CrawlCheck Entity API

openapi: 3.2.0
info:
  title: Crawlcheck Io Entity API
  version: '1'
  contact:
    name: CrawlCheck
    url: https://crawlcheck.io/policy
    email: hello@crawlcheck.io
  license:
    name: Terms
    url: https://crawlcheck.io/policy
  x-core-contract:
    promise: 'These operations are the core contract. They stay at /api/v1 and keep answering for at least 180 days after any /api/v2 is announced; their stable fields change only in a new major version, and their provisional fields only after 30 days'' notice, per /docs/api/compatibility. Verifying what they return needs none of these calls: crawlcheck-verify.mjs checks a document on your machine against the published keys (/.well-known/http-message-signatures-directory) and the rotation record, read once with --online or saved for --keys. Everything else documented here is useful but secondary, and may change with the notice its fields'' tags promise.'
    operations:
    - method: GET
      path: /api/v1/resolve
      operationId: resolveDomainV1
    - method: POST
      path: /api/v1/resolve
      operationId: resolveBatchV1
    - method: POST
      path: /api/v1/preflight
      operationId: preflightV1
    - method: GET
      path: /api/v1/decisions/{sha256}
      operationId: decisionCheckV1
    - method: GET
      path: /api/v1/revocations
      operationId: revocations
    - method: GET
      path: /api/v1/visitor
      operationId: visitorResolveV1
    - method: POST
      path: /api/v1/visitor
      operationId: visitorResolveBatchV1
    - method: GET
      path: /api/v1/mcp/scan
      operationId: mcpScanUrl
    - method: POST
      path: /api/v1/mcp/lock/check
      operationId: mcpLockCheck
    list: https://crawlcheck.io/api/v1/core
  description: 'Operations tagged Entity across 2 of this provider''s published API definitions: crawlcheck-io-openapi.json, crawlcheck-io-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://crawlcheck.io
tags:
- name: Entity
paths:
  /api/entity/observe:
    post:
      operationId: entityObserve
      summary: File a profile page as the owner's browser saw it, for the entity corroboration…
      parameters:
      - name: x-crawlcheck-key
        in: header
        required: true
        schema:
          type: string
          pattern: ^cc_[0-9a-f]{32}$
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - url
              - html
              properties:
                url:
                  type: string
                  description: The profile URL as declared in sameAs
                html:
                  type: string
                  description: The whole page as the browser saw it; at least 512 bytes, the first 200 KB are kept
                vantage:
                  type: string
                  description: Defaults to owner-browser
            examples:
              worked:
                summary: The request behind the worked response
                value:
                  url: https://crawlcheck.io/
                  html: <!doctype html><html>…at least 512 bytes of the page as your browser received it…</html>
                  vantage: browser
          application/x-www-form-urlencoded:
            schema:
              type: object
              required:
              - payload
              properties:
                payload:
                  type: string
                  description: The same JSON object as a form field
      responses:
        '200':
          description: key, sha, bytes, at, expires_days, bound_to (the licence's domains)
          content:
            application/json:
              examples:
                worked:
                  summary: Produced by the production Worker code against a stored copy of a real record; ids, keys and tokens are placeholders.
                  value:
                    ok: true
                    key: crawlcheck.io
                    sha: c0d8bc89b11c35c7
                    bytes: 818
                    at: '2026-10-01T02:29:45.363Z'
                    expires_days: 30
                    bound_to:
                    - crawlcheck.io
                    - treeservicedenverllc.com
                    note: consulted only where CrawlCheck's own fetch is unverifiable; the report labels such rows owner-browser
              schema:
                type:
                - object
                - 'null'
                properties:
                  ok:
                    type:
                    - boolean
                    - 'null'
                  key:
                    type:
                    - string
                    - 'null'
                  sha:
                    type:
                    - string
                    - 'null'
                  bytes:
                    type:
                    - number
                    - 'null'
                  at:
                    type:
                    - string
                    - 'null'
                  expires_days:
                    type:
                    - number
                    - 'null'
                  bound_to:
                    type:
                    - array
                    - 'null'
                    items:
                      type:
                      - string
                      - 'null'
                  note:
                    type:
                    - string
                    - 'null'
                additionalProperties: true
                x-schema-source: worked-example
        '400':
          description: No url or html, page under 512 bytes, or the page's canonical names another host
        '404':
          description: No valid licence key
      x-codeSamples:
      - lang: Shell
        label: curl
        source: "curl -s -X POST \\\n  -H \"x-crawlcheck-key: $CRAWLCHECK_KEY\" \\\n  -H \"content-type: application/json\" \\\n  -d '{\"url\":\"https://crawlcheck.io/\",\"html\":\"<!doctype html><html>…at least 512 bytes of the page as your browser received it…</html>\",\"vantage\":\"browser\"}' \\\n  'https://crawlcheck.io/api/entity/observe'"
      security: []
      x-auth: public; no credential read
      x-crawlcheck-budget:
        request_body_max: 1048576
      tags:
      - Entity
    servers:
    - url: https://crawlcheck.io
components:
  securitySchemes:
    licenceKey:
      type: apiKey
      in: header
      name: x-crawlcheck-key
      description: 'Your licence key: cc_ followed by 32 hex characters. Sent on every keyed call.'
    bearer:
      type: http
      scheme: bearer
      description: The same licence key as a Bearer token. Accepted on /api/v1/* and /api/usage.
externalDocs:
  url: https://crawlcheck.io/docs/api
  description: Human-readable reference
x-refined-from:
- crawlcheck-io-openapi.json
- crawlcheck-io-openapi.yml