{
 "specVersion": "1.0",
 "host": {
  "displayName": "AI Crawler Index",
  "identifier": "did:web:www.pathwren.workers.dev",
  "documentationUrl": "https://www.pathwren.workers.dev/about.html"
 },
 "entries": [
  {
   "identifier": "urn:air:www.pathwren.workers.dev:agent:ai-crawler-index",
   "displayName": "AI Crawler Index — A2A agent",
   "type": "application/a2a-agent-card+json",
   "url": "https://www.pathwren.workers.dev/c/ard/.well-known/agent-card.json",
   "description": "A2A (Agent2Agent) v1.0 agent, JSON-RPC 2.0 over POST, six read-only skills about web crawlers and AI user agents: classify_user_agent, lookup_crawler, list_crawlers, generate_robots_txt, is_verified_crawler_ip and whats_changed. Deterministic — there is no model behind it; every answer comes from a public dataset rebuilt every six hours from each operator's own published documentation and IP ranges. No key, no signup, no quota.",
   "representativeQueries": [
    "which bot is this user-agent string",
    "is this IP really GPTBot or is something spoofing it",
    "write me a robots.txt that blocks AI training crawlers but keeps search",
    "what does blocking ClaudeBot actually cost me",
    "list every AI crawler and who operates it"
   ],
   "tags": [
    "a2a",
    "crawlers",
    "user-agent",
    "robots.txt",
    "bot-detection"
   ]
  },
  {
   "identifier": "urn:air:www.pathwren.workers.dev:mcp:ai-crawler-index",
   "displayName": "AI Crawler Index — MCP servers",
   "type": "application/mcp-server-card+json",
   "url": "https://www.pathwren.workers.dev/c/ard/.well-known/mcp.json",
   "description": "Three remote MCP servers (Streamable HTTP, no auth) on one host: /mcp identifies one crawler at a time, /mcp/triage takes a pasted access log and returns who crawled you, and /mcp/doctor grades which agent-discovery documents a host actually serves. The document names all three endpoints and mirrors the record the official MCP registry holds.",
   "representativeQueries": [
    "connect an MCP server that identifies web crawlers",
    "triage an access log and tell me which AI bots hit my site",
    "check which agent discovery files my domain serves"
   ],
   "tags": [
    "mcp",
    "crawlers",
    "log-analysis",
    "discovery"
   ]
  },
  {
   "identifier": "urn:air:www.pathwren.workers.dev:api:crawler-index",
   "displayName": "AI Crawler Index — HTTP API and dataset",
   "type": "application/json",
   "url": "https://www.pathwren.workers.dev/c/ard/openapi.json",
   "description": "The same index as plain HTTP: OpenAPI 3.1 over read-only JSON and CSV endpoints — every crawler record, per-operator IP ranges mirrored from the operator's own published file, ready-made robots.txt policies, and a changelog of what moved. No key and no rate limit.",
   "representativeQueries": [
    "download a JSON list of AI crawler user agents",
    "where can I get published IP ranges for AI bots",
    "csv of crawlers by category and operator"
   ],
   "tags": [
    "api",
    "openapi",
    "dataset",
    "crawlers",
    "ip-ranges"
   ]
  }
 ]
}