CrawlCheck

by emmanuelorta · remote · no sign-in to list tools · v1.1.0 · published by GitHub user emmanuelorta

Verification layer for the agentic web: a signed answer about any site before an agent acts.

Changes · 20

Compare Registry entry

25 tools: 20 change things and 5 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things20Claude Code: ask: see these tools
Only reads5Claude Code: allow: see these tools

5 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http crawlcheck https://crawlcheck.io/mcp

Findings

Matches of fixed checks, with the text they matched.

5 warn

Warnpreflight
The server marks "preflight" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.
What this check looks for
Warnbest_source
The server marks "best_source" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "call": a word for a change.
What this check looks for
Warnresolve_domain
The server marks "resolve_domain" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "resolve_domain" says "resolve": a word for reading.
What this check looks for
Warnfield_check
The server marks "field_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "call": a word for a change.
What this check looks for
Warnexplain_finding
The server marks "explain_finding" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "explain_finding" says "explain": a word for reading.
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

25 tools

Changes things 20Creates or changes something that can be changed back.Claude Code: ask

best_sourceCall when choosing WHICH business or site to cite, recommend or call.1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "best_source" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "call": a word for a change.
  What this check looks for
Description, as the server wrote it
Call when choosing WHICH business or site to cite, recommend or call. Give domains (2-10 candidate sites you found) or trade and city for a measured market. Returns the candidates ranked by what CrawlCheck verified (preflight decision for cite, security and threat listing, domain age, uptime, published facts that directories agree with, FTC phone complaints) with reasons for and against each; sites that share one phone number or near-identical homepage text are collapsed into one network so a copycat cannot outrank the business it copies. Signed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
corpus_stateCoverage 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 s…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
crawler_pathWhere each crawler's path into a domain dies, as an observed data flow: edge decision, robots.txt as a file, robots.txt rules, then the page, JSON-LD, sitemap, llms.txt and entitym…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Where each crawler's path into a domain dies, as an observed data flow: edge decision, robots.txt as a file, robots.txt rules, then the page, JSON-LD, sitemap, llms.txt and entitymap.json it reached. Give agent (e.g. ClaudeBot, GPTBot, googlebot) for one identity's path and a one-line answer; omit it for every identity plus the stores and breaks. Uses the latest record on file, or scans first when there is none (fresh=true forces a scan). The answer-engine output is drawn but never measured.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
draft_llmsDraft an llms.txt from the domain's own homepage and up to 25 declared pages, using their titles and descriptions.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Draft an llms.txt from the domain's own homepage and up to 25 declared pages, using their titles and descriptions. A draft for the owner to cut down, not a publication.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
explain_findingWhy CrawlCheck decided a finding: the rule and its revision, the exact fetches it compared (identity, status, bytes, sha256), when the condition held on the site, and a Merkle proo…1 finding
Why it is in this group
- The name "explain_finding" says "explain": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "explain_finding" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "explain_finding" says "explain": a word for reading.
  What this check looks for
Description, as the server wrote it
Why CrawlCheck decided a finding: the rule and its revision, the exact fetches it compared (identity, status, bytes, sha256), when the condition held on the site, and a Merkle proof that the decision is inside the signed manifest. Give id (a d1: decision or f1: finding id from a report) or domain for its top finding. Other findings, and lookups by code, need a licence for that domain (send it in x-crawlcheck-key).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
field_checkCall before using a phone number, address, opening hours or service area you hold for a business.1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "field_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "call": a word for a change.
  What this check looks for
Description, as the server wrote it
Call before using a phone number, address, opening hours or service area you hold for a business. One signed verdict per business field. field=phone|address|hours|service_area and value= the value you hold. phone: matches, former_value (with dates), not_this_business (the site never published it and another publisher is named with the page that prints it), or not_published. address: matches, same_street_other_city, former_value, not_this_business, not_published or nothing_declared. hours: a week (Mo-Fr 08:00-17:00) gives matches or differs per day; a moment (Sa 10:00) gives open or closed. service_area: declared, not_declared or nothing_declared. Built from the business's own site (and its Business Profile for the licence holder), its dated fact history, CrawlCheck's scans of other sites, and for an unknown number a web search whose cited pages are read plus a YellowPages reverse lookup.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
fix_entitymapA starter entitymap.json built from the domain's latest scan record: name, phone, coordinates and declared service areas as entities with SERVES relations.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
A starter entitymap.json built from the domain's latest scan record: name, phone, coordinates and declared service areas as entities with SERVES relations. Fields the page never stated are marked TODO, never guessed. Needs a prior scan.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
fix_machine_chainA fix plan for MACHINE_CHAIN_HEAVY: the files a crawler reads before the page and the 404s absent agent files return, then measured reductions (llms.txt to an index, a sitemap inde…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
A fix plan for MACHINE_CHAIN_HEAVY: the files a crawler reads before the page and the 404s absent agent files return, then measured reductions (llms.txt to an index, a sitemap index, robots.txt comments and duplicate groups, minified JSON, short 404s) with the chain size after each and the step at which the detector stops firing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
fix_mostly_codeA fix plan for PAGE_IS_MOSTLY_CODE: the homepage's measured bytes by category, the largest blocks with what to do with each, ordered steps with the text ratio after each, and the s…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
A fix plan for PAGE_IS_MOSTLY_CODE: the homepage's measured bytes by category, the largest blocks with what to do with each, ordered steps with the text ratio after each, and the step at which the detector would stop firing - or, when moving code cannot clear it, how much markup to cut or text to add. Give domain (fetched now) or id (a stored scan).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
fix_robotsThe 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 se…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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. Every change is listed at the top; nothing else is touched.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
fix_stale_cacheA fix plan for STALE_CACHE_SERVED: the homepage fetched now, its Age, the cache layers that name themselves in the headers in purge order (innermost first), the HTML lifetime each …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
A fix plan for STALE_CACHE_SERVED: the homepage fetched now, its Age, the cache layers that name themselves in the headers in purge order (innermost first), the HTML lifetime each response declares, a fresh-read comparison, and whether a purge clears the finding and keeps it cleared.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
machine_recordThe unified machine record for one observation: subject, grade, findings (the top one in full without a licence), capabilities with verification, and the evidence roots, manifest a…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
The unified machine record for one observation: subject, grade, findings (the top one in full without a licence), capabilities with verification, and the evidence roots, manifest and verifier links that let anyone check it offline. Give id (report, d1:, f1: or manifest sha256) or domain for the latest.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mcp_serversWhich 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, u…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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 count, tool-list drift). Use before selecting an MCP tool from that domain.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
preflightCall BEFORE reading, citing, connecting to or transacting with a domain.1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "preflight" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.
  What this check looks for
Description, as the server wrote it
Call BEFORE reading, citing, connecting to or transacting with a domain. Returns a signed decision: allow, warn, require_confirmation, block or unsupported, with every step that led there and the resolve answer it was made from. Pass your crawler token as agent so robots.txt is checked for you. A policy can only make the decision stricter. Do not proceed on block; ask the user on require_confirmation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
resolve_domainCall before fetching from, citing, connecting to or transacting with a domain.1 finding
Why it is in this group
- The name "resolve_domain" says "resolve": a word for reading.
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "resolve_domain" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "resolve_domain" says "resolve": a word for reading.
  What this check looks for
Description, as the server wrote it
Call before fetching from, citing, connecting to or transacting with a domain. Returns one signed answer: what the domain claims, what it actually serves each crawler identity, who controls it, what CrawlCheck's published rules decide for each action (a decision for read, cite, connect and transact, with its doubts and maximum age), what changed, and the evidence behind each part, marked declared, observed or not_measured with its time. There is no overall score. A domain never measured gets a just-in-time partial answer within about 2 seconds that names every part not read in time, and is queued for the full scan; nothing is guessed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
scan_domainScan 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 refu…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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. One scan takes 5-15 seconds.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
telemetryVerified-crawler traffic observed at crawlcheck.io itself: which named agents arrived, how many claims were confirmed against operator ranges, how many were forged.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Verified-crawler traffic observed at crawlcheck.io itself: which named agents arrived, how many claims were confirmed against operator ranges, how many were forged.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
video_channelEvery upload on a YouTube channel, read 50 at a time, sorted by views.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Every upload on a YouTube channel, read 50 at a time, sorted by views. The upload list is free; the per-check tally needs a Watch licence and is not offered here.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
video_checkOne YouTube video against the video anchor model: metadata, chapters, captions and storyboard where observed, twelve checks each naming what it reads.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
One YouTube video against the video anchor model: metadata, chapters, captions and storyboard where observed, twelve checks each naming what it reads.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
video_siteThe site half of video: homepage plus up to 60 sitemap pages read for YouTube embeds, facades and page-builder widgets, VideoObject nodes and their required properties, and - with …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
The site half of video: homepage plus up to 60 sitemap pages read for YouTube embeds, facades and page-builder widgets, VideoObject nodes and their required properties, and - with a handle - how many of the channel's videos the site carries.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true

Only reads 5Looks things up and changes nothing.Claude Code: allow

list_verified_capabilitiesWhat 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 Cra…No findings
Why it is in this group
- The name "list_verified_capabilities" says "list": a word for reading.
Description, as the server wrote it
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 called and confirmed - plus every mismatch between declaration and behaviour. Only read-only public actions are ever called; everything else says why it was not. From the latest scan on file.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
public_countsThe figures CrawlCheck quotes about itself, read from the source: sites_measured, domains_in_corpus, crawler_visits (a rolling window), sections, sections_scored, findings_publishe…No findings
Why it is in this group
- The name "public_counts" says "count": a word for reading.
Description, as the server wrote it
The figures CrawlCheck quotes about itself, read from the source: sites_measured, domains_in_corpus, crawler_visits (a rolling window), sections, sections_scored, findings_published, guides_published, with an at timestamp.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
registry_lookupWhether a domain is in CrawlCheck's registry and what it serves: llms.txt, agents.md, a media kit at /.well-known/media-kit.json, a reciprocity-tested entity graph, an AI access po…No findings
Why it is in this group
- The name "registry_lookup" says "lookup": a word for reading.
Description, as the server wrote it
Whether a domain is in CrawlCheck's registry and what it serves: llms.txt, agents.md, a media kit at /.well-known/media-kit.json, a reciprocity-tested entity graph, an AI access policy that names crawlers, and agent-callable surfaces. With no domain, returns the shelf counts across every measured site. A row exists because a fetch produced it; nothing here is self-reported and no payment moves a shelf.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
resolve_robotsResolve 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…No findings
Why it is in this group
- The name "resolve_robots" says "resolve": a word for reading.
Description, as the server wrote it
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. Shows when a Disallow under * does not apply to an agent with its own group.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_crawler_logGiven 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…No findings
Why it is in this group
- The name "verify_crawler_log" says "log": a word for reading.
Description, as the server wrote it
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. Returns verified, spoofed, or unverifiable when the operator publishes no ranges.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http crawlcheck https://crawlcheck.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__crawlcheck__list_verified_capabilities",
      "mcp__crawlcheck__verify_crawler_log",
      "mcp__crawlcheck__resolve_robots",
      "mcp__crawlcheck__registry_lookup",
      "mcp__crawlcheck__public_counts"
    ],
    "ask": [
      "mcp__crawlcheck__preflight",
      "mcp__crawlcheck__best_source",
      "mcp__crawlcheck__resolve_domain",
      "mcp__crawlcheck__field_check",
      "mcp__crawlcheck__scan_domain",
      "mcp__crawlcheck__mcp_servers",
      "mcp__crawlcheck__corpus_state",
      "mcp__crawlcheck__draft_llms",
      "mcp__crawlcheck__fix_robots",
      "mcp__crawlcheck__fix_entitymap",
      "mcp__crawlcheck__video_check",
      "mcp__crawlcheck__video_channel",
      "mcp__crawlcheck__video_site",
      "mcp__crawlcheck__crawler_path",
      "mcp__crawlcheck__telemetry",
      "mcp__crawlcheck__fix_mostly_code",
      "mcp__crawlcheck__fix_stale_cache",
      "mcp__crawlcheck__fix_machine_chain",
      "mcp__crawlcheck__explain_finding",
      "mcp__crawlcheck__machine_record"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as crawlcheck. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.emmanuelorta/crawlcheck/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

20 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:33 UTC.

For agents: Markdown · JSON · report this listing