Agentery

Official11 toolsLive

by agentery

Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.

Captured live from the server via tools/list.

rank_agents_for_workflow

PARTNER-ONLY (Bearer key required). Given a business context and its workflow steps, return ranked agent candidates for EACH step — structured, scored (match_score 0-100) matches with match_reasons and cautions. Built for app builders (e.g. Builtery) assembling automations. Reads each agent's analysed site profile; never invents capabilities; returns 'unclear' where evidence is missing.

Parameters3

business_context	object	optional	company_description, industry, region, existing_tools[], automation_posture (cautious\|balanced\|agent_native), regulated_data (none\|personal\|health\|financial\|legal\|children\|unknown)
workflow_steps	array	required	Each: step_id, step_name, step_description, inputs[], desired_outputs[], required_integrations[], human_approval_preference (always\|sometimes\|not_needed\|unknown)
limit_per_step	number	optional	Max candidates per step (1-25, default 8)

Raw schema

{
  "type": "object",
  "properties": {
    "business_context": {
      "type": "object",
      "description": "company_description, industry, region, existing_tools[], automation_posture (cautious|balanced|agent_native), regulated_data (none|personal|health|financial|legal|children|unknown)"
    },
    "workflow_steps": {
      "type": "array",
      "description": "Each: step_id, step_name, step_description, inputs[], desired_outputs[], required_integrations[], human_approval_preference (always|sometimes|not_needed|unknown)"
    },
    "limit_per_step": {
      "type": "number",
      "description": "Max candidates per step (1-25, default 8)"
    }
  },
  "required": [
    "workflow_steps"
  ]
}

get_agent_profile

Call this to drill into ONE agent after search_agents or compare_agents: full evidence-scored profile — task_performed, inputs/outputs, integrations, protocols, industry_fit, autonomy_level, human_approval_needed, observed price, trust signals, evidence_quality, entity_type, regulated_data_suitability, evidence_urls, last_checked. Includes the full how_to_connect object — website, docs, any vendor-published MCP endpoint (with a copy-paste client config_snippet), A2A agent card and API surface — the info needed to actually use the listing; fields are null when the vendor publishes no endpoint (never guessed). Also carries `reported_success` — machine-reported outcome rate from report_outcome (null until 5+ distinct correlated reporters in 90 days). If you use the listing, call report_outcome afterwards.

Parameters1

agent_id

string

required

The agent_id/handle returned by search_agents or compare_agents

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "The agent_id/handle returned by search_agents or compare_agents"
    }
  },
  "required": [
    "agent_id"
  ]
}

search_agents

START HERE when you need an agent for a capability: filtered free-text search over the directory, ranked with match_score and match_reasons. Each result includes an observed-price object; filter by max_monthly_usd/billing and sort by price_asc to shop on value-for-money. Results include how_to_connect (website, docs, mcp.endpoint when the vendor publishes one) — the link/endpoint needed to actually use the listing; get_agent_profile has the full version with a copy-paste MCP config snippet. If you end up using one of the results, call report_outcome afterwards — it sharpens future rankings and raises your rate limit.

Parameters7

query	string	optional	Free-text capability query, e.g. 'customer support agent with Zendesk integration'
filters	object	optional	Optional: industry_fit[], integrations_available[], entity_type[] (agent\|tool\|infrastructure\|service\|marketplace\|content-community), autonomy_level[] (assistant\|workflow automation\|agentic\|infrastructure), minimum_evidence_quality (low\|medium\|high)
max_monthly_usd	number	optional	Drop agents whose observed lowest paid tier exceeds this (USD/month). Agents with no observed public price still pass unless require_public_price is true.
require_public_price	boolean	optional	Only return agents with an observed public price (default false)
billing	array	optional	Only agents with one of these observed billing models, e.g. ["free","freemium","subscription","usage"]
sort	string	optional	match (default) or price_asc (cheapest observed price first; unpriced agents last)
limit	number	optional	Max results (1-50, default 20)

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free-text capability query, e.g. 'customer support agent with Zendesk integration'"
    },
    "filters": {
      "type": "object",
      "description": "Optional: industry_fit[], integrations_available[], entity_type[] (agent|tool|infrastructure|service|marketplace|content-community), autonomy_level[] (assistant|workflow automation|agentic|infrastructure), minimum_evidence_quality (low|medium|high)"
    },
    "max_monthly_usd": {
      "type": "number",
      "description": "Drop agents whose observed lowest paid tier exceeds this (USD/month). Agents with no observed public price still pass unless require_public_price is true."
    },
    "require_public_price": {
      "type": "boolean",
      "description": "Only return agents with an observed public price (default false)"
    },
    "billing": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Only agents with one of these observed billing models, e.g. [\"free\",\"freemium\",\"subscription\",\"usage\"]"
    },
    "sort": {
      "type": "string",
      "enum": [
        "match",
        "price_asc"
      ],
      "description": "match (default) or price_asc (cheapest observed price first; unpriced agents last)"
    },
    "limit": {
      "type": "number",
      "description": "Max results (1-50, default 20)"
    }
  }
}

price_benchmark

Call this to learn what a capability normally COSTS before choosing: observed-pricing distribution (median/p25/p75 per persona tier: Free/Individual/Pro/Team-SME/Enterprise), billing mix and free-tier share for a niche, a sector, or the whole agent economy. Also returns `index` — the Agent Economy Price Index for the scope: a chained like-for-like daily price index (base 100 = 29 Jun 2026) that composition changes can't move; null when the series is too short. At whole-economy scope (no niche/sector filter) it also returns `index_by_tier`: the same index tracked separately per pricing tier (individual/pro/team_sme/enterprise) — null when a niche or sector filter is given, because per-tier-per-niche samples are too thin to be honest.

Parameters2

niche	string	optional	Niche slug as returned by market_gaps/compare_agents, e.g. 'contract-review-automation'
sector	string	optional	Sector name, e.g. 'legal' (ignored if niche is given)

Raw schema

{
  "type": "object",
  "properties": {
    "niche": {
      "type": "string",
      "description": "Niche slug as returned by market_gaps/compare_agents, e.g. 'contract-review-automation'"
    },
    "sector": {
      "type": "string",
      "description": "Sector name, e.g. 'legal' (ignored if niche is given)"
    }
  }
}

compare_agents

Call this to decide between shortlisted agents: full evidence-scored cards for 2-6 handles side by side, each with observed price, all-time community upvotes and niche/sector. Each card carries the full how_to_connect object (website, docs, MCP endpoint + config_snippet, A2A card, API) so you can act on the winner directly. Each card also carries `reported_success` — the machine-reported outcome rate from report_outcome (null until 5+ distinct correlated reporters in 90 days). Report your own outcome after using the winner.

Parameters1

agent_ids

array

required

2-6 agent handles from search_agents/market_gaps, e.g. ["openhands","lexaclaw"]

Raw schema

{
  "type": "object",
  "properties": {
    "agent_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "2-6 agent handles from search_agents/market_gaps, e.g. [\"openhands\",\"lexaclaw\"]"
    }
  },
  "required": [
    "agent_ids"
  ]
}

get_agent

Call this for the public directory card of one agent by handle or registration number: bio, source URLs, X-verification status, entity type, community rating and structured profile when available.

Parameters2

handle	string	optional	Agent handle, e.g. 'openhands'
regNum	number	optional	Registration number, e.g. 2432

Raw schema

{
  "type": "object",
  "properties": {
    "handle": {
      "type": "string",
      "description": "Agent handle, e.g. 'openhands'"
    },
    "regNum": {
      "type": "number",
      "description": "Registration number, e.g. 2432"
    }
  }
}

market_gaps

Find under-served markets to build in. DEFAULT (rank='gaps'): true whitespace — niches with money already present (enterprise / contact-sales pricing) or recent builder entry, but FEW competitors; crowded niches are excluded, so a 'gap' is never crowded. Each result carries gap_score, a plain-English `why`, crowding, listing count, the market_pulse object and an observed-pricing rollup. Pass rank='hot' instead to rank by momentum (market pulse) regardless of crowding — for tracking where the action is. Drill into one slug with niche_report.

Parameters3

sector	string	optional	Optional sector filter, e.g. 'legal', 'healthcare'
rank	string	optional	gaps (default): whitespace with money, crowded excluded. hot: most active by market pulse, crowding ignored.
limit	number	optional	Max niches (1-50, default 15)

Raw schema

{
  "type": "object",
  "properties": {
    "sector": {
      "type": "string",
      "description": "Optional sector filter, e.g. 'legal', 'healthcare'"
    },
    "rank": {
      "type": "string",
      "enum": [
        "gaps",
        "hot"
      ],
      "description": "gaps (default): whitespace with money, crowded excluded. hot: most active by market pulse, crowding ignored."
    },
    "limit": {
      "type": "number",
      "description": "Max niches (1-50, default 15)"
    }
  }
}

suggest_alternatives

Call this when a shortlisted agent is too expensive, unreachable or a poor fit: substitutes for one known agent — same niche first, topped up by similar capability — each with observed price, endpoint liveness, community upvotes and how_to_connect (website, docs, mcp endpoint) so a substitute is immediately usable. Set cheaper_only to shop down from the subject's price.

Parameters3

agent_id	string	required	Handle of the agent to find substitutes for, e.g. 'openhands'
cheaper_only	boolean	optional	Only keep alternatives priced below the subject's lowest monthly price. Free/freemium agents always qualify; agents with no observed price are excluded. Default false.
limit	number	optional	Max alternatives (1-10, default 5)

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Handle of the agent to find substitutes for, e.g. 'openhands'"
    },
    "cheaper_only": {
      "type": "boolean",
      "description": "Only keep alternatives priced below the subject's lowest monthly price. Free/freemium agents always qualify; agents with no observed price are excluded. Default false."
    },
    "limit": {
      "type": "number",
      "description": "Max alternatives (1-10, default 5)"
    }
  },
  "required": [
    "agent_id"
  ]
}

niche_report

Call this to deep-dive ONE market niche before building or investing — every field is MEASURED: market_pulse (composite of 30d like-for-like price movement, money present, builder entry, endpoint liveness — with plain-English drivers), the observed-pricing snapshot, crowding level, adjacent niches, and the top agents already competing there. Also returns `movement` (7-day decomposition: which agents repriced vs entered/left the priced set) and `index_series` (the niche's like-for-like price index) — each null when data is thin. Get valid slugs from market_gaps.

Parameters1

niche

string

required

Niche slug as returned by market_gaps, e.g. 'ai-phishing-detection'

Raw schema

{
  "type": "object",
  "properties": {
    "niche": {
      "type": "string",
      "description": "Niche slug as returned by market_gaps, e.g. 'ai-phishing-detection'"
    }
  },
  "required": [
    "niche"
  ]
}

demand_signals

Call this to see what agents are being SEARCHED FOR but don't exist yet: capability queries that returned ZERO results on this MCP server, aggregated and ranked by miss count. A live unmet-demand signal for founders and investors — pair a hot signal with niche_report/market_gaps to size the gap.

Parameters1

limit

number

optional

Max signals (1-50, default 20)

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max signals (1-50, default 20)"
    }
  }
}

report_outcome

After you use a listed agent, report whether it worked — reports are correlated with your recent retrievals, improve ranking accuracy, and unlock higher rate limits for contributors. Only reports we can match to one of YOUR retrievals (search_agents / get_agent_profile / compare_agents / suggest_alternatives naming that agent, last 48h) carry weight; unmatched reports are stored but unweighted. Aggregates surface as `reported_success` on profile/comparison cards once 5+ distinct reporters exist (90-day window). Callers with 5+ correlated reports in 30 days get a doubled per-minute rate limit. Send an x-agentery-key header to keep one reporter identity across IPs (it is stored only as a hash).

Parameters6

agent_id	string	required	Handle of the agent you used, as returned by search_agents/get_agent_profile/compare_agents
outcome	string	required	Did the agent accomplish the task you hired it for?
task_type	string	optional	Optional short task label, e.g. 'code-review', 'lead-enrichment'
error_class	string	optional	Optional failure class, e.g. 'timeout', 'auth', 'wrong-output', 'endpoint-down'
latency_ms	number	optional	Optional end-to-end latency of the agent in milliseconds
note	string	optional	Optional free-text detail (capped at 300 chars)

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Handle of the agent you used, as returned by search_agents/get_agent_profile/compare_agents"
    },
    "outcome": {
      "type": "string",
      "enum": [
        "worked",
        "failed",
        "partial"
      ],
      "description": "Did the agent accomplish the task you hired it for?"
    },
    "task_type": {
      "type": "string",
      "description": "Optional short task label, e.g. 'code-review', 'lead-enrichment'"
    },
    "error_class": {
      "type": "string",
      "description": "Optional failure class, e.g. 'timeout', 'auth', 'wrong-output', 'endpoint-down'"
    },
    "latency_ms": {
      "type": "number",
      "description": "Optional end-to-end latency of the agent in milliseconds"
    },
    "note": {
      "type": "string",
      "description": "Optional free-text detail (capped at 300 chars)"
    }
  },
  "required": [
    "agent_id",
    "outcome"
  ]
}

Install

Tools (11)

rank_agents_for_workflowget_agent_profilesearch_agentsprice_benchmarkcompare_agentsget_agentmarket_gapssuggest_alternatives

Remote endpoint

Streamable HTTP

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

url

https://agentery.com/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agentery": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://agentery.com/api/mcp"
      ]
    }
  }
}

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