Is api-evangelist live?

Yes — it answered the hub's last check (checked 25m ago). It answered 100% of checks over the last 30 days.

Is api-evangelist free to use?

Yes — the hub reached it with no key and no payment.

What tools does api-evangelist have?

83 tools: get_service, get_contact, find_posts, get_post, get_area, get_building_block, get_timeline, get_tag, ….

Is api-evangelist 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.

_ registry / mcp + a2a streamable-http · checked 25m ago

api-evangelist

https://apievangelist.com

Registry code: d9128ce15e0bbc25

api record

Sixteen years of API research plus a governance compute layer, as tools, prompts, and resources. LIGHTER ENDPOINTS: this endpoint lists all 82 tools. If you only need one kind of work, connect to a task-scoped toolset instead — same tools, same auth, a fraction of the context: https://mcp.apievangelist.com/mcp/research (31 tools: sixteen years of API research — posts, papers, videos, conversations, areas, tags, building blocks, tools, services, solutions, timeline, feeds); https://mcp.apievangelist.com/mcp/governance (43 tools: the governance compute layer — validate, coverage, scorecard,…

endpoint: https://mcp.apievangelist.com/mcp
door code: 5429641c43c7405c
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 api-evangelist live?: Yes — it answered the hub's last check (checked 25m ago). It answered 100% of checks over the last 30 days.
Is api-evangelist free to use?: Yes — the hub reached it with no key and no payment.
What tools does api-evangelist have?: 83 tools: get_service, get_contact, find_posts, get_post, get_area, get_building_block, get_timeline, get_tag, ….
Is api-evangelist 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

100%

90 days 100%· all time 100%

latency

409ms

last good check

priced tools

of 83 tools

_ answered our checks, 90 days 704 checks · signed record

_ what it is for

topic: developer tools apis & integration
used for: score an api's maturity
compare two openapi versions for breaking changes
find api tools and vendors
generate code samples for an api
search api research articles
takes → gives: code, text → data, code, text
tools: 25 reads

_ 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

through this hub

calls served

successful

paid through this hub

0 USDC

what callers paid

_ what it can do 83 tools

19 open 64 never probed 19 of 83 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.

find_solutions reads open 28h ago

The solutions registry — 740+ third-party API services and tools (gateways, portals, testing, monitoring, …) ranked by adoption across the companies API Evangelist tracks.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

find_tags open 28h ago

Browse and rank the network tag taxonomy — every subject tag across 16k+ docs, by frequency or breadth (how many content types use it). Search with q. The map of what API Evangelist covers.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text matched against tag labels, e.g. \"governance\"."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "count",
        "breadth"
      ],
      "type": "string",
      "description": "\"count\" (default, most-used first) or \"breadth\" (spread across the most content types)."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 34 lines

search_api_evangelist reads open 35h ago

Unified search across the whole network: 5k+ stories, 77 topic areas, 2.5k governance building blocks, papers, conversations, videos, tools, timelines, services, and vocabulary. Filter with types (posts, areas, guidance, rules, policies, standards, strategies, schema, properties, experiences, lifecycle, conversations, videos, papers, services, solutions, tools, timelines, vocabulary).

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "types": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Content types to include — plural resource names: posts, services, solutions, tools, areas, papers, videos, conversations, guidance, rules, policies, standards, strategies…, e.g. [\"posts\",\"papers\"]."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 65 lines

find_areas open 35h ago

The 77 focused topic areas of the network (agents, gateways, security, …), each a subsite with its own catalog.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

find_videos open 26h ago

The API Evangelist video library — interviews and discussions from across the API space, searchable by transcript.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

find_vocabulary open 26h ago

The API vocabulary — thousands of resources, actions, personas, domains, schemas, and tags extracted from the API landscape. Filter by category.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "category": {
      "enum": [
        "resources",
        "actions",
        "personas",
        "domains",
        "schemas",
        "tags"
      ],
      "type": "string",
      "description": "Vocabulary category: resources, actions, personas, domains, schemas or tags."
    }
  }
}

arguments 70 lines

get_overview reads open 11h ago

START HERE. What the API Evangelist network offers: sixteen years of API research as searchable stories, 77 topic areas, governance building blocks (guidance, rules, policies, standards, strategies), papers, conversations, and the consulting services Kin Lane offers teams. Returns counts, entry points, and how to engage.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 9 lines

find_conversations open 33h ago

API Evangelist Conversations — recorded discussions with API practitioners (guest, company, YouTube/SoundCloud links).

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

find_entities reads open 33h ago

Browse the demand-side entity catalog — every service, tool and standard companies are measured against, ranked by how many carry it. Free. This is the left-hand side of the inversion: pick an entity here, then call entity_demand to see WHO.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Substring match on the entity name."
    },
    "kind": {
      "enum": [
        "service",
        "tool",
        "standard"
      ],
      "type": "string",
      "description": "Entity kind: \"service\", \"tool\" or \"standard\"."
    },
    "page": {
      "type": "integer",
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "min_companies": {
      "type": "integer",
      "description": "Only entities carried by at least this many companies."
    }
  }
}

arguments 36 lines

insights_dimensions reads open 43h ago

Cross-section ranking of the 40 tracked investment dimensions (AI, cloud, governance, …) by company signal. Free.

mcp-tool

{
  "type": "object",
  "properties": {
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 22 lines

get_feeds open 18h ago

The static machine-readable feeds every network site publishes (JSON, APIs.json, zero-auth) — the no-key alternative to this API.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 9 lines

governance_report open 11h ago

Turn Spectral findings into a self-contained HTML governance report — severity summary, grouped by rule, framed toward progress.

mcp-tool

{
  "type": "object",
  "required": [
    "results"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "results": {
      "type": [
        "array",
        "object"
      ],
      "description": "Spectral findings to render. An array, or the `{ results: [...] }` object a run returned."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

validate_onboarding open 2d ago

Validate an API Onboarding Descriptor (AID) against the api-commons schema and report which optional sections it fills in.

mcp-tool

{
  "type": "object",
  "required": [
    "descriptor"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "descriptor": {
      "type": [
        "string",
        "object"
      ],
      "description": "An API Onboarding Descriptor (AID) to validate. Aliases: `aid`, `document`."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

find_measured_standards open 31h ago

The standards bodies API Evangelist has actually MEASURED — repositories, maturity, governance, coalition. Distinct from find_standards, which searches 613 catalog entries describing what a standard IS. Free.

mcp-tool

{
  "type": "object",
  "properties": {
    "page": {
      "type": "integer",
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 19 lines

find_papers open 31h ago

API Evangelist papers — single-PDF deep dives on one practice or topic, with outlines.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

find_services open 31h ago

The services API Evangelist offers teams and customers — API strategy, governance, discovery, and evangelism engagements by Kin Lane. The front door to working with API Evangelist. (For the third-party vendor registry, use find_solutions.)

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

find_company_insights reads open 35h ago

Browse profiled companies (Fortune 1000 + API providers) by name; ranked by technology-readiness signal. Free.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text matched against company name, e.g. \"chase\"."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 26 lines

insights_adoption open 2d ago

Services, tools, or standards ranked by how many companies adopt them. Free.

mcp-tool

{
  "type": "object",
  "properties": {
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "type": {
      "enum": [
        "service",
        "tool",
        "standard"
      ],
      "type": "string",
      "default": "service",
      "description": "What to rank by adoption across the companies: \"service\" (default), \"tool\" or \"standard\"."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 32 lines

find_tools reads open 28h ago

The open-source tooling registry — 400+ tools in use across the companies API Evangelist tracks, each with adoption counts and technology-radar placement.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 58 lines

get_service unknown never probed

Full detail for one service offering by slug; include=["content"] inlines the full pitch.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Service slug, as find_services returns it, e.g. \"governance-agent-readiness\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "include": {
      "type": "array",
      "items": {
        "enum": [
          "content"
        ]
      },
      "description": "Pass [\"content\"] to inline the full body (Pro). Omitted, you get the summary."
    }
  }
}

arguments 25 lines

get_contact unknown never probed

Every way to reach API Evangelist — email, contact form, newsletter, GitHub, social channels, and postal mail.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 9 lines

find_posts reads unknown never probed

Search or browse 5,100+ API Evangelist stories (2010–present); filter by year or tags.

mcp-tool

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "year": {
      "type": "string",
      "description": "Four-digit year; only posts whose date starts with it, e.g. \"2024\"."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 62 lines

get_post unknown never probed

One story by slug (YYYY-MM-DD-slug); include=["content"] returns the full markdown body.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Post slug — date-prefixed, as find_posts returns it, e.g. \"2026-09-29-you-cannot-see-your-own-api-from-the-outside\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "include": {
      "type": "array",
      "items": {
        "enum": [
          "content"
        ]
      },
      "description": "Pass [\"content\"] to inline the full body (Pro). Omitted, you get the summary."
    }
  }
}

arguments 25 lines

get_area unknown 43h ago

One topic area with its related-area graph resolved — walk the network from here.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Area slug, as find_areas returns it, e.g. \"agents\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

get_building_block unknown 43h ago

One building block by type + slug; include=["content"] returns the full body.

mcp-tool

{
  "type": "object",
  "required": [
    "type",
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Building-block slug within `type`, as find_building_blocks returns it, e.g. \"access\" with type \"guidance\"."
    },
    "type": {
      "enum": [
        "guidance",
        "rules",
        "policies",
        "standards",
        "strategies",
        "schema",
        "properties",
        "experiences",
        "lifecycle"
      ],
      "type": "string",
      "description": "Building-block type: guidance, rules, policies, standards, strategies, schema, properties, experiences or lifecycle."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "include": {
      "type": "array",
      "items": {
        "enum": [
          "content"
        ]
      },
      "description": "Pass [\"content\"] to inline the full body (Pro). Omitted, you get the summary."
    }
  }
}

arguments 41 lines

get_timeline unknown 24h ago

One of the four research timelines in chronological order: api (the moments that shaped web APIs), resources (which digital resources became APIs and when), industries (the industrial history framing API infrastructure), people (the people who made compute and APIs possible).

mcp-tool

{
  "type": "object",
  "required": [
    "timeline"
  ],
  "properties": {
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "timeline": {
      "enum": [
        "api",
        "resources",
        "industries",
        "people"
      ],
      "type": "string",
      "description": "Which timeline: api, resources, industries or people."
    }
  }
}

arguments 35 lines

get_tag unknown 37h ago

One tag with its per-type counts and everything it labels across the whole network (stories, areas, guidance, papers, …). Filter with types.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "slug": {
      "type": "string",
      "description": "Tag slug, as find_tags returns it, e.g. \"apis\"."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "types": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Only return tagged items of these types, e.g. [\"posts\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 36 lines

company_signals reads unknown never probed

PRO — the company's adopted stack entity by entity (services, tools, standards), each with how many companies across the cohort carry it and its radar ring.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Company slug, as find_company_insights returns it, e.g. \"jp-morgan-chase\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

forge_mcp_tools reads unknown 46h ago

From an OpenAPI, forge an MCP server design, per-operation tools, Agent Skills, an enriched OpenAPI, a server.json, and apis.json properties.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

detect_format unknown 24h ago

Identify a document: OpenAPI (Swagger 2.0 vs 3.x), AsyncAPI, Arazzo, JSON Schema, APIs.json, MCP, an agent SKILL.md, an Overlay or a ruleset — and how many catalog rules and which named profiles apply.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

document_ruleset unknown never probed

Generate human-readable Markdown documentation for a ruleset — each rule's severity, what it checks, its message and how to fix it. Pass `ruleset`, or `profile` for a curated one (owasp, problem-details, fhir, api-authorization).

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

ruleset_from_style_guide unknown never probed

PRO — Turn a prose API style guide into an owned, grounded ruleset: one rule per checkable statement, each validated, with the statements no rule can check listed separately. Test the result with test_ruleset.

mcp-tool

{
  "type": "object",
  "required": [
    "guide"
  ],
  "properties": {
    "guide": {
      "type": "string",
      "description": "The API style guide as prose or Markdown (up to 40 KB)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 17 lines

guide_topic reads unknown 7h ago

PRO — Curated guide to one API topic (e.g. "gateways", "api governance", "discovery", "agents"). Bundles the matching topic area (with related areas), top guidance, rules, policies, and standards, relevant papers and recent stories, plus the API Evangelist services that can help a team with this topic.

mcp-tool

{
  "type": "object",
  "required": [
    "topic"
  ],
  "properties": {
    "topic": {
      "type": "string",
      "description": "The topic to build a guide for."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

reconcile_waivers reads unknown 7h ago

Reconcile a waivers file against lint output: suppress sanctioned violations and surface the expired, stale, and expiring ones. Returns the effective failing set a build should gate on.

mcp-tool

{
  "type": "object",
  "required": [
    "waivers",
    "violations"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "waivers": {
      "type": [
        "string",
        "object"
      ],
      "description": "The waivers file to reconcile — sanctioned violations, with expiry."
    },
    "violations": {
      "type": [
        "array",
        "object",
        "string"
      ],
      "description": "Lint output to reconcile against the waivers. An array of findings, or the object a linter returned."
    }
  },
  "additionalProperties": true
}

arguments 29 lines

apply_overlay unknown 2d ago

Apply an OpenAPI Overlay to a document and report what each action matched. Use it for deprecation and migration choreography without forking the contract.

mcp-tool

{
  "type": "object",
  "required": [
    "document",
    "overlay"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "overlay": {
      "type": [
        "string",
        "object"
      ],
      "description": "An OpenAPI Overlay document whose actions are applied to `document`."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 28 lines

certify_api unknown 2d ago

Issue a tamper-evident governance certificate attesting an API passed a named ruleset at a profile threshold. A SHA-256 fingerprint lets anyone re-verify it.

mcp-tool

{
  "type": "object",
  "required": [
    "api"
  ],
  "properties": {
    "api": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description being attested or verified. String or parsed object."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

describe_rule unknown 26h ago

Look up one rule by id — description, severity, given/then, reference — and its remediation prompt: what to change when it fires. Suggests close matches for an unknown id.

mcp-tool

{
  "type": "object",
  "required": [
    "rule"
  ],
  "properties": {
    "rule": {
      "type": "string",
      "description": "A rule id, e.g. \"info-require-license\" or \"operation-operationId\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 17 lines

map_api_experience unknown 41h ago

Map each REST operation to its MCP tool and Agent Skill — the API -> MCP -> Agent-Skill chain — from an APIs.json, with a free/paid coverage scorecard and a flow map.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

get_company_insight reads unknown 41h ago

Full demand-side profile for one company: 40-dimension readiness, adopted stack, per-quarter history. Pro.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Company slug, as find_company_insights returns it, e.g. \"jp-morgan-chase\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

standard_repositories reads unknown 4h ago

Every repository a standards body publishes, with maturity, stars, forks, open issues and archived status. Free.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "page": {
      "type": "integer",
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "slug": {
      "type": "string",
      "description": "Standards body slug, as find_measured_standards returns it, e.g. \"asyncapi\"."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 26 lines

api_coverage reads unknown 4h ago

Measure how much of an API description your governance actually inspects — coverage by section, each rule's reach, and the rules that match nothing. Like test coverage, one altitude up.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

get_stats reads unknown 25m ago

PRO — catalog intelligence: per-type counts, stories-per-year, and the top tags by reach across the network.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 9 lines

standard_adoption unknown 7h ago

How far a standards body actually got: repositories published, how many graduated past unclassified and the resulting share, release cadence, contributor count — with the provenance of every figure and an explicit list of what is NOT measured. Free, because a specification is a public good.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Standards body slug, as find_measured_standards returns it, e.g. \"asyncapi\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

fingerprint_generator unknown 18h ago

PRO — For a code-first API: identify which OpenAPI generator produced the spec, and split findings into those to fix with code annotations vs. spec authoring, with per-generator remediation.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

fix_diagnostics unknown 18h ago

PRO — Propose an OpenAPI Overlay that fixes the lint errors (or the `rules` you name), apply it, re-lint, and report what was resolved, what newly fires, and any breaking change. Review the overlay before applying it.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

govern_estate unknown 11h ago

PRO — Run the core governance checks across a WHOLE SET of internal APIs and roll them up: per-API score/grade/errors/PII, plus estate aggregates (avg score, grade distribution, APIs with PII/secrets) and a worst-first punch-list of what to fix. Pass `apis` ([{id, document}]) and your own `ruleset`. detail:true adds per-API dimensions.

mcp-tool

{
  "type": "object",
  "required": [
    "apis"
  ],
  "properties": {
    "apis": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "The estate: one entry per API, [{ id, document }]. `document` alone is accepted for a single API."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

baseline_violations unknown 33h ago

PRO — Adopt a ruleset on a legacy API without a wall of red: snapshot today's violations as a baseline, then pass that baseline back to fail only on NEW violations (with fixed counts, a warning budget and burndown).

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

get_guidance_section reads unknown 39h ago

One editorial guidance section as a list: history, technology, business, politics, governance, or evangelism — the six lenses API Evangelist organizes guidance through.

mcp-tool

{
  "type": "object",
  "required": [
    "section"
  ],
  "properties": {
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "section": {
      "enum": [
        "history",
        "technology",
        "business",
        "politics",
        "governance",
        "evangelism"
      ],
      "type": "string",
      "description": "Guidance section: history, technology, business, politics, governance or evangelism."
    }
  }
}

arguments 37 lines

get_paper unknown 39h ago

One paper with its full outline and purchase/landing URL.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Paper slug, as find_papers returns it, e.g. \"change-on-the-agent-surface\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

deprecation_posture unknown never probed

Report every deprecated operation and whether it actually announces a sunset. The ones that go quiet are the ones that break consumers.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

mock_payloads unknown never probed

Generate an example request and success-response payload for every operation from its schema.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

submit_api_evangelist_feedback unknown never probed

Report something wrong with a result: wrong data, a filter that did not filter, a ranking that put off-topic results first, a number you could not reproduce, or an answer that was useless for your task. Free, and the fastest way to get a defect fixed — the support sweep reads the log this lands in. Say what you expected as well as what you got.

mcp-tool

{
  "type": "object",
  "required": [
    "problem"
  ],
  "properties": {
    "tool": {
      "type": "string",
      "description": "Optional name of the tool that produced it."
    },
    "about": {
      "type": "string",
      "description": "Optional slug, area, paper or story the report concerns."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "problem": {
      "type": "string",
      "description": "What was wrong. Be specific — the tool you called, the arguments, and what came back."
    },
    "expected": {
      "type": "string",
      "description": "What you expected instead."
    },
    "severity": {
      "enum": [
        "wrong",
        "misleading",
        "unhelpful"
      ],
      "type": "string",
      "description": "wrong = factually incorrect; misleading = correct but reads as something else; unhelpful = right and useless."
    }
  }
}

arguments 37 lines

company_whitespace unknown 2d ago

PRO — what this company's peers run that it does not, ranked by how many peers carry it. The opening list for a vendor selling into the account.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Company slug, as find_company_insights returns it, e.g. \"jp-morgan-chase\"."
    },
    "limit": {
      "type": "integer",
      "maximum": 200,
      "minimum": 1,
      "description": "How many whitespace rows to return, 1-200."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 22 lines

diff_api_versions reads unknown 2d ago

Compare two OpenAPI versions and classify every change as breaking, non-breaking, or an addition — at path, operation, parameter, request-body, and response granularity.

mcp-tool

{
  "type": "object",
  "required": [
    "old",
    "new"
  ],
  "properties": {
    "new": {
      "type": [
        "string",
        "object"
      ],
      "description": "The CANDIDATE version to compare against the baseline. Aliases: `to`, `revision`."
    },
    "old": {
      "type": [
        "string",
        "object"
      ],
      "description": "The BASELINE version of the document. Aliases: `from`, `base`."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 28 lines

entity_demand unknown 2d ago

PRO — THE INVERSION. Every other insights tool runs company -> stack; this one runs stack -> companies: which companies show demand for a given service, tool or standard, broken down by industry. This is the prospecting query — "who should I be selling this to" — and it exists in no report, bundle or page. Returns BOTH the authoritative company count and the companies it can actually name, with the basis difference explained.

mcp-tool

{
  "type": "object",
  "required": [
    "kind",
    "slug"
  ],
  "properties": {
    "kind": {
      "enum": [
        "service",
        "tool",
        "standard"
      ],
      "type": "string",
      "description": "Entity kind: \"service\", \"tool\" or \"standard\"."
    },
    "slug": {
      "type": "string",
      "description": "Entity slug or display name — either resolves (\"spark\" and \"Apache Spark\" both work)."
    },
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "How many named companies to return, 1-500."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "industry": {
      "type": "string",
      "description": "Restrict the named companies to one industry."
    }
  }
}

arguments 36 lines

classify_api_fields reads unknown 2d ago

Inventory the PII, secret, and sensitive fields an OpenAPI exposes, across parameters and request/response schemas. Run this before exposing an API to agents.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

code_snippets reads unknown 2d ago

Generate runnable curl, JavaScript, and Python samples for every operation, with path params filled in and a realistic body.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

company_dimensions unknown 2d ago

PRO — a company's investment dimensions, each read AGAINST the measured cohort: the cohort median, mean and max, this company's rank and percentile, and an index where 1.0 is exactly typical. A raw dimension score is unreadable on its own; these are the columns that make it mean something.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Company slug, as find_company_insights returns it, e.g. \"jp-morgan-chase\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

find_related unknown 46h ago

Given any doc (type + slug), the most related content across the whole network, ranked by shared-tag relevance (rare, specific tags weigh most). "More like this," across stories, areas, guidance, papers, conversations, and more.

mcp-tool

{
  "type": "object",
  "required": [
    "type",
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Slug of the item to find related content for, within `type`, e.g. \"2026-09-29-you-cannot-see-your-own-api-from-the-outside\"."
    },
    "type": {
      "type": "string",
      "description": "Content type of the item `slug` names — the plural path name: posts, services, solutions, tools, areas, papers, videos, conversations, guidance…, e.g. \"posts\"."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "types": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Only return related items of these types, e.g. [\"papers\",\"posts\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 35 lines

get_video reads unknown 15h ago

One video by slug with its YouTube id; include=["content"] returns the full transcript.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Video slug, as find_videos returns it, e.g. \"adam-duvander\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "include": {
      "type": "array",
      "items": {
        "enum": [
          "content"
        ]
      },
      "description": "Pass [\"content\"] to inline the full body (Pro). Omitted, you get the summary."
    }
  }
}

arguments 25 lines

get_solution reads unknown 39h ago

One solution from the vendor registry by slug, with its website and adoption count.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Solution (vendor) slug, as find_solutions returns it, e.g. \"adobe\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

export_agent_rules reads unknown never probed

Turn a governance ruleset into agent-native guidance — an AGENTS.md block, a system-prompt set, a per-rule remediation pack, and a digest — so agents follow the rules while authoring, not after linting.

mcp-tool

{
  "type": "object",
  "required": [
    "ruleset"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "ruleset": {
      "type": "object",
      "description": "A Spectral ruleset to run instead of the catalog default. Score against rules you never adopted means little — pass your own."
    }
  },
  "additionalProperties": true
}

arguments 17 lines

audit_pipeline unknown 37h ago

Score a repository's Spectral CI setup against an 8-point maturity rubric and return a prioritized punch-list. Pass a public `repo` ("owner/name") or `files`.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

validate_ruleset unknown never probed

Check that an OpenLint/Spectral ruleset is valid BEFORE running or storing it: invalid JSONPath, unknown functions, undefined aliases, and anything the engine rejects. Catalog metadata (title, prompt, x-*) is set aside and reported. Run this on every ruleset you write.

mcp-tool

{
  "type": "object",
  "required": [
    "ruleset"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "ruleset": {
      "type": "object",
      "description": "A Spectral ruleset to run instead of the catalog default. Score against rules you never adopted means little — pass your own."
    }
  },
  "additionalProperties": true
}

arguments 17 lines

query_jsonpath unknown 15h ago

Evaluate a JSONPath (a rule's `given`) against a document and return what it matches — pointers, values, and optionally whether `field` is present on each match. The fastest way to get a `given` right.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

test_ruleset unknown never probed

Run a ruleset against fixture documents with expectations — codes that must fire, exact counts, or a clean lint — and report pass/fail per case plus which rules no case asserts on or ever triggers.

mcp-tool

{
  "type": "object",
  "required": [
    "ruleset",
    "cases"
  ],
  "properties": {
    "cases": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Fixtures: [{ name, document, expect }] where `expect` is a list of rule codes that must fire, a { code: count } map, or [] for a clean lint. Optional `forbid`: codes that must not fire."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "ruleset": {
      "type": "object",
      "description": "A Spectral ruleset to run instead of the catalog default. Score against rules you never adopted means little — pass your own."
    }
  },
  "additionalProperties": true
}

arguments 25 lines

get_tool unknown 21h ago

One tool from the tooling registry by slug, with its website, adoption count, and radar ring.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Tool slug, as find_tools returns it, e.g. \"ajv\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

lint_agent_skill unknown 15h ago

Lint an agent SKILL.md (markdown with YAML frontmatter) against the API Commons skill rules — name, description, structure, metadata.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

federate_rulesets unknown never probed

PRO — Model a central baseline ruleset and the domains that adopt it (inherit / override / waive / defer / local rules) and compute divergence per rule, drift per domain, and local rules worth promoting.

mcp-tool

{
  "type": "object",
  "required": [
    "federation"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "federation": {
      "type": [
        "string",
        "object"
      ],
      "description": "The federation model: { central: { rules: [{ code, severity }] }, domains: [{ id, adoptions: [{ code, state, severity?, reason? }] }] }. YAML/JSON string or object."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

get_org_ruleset unknown never probed

PRO — Read your org default ruleset: the one every governance call without its own `ruleset` runs against.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

set_org_ruleset unknown never probed

PRO — Store an org default ruleset (validated first). From then on validate, coverage, scorecard, estate, baseline, codefirst and fix use it whenever no `ruleset` is passed.

mcp-tool

{
  "type": "object",
  "required": [
    "ruleset"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "ruleset": {
      "type": "object",
      "description": "A Spectral ruleset to run instead of the catalog default. Score against rules you never adopted means little — pass your own."
    }
  },
  "additionalProperties": true
}

arguments 17 lines

gate_agent_context unknown 24h ago

Choose which operations and fields an API exposes to agents and emit a governed Tyk OpenAPI, an MCP tool manifest, and a Spectral ruleset with PII and secret checks.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

get_conversation unknown 41h ago

One conversation with guest detail and media links; include=["content"] returns the writeup.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Conversation slug — date-prefixed, as find_conversations returns it, e.g. \"2026-09-01-lukasz-gornicki\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "include": {
      "type": "array",
      "items": {
        "enum": [
          "content"
        ]
      },
      "description": "Pass [\"content\"] to inline the full body (Pro). Omitted, you get the summary."
    }
  }
}

arguments 25 lines

verify_certificate unknown 2d ago

Re-verify a governance certificate against the API it attests to. If the API drifted or the certificate was forged, verification fails.

mcp-tool

{
  "type": "object",
  "required": [
    "certificate",
    "api"
  ],
  "properties": {
    "api": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description being attested or verified. String or parsed object."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "certificate": {
      "type": [
        "string",
        "object"
      ],
      "description": "The governance certificate to re-verify. Alias: `cert`."
    }
  },
  "additionalProperties": true
}

arguments 28 lines

company_peers unknown 2d ago

PRO — the companies most comparable to this one (same sub-sector where the data supports it, same industry otherwise), each with signal totals and top dimensions. The response says which basis it used.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Company slug, as find_company_insights returns it, e.g. \"jp-morgan-chase\"."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "How many peers to return, 1-100."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 22 lines

find_building_blocks unknown 46h ago

Search the governance building blocks by type: guidance (177), rules (617), policies (283), standards (432), strategies (75), schema (11), properties (790), experiences (46), lifecycle (29).

mcp-tool

{
  "type": "object",
  "required": [
    "type"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "Free text over title, summary, tags, and body."
    },
    "page": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Page number, 1-based (default 1). Use with `limit` to walk a long list."
    },
    "sort": {
      "enum": [
        "default",
        "title",
        "date"
      ],
      "type": "string",
      "description": "Order when there is no `q`: \"default\" (dated content newest first, the rest A-Z), \"title\" (A-Z) or \"date\" (newest first). A `q` always orders by relevance."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tag slugs; match any by default."
    },
    "type": {
      "enum": [
        "guidance",
        "rules",
        "policies",
        "standards",
        "strategies",
        "schema",
        "properties",
        "experiences",
        "lifecycle"
      ],
      "type": "string",
      "description": "Building-block type: guidance, rules, policies, standards, strategies, schema, properties, experiences or lifecycle."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page, 1-100 (default 25)."
    },
    "match": {
      "enum": [
        "any",
        "all"
      ],
      "type": "string",
      "default": "any",
      "description": "How multiple `tags` combine: \"any\" (default, at least one) or \"all\" (every tag)."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Return only these keys on each record, e.g. [\"slug\",\"title\",\"url\"]."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 76 lines

generate_agent_descriptor reads unknown 21h ago

Generate an API's llms.txt and an AGENTS.md consumption contract — base URL, auth, the operation table, deprecated operations to avoid, and usage rules.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

company_gaps unknown 2d ago

A company's weakest investment dimensions — where it is thin. Pro.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Company slug, as find_company_insights returns it, e.g. \"jp-morgan-chase\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

score_reusability unknown 37h ago

Score how reusable a set of APIs is and detect duplication across them — the anti-sprawl view of an estate.

mcp-tool

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  },
  "additionalProperties": true
}

arguments 10 lines

standard_coalition unknown 4h ago

Who is actually behind a standard: the governing bodies and their membership, the working groups, the member companies, and the named people. Carries the caveats where our machine-readable source disagrees with the body's own published roster. Free.

mcp-tool

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Standards body slug, as find_measured_standards returns it, e.g. \"asyncapi\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    }
  }
}

arguments 16 lines

explain_rule_result unknown 21h ago

Explain why a rule did or did not fire on a document: whether its formats matched, what its `given` matched, what `then` checked, and the verdict. Works for your own rules, the catalog, and the built-ins.

mcp-tool

{
  "type": "object",
  "required": [
    "document",
    "rule"
  ],
  "properties": {
    "rule": {
      "type": "string",
      "description": "A rule id, e.g. \"info-require-license\" or \"operation-operationId\"."
    },
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 25 lines

validate_api unknown 25m ago

Lint an OpenAPI, AsyncAPI, Arazzo, or JSON Schema document against the curated best-of-breed ruleset (Spectral) and return the findings. Pass your own `ruleset` to run rules you own instead of the catalog — which is what you should do before gating on anything.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 lines

api_scorecard reads unknown 25m ago

Score an API's maturity 0-100 with a letter grade across design, governance coverage, documentation, and (from an apis.json) discoverability, agent-readiness, and operations. Pass your own `ruleset` — a score against rules you never adopted means little.

mcp-tool

{
  "type": "object",
  "required": [
    "document"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."
    },
    "document": {
      "type": [
        "string",
        "object"
      ],
      "description": "The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted."
    }
  },
  "additionalProperties": true
}

arguments 20 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.

Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
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.
Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id d9128ce15e0bbc25.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/d9128ce15e0bbc25/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/d9128ce15e0bbc25/badge.svg)](https://brick.blue/agent/d9128ce15e0bbc25?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

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.

_ also on apievangelist.com 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

mcp.apievangelist.com mcp · 67 tools