com/mcp) or stdio command; for 'cli' the install-and-run command (npx example-cli). Must be reachable: it is probed daily and a dead endpoint loses its reliability score."
    },
    "auth_mode": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "How a caller authenticates, in a few words: 'none', 'Bearer API key', 'API key in query', 'OAuth 2.1', 'Basic auth'. Write 'none' rather than leaving it vague; auth_params carries the individual credentials."
    },
    "capabilities": {
      "default": [],
      "description": "Up to 12 lowercase hyphenated verbs an agent's need is matched against, e.g. ['send-email','list-templates','verify-address']. This is the single field that drives discovery: an entry with no capabilities is rarely returned. One action per item, 2-40 chars, no sentences.",
      "maxItems": 12,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 2,
        "maxLength": 40
      }
    },
    "auth_params": {
      "default": [],
      "description": "Up to 10 individual credentials the caller must supply, each {name, location, required}. Leave empty when auth_mode is 'none'. Never include credential values here, only their names.",
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "minLength": 1,
            "maxLength": 60,
            "description": "Exact credential name as sent, e.g. 'Authorization' or 'api_key'."
          },
          "location": {
            "type": "string",
            "minLength": 1,
            "maxLength": 40,
            "description": "Where the credential goes: 'header', 'query', 'env' (CLI/MCP environment variable) or 'flag' (CLI argument)."
          },
          "required": {
            "default": true,
            "description": "False only when the call also works without this credential. Defaults to true.",
            "type": "boolean"
          }
        },
        "required": [
          "name",
          "location"
        ]
      }
    },
    "input_format": {
      "default": "",
      "description": "MIME type or shape the interface accepts, e.g. 'application/json', 'multipart/form-data', 'command-line flags'. Empty string when not applicable.",
      "type": "string",
      "maxLength": 120
    },
    "output_format": {
      "default": "",
      "description": "MIME type or shape the interface returns, e.g. 'application/json', 'text/csv', 'stdout text'. Empty string when not applicable.",
      "type": "string",
      "maxLength": 120
    },
    "rate_limit": {
      "default": "",
      "description": "Published quota in the vendor's own words, e.g. '100 requests/minute', '10k calls/month on the free tier'. Leave empty rather than guessing.",
      "type": "string",
      "maxLength": 120
    },
    "pricing": {
      "default": "",
      "description": "Cost in one short phrase, e.g. 'Free', 'Free tier then $20/month', 'Usage-based, $0.001/call'. Agents filter on this, so be concrete.",
      "type": "string",
      "maxLength": 120
    },
    "invocation_example": {
      "default": "",
      "description": "One copy-pasteable call that works: a curl command, a JSON-RPC body or a CLI line, max 1000 chars. Never include a real credential — use a placeholder such as $API_KEY. This is what reviewers check first.",
      "type": "string",
      "maxLength": 1000
    },
    "docs_url": {
      "description": "Absolute https URL of the developer documentation (not the marketing home page). Omit if none exists; submissions without it are approved more slowly.",
      "type": "string",
      "maxLength": 500,
      "format": "uri"
    },
    "tags": {
      "default": [],
      "description": "Up to 8 short domain labels for browsing, e.g. ['email','messaging']. Domains, not actions — actions belong in capabilities[].",
      "maxItems": 8,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 24
      }
    },
    "description": {
      "default": "",
      "description": "Optional long form, max 4000 chars: what the interface does well, notable limits, quirks an agent should know before calling. Plain text; no HTML.",
      "type": "string",
      "maxLength": 4000
    },
    "contact_email": {
      "description": "Optional. Where to email the moderation decision (approved or rejected, with the reason). Never published, never shared.",
      "type": "string",
      "maxLength": 200,
      "format": "email",
      "pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
    }
  },
  "required": [
    "name",
    "category",
    "summary",
    "endpoint",
    "auth_mode"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

README.md4 KBView on GitHub

Agent Nexus

The continuously verified registry of the APIs, MCP servers and CLIs that AI agents call.

Live: https://agentnexus.app · MCP endpoint (no login): https://agentnexus.app/api/public/mcp

Agent Nexus answers one question for an autonomous agent: "what can actually do this, right now, and how exactly do I call it?" Every entry is probed over HTTP on a schedule, so the answer carries a real reliability score instead of a stale README badge.

Listed on the official MCP registry as app.agentnexus/agent-nexus, on Smithery, on Glama and on the M8ven Trust Index.

Connect an agent in one line

MCP (Streamable HTTP, stateless, anonymous — no consent screen, no key):

json

{
  "mcpServers": {
    "agent-nexus": {
      "type": "http",
      "url": "https://agentnexus.app/api/public/mcp"
    }
  }
}

Or over plain HTTP — an agent can register itself and start calling without any human:

# 1. get your own key (instant, free tier: 1000 calls/day)
curl -s -X POST https://agentnexus.app/api/public/keys \
  -H 'content-type: application/json' \
  -d '{"agent":"my-agent","purpose":"capability discovery"}'

# 2. turn a plain-language need into a callable contract
curl -s 'https://agentnexus.app/api/public/discover?need=send%20transactional%20email' \
  -H 'x-api-key: nx_...'

MCP tools

Tool	What it does
`discover_capabilities`	Plain-language need → ranked callable interfaces with auth, formats, limits, reliability
`search_registry`	Keyword search across APIs, MCP servers and CLIs
`get_entry`	Full contract for one interface
`list_categories`	Browse the taxonomy

Machine-readable surfaces

Surface	Purpose
`/llms.txt`, `/agents.txt`	How an agent onboards itself, unattended
`/api/public/registry`	Full typed registry
`/api/public/capabilities`	Capability index
`/api/public/entries.ndjson`	Streamable bulk export
`/api/public/status`	Uptime history and recent incidents
`/openapi.json`, `/server.json`	OpenAPI + MCP server manifest
`/.well-known/mcp.json`, `/.well-known/agent-card.json`	Discovery manifests
`/feed.xml`	New and updated interfaces

Human pages

/explore · /connect · /status · /pricing · /keys

Tiers

Tier	Who it is for	Daily calls
Anonymous	Trying it out, no account	100
Free key	Agent developers	1 000
Agent Pro	Production agents that must not stall	50 000
Publisher	API / MCP / CLI vendors: verified badge, monitoring, alerts	—

Stack

TanStack Start (React 19, Vite), Tailwind CSS v4, Postgres with row-level security, server functions on an edge runtime, scheduled HTTP health probes. Built with Lovable.

Only publishable keys live in this repository; every secret is held server-side.

Development

git clone https://github.com/Strategiumfinancepartner/AgentNexus.git
cd AgentNexus
npm i
npm run dev

Operated by BrainPath.io · support@agentnexus.app

Install

Tools (6)

discover_capabilitiessearch_registryget_entrylist_categorieslist_entriessubmit_entry

Remote endpoint

Streamable HTTP

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

url

https://agentnexus.app/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agent-nexus": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://agentnexus.app/mcp"
      ]
    }
  }
}

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

MCP Server: app.agentnexus/agent-nexus

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

discover_capabilities

search_registry

get_entry

list_categories

list_entries

submit_entry

Agent Nexus

Connect an agent in one line

MCP tools

Machine-readable surfaces

Human pages

Tiers

Stack

Development

Install

Remote endpoint

Related servers