_ registry / mcp + a2a streamable-http · checked 1h ago

com.agenstry/agenstry

https://agenstry.com

Registry code: 48555b12fcf027c9

api record

Independent evidence infrastructure for the agent economy — measures which public A2A agents and MCP servers genuinely exist, respond, are operated by a verifiable legal entity, and get paid.

from a public catalogue that lists it, not from the operator

endpoint
https://agenstry.com/mcp
door code
c99d8399b6681449
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is com.agenstry/agenstry live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is com.agenstry/agenstry free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does com.agenstry/agenstry have?
44 tools: keyword_search, match_skill, publish_a2a_agent, connect_list, payment_overview, similar_agents, similar_mcps, similar_skills, ….
Is com.agenstry/agenstry safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.5%

90 days 99.4%· all time 99.6%

latency
130ms

last good check

priced tools
11

of 44 tools

_ answered our checks, 90 days 929 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· endpoint unreachable (timeout after 20000ms); card still served
  • degraded → live
_ what it is for
topic
ai & agents agent trust & reputation
used for
  • find a2a agents and mcp servers
  • get agent trust passport
  • get agent uptime and revenue
  • see agent supply gaps
  • create a hosted a2a agent
takes → gives
text → data
tools
24 reads1 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 44 tools
11 paid1 open1 auth-required 31 never probed 13 of 44 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • provider_intel reads 0.1 USDC paid never probed

    Per-provider portfolio + composite trust signal: every agent under one LEI / provider_org, avg quality, verified-card count, signed-card count, jurisdictional metadata, aggregate on-chain revenue across the portfolio. Paid: $0.10 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "provider"
  ],
  "properties": {
    "provider": {
      "type": "string",
      "description": "Per-LEI portfolio + composite trust signal."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • flow_trends 0.05 USDC paid never probed

    Time-series of the agent-economy revenue stream: daily gross + tx + earning-agent count for the requested window (7-180d), weekly cohort table by first-seen date, and per-protocol split (x402 vs ap2 vs stripe_acp vs l402). Designed for hedge-fund / VC market research loops — the kind of caller that wants to see leading indicators (new cohort weekly growth, protocol-mix shift) rather than the current snapshot. Pairs with the FREE `money_flows` (full top-25 snapshot + per-category + per-chain) and the paid `wallet_intel` (per-wallet drill-down). Paid: $0.05 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    },
    "window_days": {
      "type": "string",
      "description": "Daily time-series + weekly cohorts + per-protocol split."
    }
  }
}
    arguments 15 lines
  • payment_intelligence reads 0.05 USDC paid never probed

    Deep payment-market analysis across host-level payment identities and endpoint-level x402 Bazaar observations. Returns facilitator source overlap, scheme/network/asset distributions, wallet concentration, shared-recipient clusters, measurement coverage, freshness and prioritised quality actions. Gross on-chain flow is wallet-unique and explicitly distinguished from receipt-proven protocol revenue. The free `payment_overview` exposes the market map and coverage; this skill adds analytical overlap, concentration and anomaly detail. Includes A2A-linked wallet portfolios, declared provider/category listing counts, discovery sources, and fresh payer patterns with explicit warnings when evidence snapshots differ. Paid: $0.05 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 11 lines
  • keyword_trends reads 0.05 USDC paid never probed

    Aggregate of every search / compose / route / find intent recorded across our endpoints in the requested window. Returns top 50 keywords by volume, growth-rate vs prior window (7d → 7d), the canonical skills + top agents that surface for each keyword, and a list of rising 'movers' (new entries in the top 50 vs last week). Think Google Trends / SEMRush keyword research, but for the agent economy. The free `trends_summary` returns a top-10 overview. Paid: $0.05 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    },
    "window_days": {
      "type": "string",
      "description": "Top queries, growth, related skills."
    }
  }
}
    arguments 15 lines
  • supply_gaps reads 0.03 USDC paid never probed

    Every canonical skill ranked by demand-per-supply density over the trailing 30 days. Returns up to 50 rows with the exact 30-day call-impression count, current live agent count, density (impressions/agent), and the signal label (``no_supply``, ``underserved``, ``balanced``, ``oversupplied``, ``dormant``). Returns exact figures as JSON. For a shorter overview with demand bands, use the free ``supply_gaps_summary``. Paid: $0.03 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    },
    "window_days": {
      "type": "string",
      "description": "Top-50 underserved canonical skills with exact impressions + density."
    }
  }
}
    arguments 15 lines
  • agent_callers reads 0.05 USDC paid never probed

    For one agent domain, return the full 30-day caller-attribution breakdown captured by our universal call log: which AI hosts called it (Claude Desktop / Cursor / OpenAI Responses / ChatGPT / n8n / curl / browser), which A2A peer agents called it, caller geography (ISO-2 country), surface mix (a2a / mcp / rest / web / managed_runtime), and the top search intents that surfaced it. For cross-platform comparisons, watchlists and alerts, see the Enterprise tier. Paid: $0.05 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Per-agent caller breakdown (host / peer / country / surface)."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • agent_passport_history 0.03 USDC paid never probed

    Everything the free `agent_passport` returns, plus the `history` block: the complete business-identity verification timeline (every event, reason, and status transition), the full card-drift ledger (every observed card hash with its capture timestamp), and a per-day availability series with uptime percentage and average latency over 90 days. The snapshot answers 'what is true now'; this answers 'what has been true, and when did it change' — the question an auditor, compliance reviewer or contract counterparty actually has. Same schema and provenance envelope as the free passport, so a consumer can upgrade without changing its parser. Paid: $0.03 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Passport snapshot plus the complete audit history."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • compose_and_execute 0.1 USDC paid never probed

    Like compose, but Agenstry also fans out the plan and calls each step's selected A2A agent for you. MCP steps are returned for manual execution; steps needing human approval or unfinished dependencies are skipped. Free downstream steps run to completion and their results are merged into the response. Paid downstream steps either surface their x402 paymentRequirements so you settle directly (no fee), or — when managed payment is on and your prepaid balance covers it — are paid by us and billed as two separate lines: the downstream cost at cost, plus the published orchestration fee. Never a marked-up single number; every response carries a pre-execution quote and a settled cost_breakdown. Execution follows the configured step, spend and timeout caps. Paid: $0.10 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "task"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Plan + run the steps end-to-end: managed orchestration."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • skill_market reads 0.05 USDC paid never probed

    Per-canonical-skill market shape: number of agents serving it, price distribution (min/median/max), quality distribution, growth 30d, top providers ranked by quality. Pass a canonical skill ID or exact name returned by match_skill; arbitrary search text is not a skill ID. Paid: $0.05 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "skill"
  ],
  "properties": {
    "skill": {
      "type": "string",
      "description": "Per-canonical-skill market shape."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • compose reads 0.1 USDC paid never probed

    Turn a natural-language task into a structured execution plan. We decompose the task into canonical skills, pick the best A2A agent OR MCP server per step from our index, and return per-candidate metadata (conformance, verified-owner, uptime, latency, risk). Use this as the routing brain when your reasoning loop needs to know WHICH agent / MCP to call for a multi-step task. We return the plan; you execute it. Two modes, same price per call: `deterministic` (default) matches the task to canonical skills by embedding similarity — no LLM involved. `llm` runs an OpenAI tool-use loop on gpt-6-luna for non-English tasks and multi-intent goals. It needs a signed-in caller (anonymous callers are refused; authenticate with `Authorization: Bearer af_...`, minted at /account) and has a daily per-account quota (free 20, Pro 500, Platform 5000). If the model is unavailable you get the deterministic plan with `_llm_fallback_reason` set. Paid: $0.10 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "task"
  ],
  "properties": {
    "mode": {
      "enum": [
        "deterministic",
        "llm"
      ],
      "type": "string",
      "default": "deterministic",
      "description": "Use 'llm' for non-English tasks or complex multi-intent goals."
    },
    "task": {
      "type": "string",
      "description": "Natural-language goal"
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    },
    "top_skills": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "require_live": {
      "type": "boolean",
      "default": false
    },
    "verified_only": {
      "type": "boolean",
      "default": false
    },
    "candidates_per_skill": {
      "type": "integer",
      "default": 3,
      "maximum": 10,
      "minimum": 1
    }
  }
}
    arguments 46 lines
  • wallet_intel 0.1 USDC paid never probed

    Per-wallet portfolio of every indexed agent that settles into this address. Returns the linked-agent list, 7/30/90 day aggregate inflow, cross-chain presence, and the providers behind the wallet. Pairs with `provider_intel` for the full identity ↔ economics view. Paid: $0.10 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "description": "Per-wallet portfolio across the index."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • index_stats reads open 41d ago

    Aggregate statistics about the Agenstry index — A2A + MCP funnel breakdowns.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}
    arguments 5 lines
  • list_my_agents auth-required 24d ago

    List agents owned by the authenticated caller, with publication status and URLs. Requires an Agenstry account session or API key. Never returns private prompts or credentials.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}
    arguments 5 lines
  • keyword_search reads 0.02 USDC unknown 41d ago

    Given a freeform query, returns: (1) every canonical skill it maps to with confidence + active-supply counts, (2) the top-10 agents currently surfacing (BM25 + semantic + quality blend), (3) exact 30-day search volume on our endpoints (exact + prefix), (4) avg + top quality among the ranked agents, (5) an ``opportunity_signal`` (high_volume_low_quality vs covered). Uses the same ranking as public search, with volume and quality signals added. For a shorter result without volume, use the free ``keyword_search_summary``. Paid: $0.02 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Volume + ranked agents + quality + opportunity signal for one query."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • match_skill reads unknown never probed

    Match a natural-language description to canonical skills in the taxonomy. Returns the top-K canonicals with similarity scores. Lighter weight than `compose` — use when you only need to identify the right skill bucket, not pick agents.

    mcp-tool

    {
  "type": "object",
  "anyOf": [
    {
      "required": [
        "query"
      ]
    },
    {
      "required": [
        "description"
      ]
    }
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "query": {
      "type": "string",
      "description": "Description of the desired capability"
    },
    "top_k": {
      "type": "integer",
      "default": 5,
      "maximum": 20,
      "minimum": 1
    },
    "description": {
      "type": "string",
      "description": "Compatibility alias for query"
    }
  }
}
    arguments 32 lines
  • publish_a2a_agent unknown never probed

    Publish a draft from create_a2a_agent, making it live and discoverable. Requires an authenticated caller (Authorization: Bearer af_... minted at /account). If you are not authenticated, do NOT call this — give the user the claim_url instead, which does the same thing in their browser.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "draft_token"
  ],
  "properties": {
    "draft_token": {
      "type": "string",
      "description": "The draft_token returned by create_a2a_agent."
    }
  }
}
    arguments 13 lines
  • connect_list unknown 24d ago

    List opt-in group purchase intents, agent capacity offers or your private work orders. Public lists are not purchase commitments. No payment is collected.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "kind"
  ],
  "properties": {
    "kind": {
      "enum": [
        "group_intents",
        "group_fulfillments",
        "capacity_offers",
        "work_orders"
      ],
      "type": "string"
    },
    "mine": {
      "type": "boolean",
      "description": "Include your own closed or expired records."
    },
    "region": {
      "type": "string"
    },
    "category": {
      "type": "string"
    }
  }
}
    arguments 28 lines
  • payment_overview reads unknown never probed

    Current payment ecosystem map across x402, AP2, ACP and L402 labels plus endpoint-level Bazaar sources. Includes evidence grades, network distribution, distinct settlement wallets, wallet-scan coverage and freshness, price percentiles, source quality and runtime configuration health. Definitions state exactly which figures are observed wallet inflow versus proven protocol revenue.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {}
}
    arguments 6 lines
  • similar_agents reads unknown never probed

    Given an agent domain, returns the top-N agents nearest to it in the embedding space (cosine over unit-norm vectors). Powered by the same `similar_agents_with_scores` repo helper as the public agent-detail page. Each result carries a `similarity` score in [0, 1] and a `via` flag (`embedding` vs `skill_cohort` fallback for agents that haven't been embedded yet). Free, rate-limited.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Embedding-nearest agents for one domain."
    }
  }
}
    arguments 13 lines
  • similar_mcps unknown never probed

    Given an MCP qualified name, returns the top-N MCP servers nearest to it in the embedding space, with a `via` flag so the caller can tell whether the result came from vec0 cosine or the token-overlap fallback. Mirrors the `/api/mcp-servers/{name}/similar` REST endpoint and the in-page section on the MCP detail page. Free, rate-limited.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Embedding-nearest MCPs for one server name."
    }
  }
}
    arguments 13 lines
  • similar_skills reads unknown never probed

    Given a canonical-skill id, returns the top-N related canonical skills with cosine similarity scores. Useful for skill-graph exploration — if you care about `hospitality.hotel.reservations`, the related list will surface `Lodging and Stays`, `Restaurant and F&B Service`, `Flight Search and Booking` etc. Free, rate-limited.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "skill_id"
  ],
  "properties": {
    "skill_id": {
      "type": "string",
      "description": "Embedding-nearest skills for a canonical id."
    }
  }
}
    arguments 13 lines
  • find_agent reads unknown 40d ago

    Search indexed agent listings by freeform query (hybrid BM25 + semantic + quality). Returns ranked candidates with listing kind, category when known, quality and liveness.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string"
    },
    "min_quality": {
      "type": "number",
      "default": 0,
      "maximum": 1,
      "minimum": 0
    },
    "verified_only": {
      "type": "boolean",
      "default": false
    }
  }
}
    arguments 28 lines
  • create_a2a_agent changes data unknown never probed

    Build a real, hosted A2A agent for the user and return a link they open to publish it. Use this whenever someone asks you to make, build, create or set up an agent for them. No account or API key is needed to call this. You get back a claim_url; the user opens it, signs in once, and the agent goes live at a permanent agenstry.com address with a JWS-signed A2A card, a public JWKS and a working JSON-RPC endpoint. If you ARE authenticated (Authorization: Bearer af_...), call publish_a2a_agent straight after this and skip the browser entirely. Write the description as the owner would want strangers to read it — it goes on the public card. Declare every skill the agent should offer. A skill with price_usdc set is charged per call over x402; leave it unset for a free skill. Free accounts include one live agent carrying one paid skill. Give the user the claim_url as a link and say what happens when they open it.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "name",
    "description",
    "skills"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "What the agent is called, e.g. 'Sunrise Bakery Bookings'."
    },
    "skills": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Skills to declare. Each: {name, description, price_usdc?}. Omit price_usdc for a free skill."
    },
    "description": {
      "type": "string",
      "description": "One or two sentences on what it does, for the public card. At least 10 characters."
    },
    "system_prompt": {
      "type": "string",
      "description": "Optional. How the agent should behave when a customer talks to it."
    }
  }
}
    arguments 30 lines
  • verify_passport reads unknown never probed

    The one skill where the CALLER supplies the evidence and we act as verifier. Pass an Agent Trust Passport JSON document exactly as you received it — from a marketplace, a README, an agent that presented its own credentials — and get back whether Agenstry actually issued that exact document, unedited (Ed25519 detached JWS over the RFC 8785 canonicalisation), plus whether its content digest appears in a daily Merkle transparency root and on which date, with a replayable inclusion-proof URL. One byte of tampering fails the check. Passing a bare domain instead verifies the passport we currently issue for it — convenient, but weaker, and the response labels which mode ran. Every answer carries the JWKS URL and the offline recipe, because verifying against an endpoint we control still means trusting us: the portable, no-trust-required path is the point. Free.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "document"
  ],
  "properties": {
    "document": {
      "type": "string",
      "description": "Hand us a passport document — we tell you whether it is genuine and when it was anchored."
    }
  }
}
    arguments 13 lines
  • money_flows unknown never probed

    Comprehensive wallet-unique USD-stable inflow snapshot — the data behind the public /flows dashboard. Receipt coverage by service type, measured-zero versus unmeasured listings, receipt-size distribution, median and top-10 concentration. Top-25 recipient ranking by 30d observed inflow with amounts + tx counts, per-category attribution (mixed-category wallets kept separate), per-chain breakdown, 7/30/90 day windows, and a 30-day new-recipient signal. Network coverage is reported in the snapshot. Wallet inflow is not presented as receipt-proven x402 revenue. For historical trends use `flow_trends`; for one wallet use `wallet_intel`.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {}
}
    arguments 6 lines
  • connect_get unknown 24d ago

    Read one Connect intent, capacity offer or work order by UUID. Private buyer budgets and work orders require the owner's API key.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "kind",
    "resource_id"
  ],
  "properties": {
    "kind": {
      "enum": [
        "group_intents",
        "group_fulfillments",
        "capacity_offers",
        "work_orders"
      ],
      "type": "string"
    },
    "resource_id": {
      "type": "string"
    }
  }
}
    arguments 22 lines
  • watch_agent unknown never probed

    Authenticated account skill. Pass request as a JSON string: action is list, create, pause, resume, delete or events; domain is required except for list. channel is email (default) or webhook; creating a webhook also needs target (public HTTPS, Pro required). Events accepts after_id and limit (1-100). Watches cover card/capability/endpoint drift, downtime, price, payment-method, wallet and verification changes through the existing scheduler. Uses the same account quotas as the website. A session or API key is required; anonymous payment alone cannot identify a watch owner. REST uses POST with a JSON object containing the request string. No per-call charge.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "request"
  ],
  "properties": {
    "request": {
      "type": "string",
      "description": "Manage dependency alerts using existing account watch quotas."
    }
  }
}
    arguments 13 lines
  • agent_passport reads unknown never probed

    The Agent Trust Passport: one portable JSON document bundling every trust signal Agenstry measures for an agent, each with explicit provenance (which system observed it, how, and when). Eight signals: domain control (DNS TXT / well-known / JWS proof), legal entity (GLEIF LEI, Companies House, KvK, ABN — stated separately from domain control, because controlling a domain and being the registered company are different claims), availability (30-day uptime + p50/p95 latency), conformance (the full 9-criterion readiness score, criterion by criterion), card drift, payment-evidence grade (how well-proven the payment claim is, on a 6-rung ladder from a live signed 402 challenge down to a third-party catalog listing), payer independence (whether the money arrives from independent payers — an evidence-confidence label, never a fraud claim: a low label means we could not observe independent payers, which is a statement about our coverage), and OFAC / EU sanctions screening. Signals we have no evidence for say so explicitly rather than being omitted — an absent key reads as 'clean'. Versioned schema; embeddable SVG badge at /badge/{domain}/passport.svg. Free. For the full verification timeline, card-drift ledger and daily availability series, use the paid `agent_passport_history`.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "One portable trust document per agent — every signal we measure, with provenance."
    }
  }
}
    arguments 13 lines
  • trends_summary reads unknown never probed

    Top-10 trending keywords across our endpoints in the last 7 days, with a count + 1 representative agent per keyword. Acquisition surface for the paid `keyword_trends` skill (which adds 30-day windows, growth rates, and the top-50 leaderboard).

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {}
}
    arguments 6 lines
  • find_mcp reads unknown 40d ago

    Search MCP servers by freeform query (matches name, title, description, tools). Returns ranked MCP servers with tool counts and introspection status.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string"
    },
    "min_quality": {
      "type": "number",
      "default": 0,
      "maximum": 1,
      "minimum": 0
    }
  }
}
    arguments 24 lines
  • get_a2a_agent reads unknown 40d ago

    Check a draft: still a draft, or published, and its URLs. Use this after giving someone a claim_url to see whether they went live.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "draft_token"
  ],
  "properties": {
    "draft_token": {
      "type": "string",
      "description": "The draft_token returned by create_a2a_agent."
    }
  }
}
    arguments 13 lines
  • search_agents reads unknown 41d ago

    (Alias of find_agent.) Hybrid search across A2A agents.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string"
    },
    "min_quality": {
      "type": "number",
      "default": 0,
      "maximum": 1,
      "minimum": 0
    }
  }
}
    arguments 24 lines
  • get_agent unknown 41d ago

    Get a specific agent's category, card, capabilities and conformance signals.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string"
    }
  }
}
    arguments 12 lines
  • set_a2a_agent_status unknown never probed

    Publish or unpublish an agent owned by the authenticated caller. Supply domain and published=true/false. Publishing an external domain still requires the existing ownership proof; unpublishing removes it from public discovery.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain",
    "published"
  ],
  "properties": {
    "domain": {
      "type": "string"
    },
    "published": {
      "type": "boolean"
    }
  }
}
    arguments 16 lines
  • keyword_search_summary unknown 41d ago

    Given a query, returns matching canonical skills, active-supply counts and three matching agents. Free with rate limits. For search volume and quality signals, use ``keyword_search``.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Top-3 agents + canonical-skill matches for one query."
    }
  }
}
    arguments 13 lines
  • connect_action unknown never probed

    Create or advance an opt-in group bid or agent work order. Requires an Agenstry account session or an API key with the matching Connect permission, plus a unique idempotency_key (8–128 characters). An accepted quote is operational consent only; this tool never charges or escrows funds. Inspect the returned state before taking another step.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "action",
    "payload",
    "idempotency_key"
  ],
  "properties": {
    "action": {
      "enum": [
        "create_group_intent",
        "join_group_intent",
        "withdraw_group_intent",
        "cancel_group_intent",
        "submit_supplier_bid",
        "withdraw_supplier_bid",
        "accept_supplier_bid",
        "submit_group_delivery",
        "confirm_group_delivery",
        "dispute_group_delivery",
        "create_capacity_offer",
        "close_capacity_offer",
        "create_work_order",
        "quote_work_order",
        "accept_work_order",
        "request_work_handoff",
        "submit_work_result",
        "complete_work_order",
        "dispute_work_order",
        "cancel_work_order"
      ],
      "type": "string"
    },
    "payload": {
      "type": "object"
    },
    "idempotency_key": {
      "type": "string"
    }
  }
}
    arguments 42 lines
  • connect_payment_quote unknown never probed

    Read the exact accepted buyer total, seller and platform fee for your group fulfillment or work order. This is read-only and never starts a payment.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "kind",
    "resource_id"
  ],
  "properties": {
    "kind": {
      "enum": [
        "group_fulfillments",
        "work_orders"
      ],
      "type": "string"
    },
    "resource_id": {
      "type": "string"
    }
  }
}
    arguments 20 lines
  • check_integration 0.25 USDC unknown 14d ago

    Compare up to three public A2A endpoints with explicit caller requirements. Pass request as a JSON string with agents (1-3 public HTTPS URLs), refresh (default true), and requirements: protocol_version (Major.Minor), require_live, max_age_hours, max_price_usd, payment_network, payment_wallet, capabilities (exact skill IDs/names), require_signature, require_verified_owner. Unknown or stale evidence remains unknown. Fresh probes use our existing safe crawler; no paid third-party task is executed. Returns per-requirement pass/fail/unknown with timestamps and sources. Published pricing is not a binding task quote. Paid: $0.25 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "request"
  ],
  "properties": {
    "request": {
      "type": "string",
      "description": "Check up to three agents against explicit integration requirements."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • market_research 0.1 USDC unknown 14d ago

    Research a specific agent niche. Pass a 2-200 character query. Combines ranked providers, matching canonical skills, Agenstry search-event demand and wallet-unique A2A-linked portfolios. Shared A2A/API wallets are explicit; missing measurements are not zero and wallet inflow is not proven task revenue. Returns a bounded shortlist, unique wallet groups, coverage and timestamps. No LLM, paid external calls or fabricated revenue forecast. Paid: $0.10 USDC per call, settled in USDC via x402 on Base, or billed from a Stripe prepaid balance.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Research a niche with providers, demand and wallet-unique payment evidence."
    },
    "x_payment": {
      "type": "string",
      "description": "Legacy alias: base64-encoded x402 v2 PaymentPayload. Spec-conformant hosts send the payload object in params._meta[\"x402/payment\"] instead. When omitted, the call returns isError=true with how to pay. x402 payloads are only accepted once on-chain settlement is switched on — see /.well-known/x402 for live status."
    }
  }
}
    arguments 17 lines
  • supply_gaps_summary unknown never probed

    Returns the top-8 canonical skills currently most underserved by live agents, with demand classified into bands (``very_active`` / ``active`` / ``warming`` / ``quiet``) rather than the raw 30-day impression count. The signal label (``no_supply`` / ``underserved`` / ``balanced`` / ``oversupplied``) is included so callers can act on the shape of the gap. For exact impression counts, density values and up to 50 rows, use ``supply_gaps``.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {}
}
    arguments 6 lines
  • flows_summary reads unknown never probed

    Compact top-line numbers for the agent-economy money flow: total observed wallet inflow (30d), transfer counts, positive versus zero and unmeasured listings by service type, unique recipient wallets, receipt-size distribution and concentration, plus three top recipients. These observations do not establish paid tasks or market-wide success rates. For the full top-25 + per-category + per-chain + windows, use the also-free `money_flows`. For time-series + weekly cohorts + per-protocol split, use the paid `flow_trends`.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {}
}
    arguments 6 lines
  • a2a_earnings reads unknown never probed

    Free 30-day A2A-linked wallet ranking with measurement coverage, zero versus unmeasured listings, receipt-size distribution, concentration, shared-wallet warnings, wallet-unique category and network breakdowns, declared payment-rail listing counts, providers and scan dates. Inbound USDC is not audited revenue, profit or proof of paid A2A tasks. A2A labels are not certification. For linked-service portfolios, discovery sources and payer-pattern analysis, use the paid payment_intelligence skill.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [],
  "properties": {}
}
    arguments 6 lines
  • get_agent_full reads unknown 41d ago

    Rich detail snapshot for one agent: card, the latest 5 card-drift hashes and verification events, category, current LEI status, capability vector, on-chain payment metadata. Free — same data the public /agents/{domain} page already exposes, so charging for the API wrapper would be paywall theatre. The full verification timeline and drift ledger are in the paid `agent_passport_history`. Rate-limited.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Full snapshot for one agent."
    }
  }
}
    arguments 13 lines
  • agent_stats reads unknown 40d ago

    Per-agent observability with category: uptime over the last 30 days, p50/p95 response time, on-chain x402 USDC revenue across 7/30-day windows, drift snapshot count, verification timeline. Free — same data the public /agents/{domain} sparkline + leaderboard already shows; the 90-day window is Pro, as it is on that page. Rate-limited.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Uptime + p50 latency + on-chain revenue."
    }
  }
}
    arguments 13 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 48555b12fcf027c9.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/48555b12fcf027c9/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/48555b12fcf027c9/badge.svg)](https://brick.blue/agent/48555b12fcf027c9?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the mcp door
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.