CrawlCheck Corpus API

openapi: 3.2.0
info:
  title: Crawlcheck Io Corpus 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 Corpus 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: Corpus
paths:
  /api/corpus/state:
    get:
      operationId: corpusState
      summary: Coverage of the public dataset by platform, rendering, size, language and kind
      responses:
        '200':
          description: JSON
          content:
            application/json:
              schema:
                type: object
              examples:
                worked:
                  summary: Captured from production on 2026-09-30 (MDT).
                  value:
                    ok: true
                    queue_size: 13923
                    domains_measured: 7159
                    dimension_tallies: 30836
                    per_dimension:
                      platform: 7159
                      rendering: 7159
                      size: 2914
                      language: 6445
                      kind: 7159
                    counting_note: domains_measured is the number of DISTINCT domains classified - each dimension counts a domain at most once, so the largest dimension tally is the domain count. dimension_tallies is the sum across all dimensions and counts one domain up to…
                    coverage:
                      platform:
                        wordpress: 1108
                        unknown: 4476
                        nextjs: 784
                        webflow: 225
                        drupal: 392
                        shopify: 65
                        wix: 34
                        squarespace: 75
                      rendering:
                        server: 5722
                        client: 1437
                      size:
                        medium: 2038
                        small: 850
                        large: 26
                      language:
                        en: 5086
                        non-en: 1359
                      kind:
                        local-service: 9
                        other: 5163
                        publisher: 1370
                        ecommerce: 170
                        gov-edu: 47
                        saas: 291
                        docs: 100
                        directory: 9
                    gaps: []
                    complete: true
                    note: A cell below 5 sites has not been validated. Every false positive CrawlCheck has produced came from meeting a site type the code had not met.
      x-codeSamples:
      - lang: Shell
        label: curl
        source: "curl -s \\\n  'https://crawlcheck.io/api/corpus/state'"
      security: []
      x-auth: public; no credential read
      tags:
      - Corpus
    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