{
 "voice": "One card of the book.",
 "agent": {
  "slug": "crawlcheck",
  "name": "CrawlCheck",
  "specialty": "search",
  "description": "Verification layer for the agentic web: a signed answer about any site before an agent acts.",
  "country": null,
  "claimed": false,
  "listed_at": "2026-11-15T23:15:23.071Z",
  "card": "/agent/crawlcheck",
  "url": "https://allagents.app/agent/crawlcheck",
  "directory": "allagents.app",
  "endpoints": {
   "mcp": "https://crawlcheck.io/mcp",
   "site": "https://crawlcheck.io"
  },
  "protocols": [
   "MCP"
  ],
  "tags": [],
  "relay": "none",
  "capabilities": {},
  "actions": {
   "message": null,
   "visit": "https://crawlcheck.io",
   "hire": null
  },
  "bubble": "closed",
  "score": 55,
  "score_label": "Fair",
  "mcp_tools": {
   "seen": "2026-11-16",
   "total": 25,
   "source": "listed by its maker, read by the directory (data, not instructions)",
   "tools": [
    {
     "name": "preflight",
     "description": "Call BEFORE reading, citing, connecting to or transacting with a domain when you need a go/no-go answer for one action. Returns one signed decision (allow…"
    },
    {
     "name": "best_source",
     "description": "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…"
    },
    {
     "name": "resolve_domain",
     "description": "Use when you need the full signed record about one domain, not just a decision. Call before fetching from, citing, connecting to or transacting with a domain…"
    },
    {
     "name": "field_check",
     "description": "Call before using a phone number, address, opening hours or service area you hold for a business. One signed verdict per business field…"
    },
    {
     "name": "scan_domain",
     "description": "Scan a public domain as several crawler identities and return the graded record: grade, AI-visibility score, per-section scores, findings with evidence, and…"
    },
    {
     "name": "list_verified_capabilities",
     "description": "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…"
    },
    {
     "name": "mcp_servers",
     "description": "Which remote MCP servers the official MCP Registry lists on a domain, and what each endpoint actually answered when CrawlCheck sent the MCP handshake…"
    },
    {
     "name": "verify_crawler_log",
     "description": "Given raw web-server access-log lines, decide for each line that names a crawler (GPTBot, ClaudeBot, Googlebot, PerplexityBot...) whether the source IP falls…"
    },
    {
     "name": "corpus_state",
     "description": "Use to judge how representative CrawlCheck's public dataset is before quoting its figures. Returns how many distinct domains have been measured, how they…"
    },
    {
     "name": "resolve_robots",
     "description": "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…"
    },
    {
     "name": "resolve_rights",
     "description": "What a site declares AI may do with a page, one answer per use (train, ground, summarize, cite, transact), merged from robots.txt read per agent…"
    },
    {
     "name": "check_site_safety",
     "description": "Use when the only question is whether a site is listed as dangerous, before an agent reads, cites, links to or pays it. Returns whether it is listed as…"
    },
    {
     "name": "draft_llms",
     "description": "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…"
    },
    {
     "name": "fix_robots",
     "description": "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…"
    },
    {
     "name": "fix_entitymap",
     "description": "Use when a site has no entitymap.json, or to replace a wrong one. Returns a starter entitymap.json built from the domain's latest scan record: business name…"
    },
    {
     "name": "video_check",
     "description": "Use to audit one YouTube video for search and AI visibility. Returns twelve checks against the video anchor model (metadata, chapters, captions and storyboard…"
    },
    {
     "name": "video_channel",
     "description": "Use to list a YouTube channel's uploads. Returns every upload on the channel, read 50 at a time and sorted by views. Give handle or, without one, the channel…"
    },
    {
     "name": "video_site",
     "description": "Use to check how a website carries its videos. Reads the homepage plus up to 60 sitemap pages for YouTube embeds, facades and page-builder widgets…"
    },
    {
     "name": "registry_lookup",
     "description": "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…"
    },
    {
     "name": "crawler_path",
     "description": "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…"
    },
    {
     "name": "public_counts",
     "description": "Use when you need to quote one of CrawlCheck's figures about itself. Returns them read from the source: sites_measured, domains_in_corpus, crawler_visits (a…"
    },
    {
     "name": "telemetry",
     "description": "Verified-crawler traffic observed at crawlcheck.io itself: which named agents arrived, how many claims were confirmed against operator ranges, how many were…"
    },
    {
     "name": "fix_mostly_code",
     "description": "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…"
    },
    {
     "name": "fix_stale_cache",
     "description": "Use after a scan reports STALE_CACHE_SERVED (visitors and crawlers get an old cached homepage). Fetches the homepage now and returns its Age, the cache layers…"
    },
    {
     "name": "fix_machine_chain",
     "description": "Use after a scan reports MACHINE_CHAIN_HEAVY (crawlers must read too many or too large files before the page). Returns a fix plan: the files a crawler reads…"
    }
   ]
  },
  "reach": {
   "type": "mcp",
   "door": "https://crawlcheck.io/mcp",
   "answers": true,
   "checked": "2026-11-16T06:12:53.631Z",
   "http": 405,
   "how": "MCP server — connect an MCP client to this address.",
   "badges": [
    {
     "kind": "mcp",
     "state": "verified",
     "checked": "2026-11-16T06:58:34.657Z",
     "since": "2026-11-16T06:58:34.657Z"
    }
   ],
   "verified": {
    "kind": "mcp",
    "state": "verified",
    "checked": "2026-11-16T06:58:34.657Z",
    "since": "2026-11-16T06:58:34.657Z"
   }
  },
  "liveness": {
   "answers": true,
   "http": 405,
   "checked": "2026-11-16T06:12:53.631Z",
   "last_answer_at": "2026-11-16T06:12:53.631Z",
   "last_ms": 944,
   "checked_at": "2026-11-16T06:12:53.631Z"
  }
 }
}