io.github.emmanuelorta/crawlcheck

2 of 25 tools are described as changing something (creating, editing, deleting, sending or running). For 5 the reading was uncertain, so no mark is shown.

• preflighton 16 other serversreads or searches

  “Call BEFORE reading, citing, connecting to or transacting with a domain.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  5 inputs, 1 required

  • domainstringrequired“Bare domain, e.g.”
  • actionstring“What you are about to do (default read)”
  • agentstring“Your crawler user-agent token, e.g.”
  • templatestring“safe_citation, safe_data_retrieval, safe_api_connect, safe_mcp_tool, safe_commerce, safe_oauth or support_escalation”
  • policyobject“max_age_hours, on_warn (warn|require_confirmation|block), require_entity, human_approval[], allow[], deny[]”
• best_sourcereads or searches

  “Call when choosing WHICH business or site to cite, recommend or call.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  3 inputs

  • domainsarray“Candidate sites, bare domains, up to 10”
  • tradestring“e.g.”
  • citystring“e.g.”
• resolve_domainreads or searches

  “Call before fetching from, citing, connecting to or transacting with a domain.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  1 input, 1 required

  • domainstringrequired“Bare domain, e.g.”
• field_checkreads or searches

  “Call before using a phone number, address, opening hours or service area you hold for a business.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  3 inputs, 3 required

  • domainstringrequired“Bare domain of the business, e.g.”
  • fieldstringrequired
  • valuestringrequired“The value you hold: a 10-digit number, a street address, a week (Mo-Fr 08:00-17:00) or a moment (Sa 10:00), or a place name”
• scan_domainon 11 other serversreads or searches

  “Scan a public domain as several crawler identities and return the graded record: grade, AI-visibility score, per-section scores, findings with evidence, and whether the origin refused CrawlCheck.”

  Publisher declares: read-only no · destructive no · idempotent no · open-world yes

  1 input, 1 required

  • domainstringrequired“A bare domain such as example.com, or a full URL”
• list_verified_capabilitiesreads or searches

  “What a domain declares agents can do (OpenAPI operations, MCP tools, A2A skills, API catalog entries), each classed by safety (read_only_public up to financial), and which ones CrawlCheck actually ca…”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  2 inputs, 1 required

  • domainstringrequired
  • verified_onlyboolean“Return only the capabilities that were confirmed”
• mcp_serverson 2 other serversreads or searches

  “Which remote MCP servers the official MCP Registry lists on a domain, and what each endpoint actually answered when CrawlCheck sent the MCP handshake (initialized, auth_required, unreachable, tool co…”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  1 input, 1 required

  • domainstringrequired“Bare domain or host, e.g.”
• verify_crawler_logreads or searches

  “Given raw web-server access-log lines, decide for each line that names a crawler (GPTBot, ClaudeBot, Googlebot, PerplexityBot...) whether the source IP falls inside that operator's published ranges.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  1 input, 1 required

  • linesstringrequired“Up to 200 raw log lines, newline separated”
• corpus_statereads or searches

  “Coverage of CrawlCheck's public dataset: how many distinct domains have been measured and how they split by platform, rendering, size, language and kind, with the strata that are still under-sampled.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  Takes no inputs.

• resolve_robotsreads or searches

  “Resolve every named answer engine, search index and training crawler against a domain's robots.txt the way a crawler does: most-specific group only, longest match, allow wins a tie.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  2 inputs, 1 required

  • domainstringrequired
  • pathstring“Path to test, default /”
• draft_llmsgenerates content

  “Draft an llms.txt from the domain's own homepage and up to 25 declared pages, using their titles and descriptions.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  1 input, 1 required

  • domainstringrequired
• fix_robotscreates or changes datadescribed as changing data

  “The domain's served robots.txt, corrected: * group rules copied into named groups that lacked them (shadowing), a Sitemap line added when missing, a minimal replacement when the served file was HTML.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  1 input, 1 required

  • domainstringrequired

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.