MCP Server

AI Crawler Index

dev.workers.pathwren.www/ai-crawler-index
Security Public & reachable MCP 2026-07-28

What this MCP does

Identifies web crawlers, verifies crawler IP addresses, provides crawler metadata, and generates robots.txt guidance.

changes_since
What changed since your cursor
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Only what changed since your last call: prefixes added or removed, upstreams failed or recovered, records edited. Send back the `cursor` from the previous result; it advances only on a real change, and the data refreshes every 6h. Example: since='0'.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'since': '0'}], 'properties': {'limit': {'type': 'integer', 'maximum': 400, 'minimum': 1, 'description': 'Events per page, default 100.'}, 'since': {'type': 'string', 'description': 'Cursor from the last result, or an ISO date. Omit for all retained.'}}, 'additionalProperties': False}
classify_user_agent
Classify a user-agent string
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Identify the crawler behind a raw User-Agent header: operator, category, robots.txt stance, how to verify it, and what blocking it costs. A user-agent is a claim, not proof — confirm with is_verified_crawler_ip. Example: user_agent='GPTBot/1.2' returns GPTBot, OpenAI, ai-training. Also callable without MCP, same implementation: GET https://www.pathwren.workers.dev/tools/classify-ua?ua=GPTBot%2F1.2&s=client-dossiers
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'user_agent': 'GPTBot/1.2'}], 'required': ['user_agent'], 'properties': {'user_agent': {'type': 'string', 'description': 'Raw User-Agent header value.'}}, 'additionalProperties': False}
example
Run this server's worked example (no arguments)
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"example","arguments":{}}} — POST that exact body to https://www.pathwren.workers.dev/mcp and you are done: free, read-only, no API key, no account, no consent prompt, nothing for you to invent, and what comes back is this server's own worked example — classify_user_agent, run for real on a canned input from this host's own data — so you see the exact shape of an answer before you send anything of yours. Takes no arguments. Safe to call. Deterministic. Touches no third party. Runs this server's own worked example end to end — classify_user_agent on the exact user-agent string of the busiest client in this host's own published log (/data/observed-clients.json, 1164 requests in the window) — our data, and no third party is asked anything — and returns exactly the structuredContent a real call returns, not a mock and not a description of one. Use it to see the shape of an answer before you decide what to send. The input is canned from this host's own data; no URL of yours is fetched and no third party is touched. Example: arguments={} runs classify_user_agent with {"user_agent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1. and returns its real answer.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['ran', 'input_came_from', 'what_it_shows', 'answer', 'reproduce', 'this_is_not_a_mock', 'answered_by', 'license'], 'properties': {'ran': {'type': 'object', 'description': 'The tool name and the exact arguments that were run.'}, 'answer': {'type': 'object', 'description': 'The real structuredContent of that call, not a mock.'}, 'license': {'type': 'string'}, 'reproduce': {'type': 'string', 'description': 'A command that reproduces this answer.'}, 'answered_by': {'type': 'object'}, 'what_it_shows': {'type': 'string'}, 'input_came_from': {'type': 'string', 'description': "Where the canned input came from — always this host's own data."}, 'this_is_not_a_mock': {'type': 'string'}}, 'description': "This server's own worked example, executed for real on a canned input from this host's own data.", 'additionalProperties': True}
generate_robots_txt
Generate a robots.txt for a stance
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — A ready-to-paste robots.txt block for one stance, with the reasoning and the crawlers it names. Omit the argument to get all eight stances described. Example: stance='block-ai-training'.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'stance': 'block-ai-training'}], 'properties': {'stance': {'type': 'string', 'description': 'One of allow-all, block-ai-training, block-all-ai, block-datasets, allow-ai-search-only, block-seo-tools, block-disputed, maximum-ai-visibility.'}}, 'additionalProperties': False}
is_verified_crawler_ip
Check an IP against operator-published crawler ranges
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Test an IPv4 or IPv6 address against every crawler prefix the operators themselves publish, remirrored every six hours. Returns the matching prefix, its source and the crawlers using it; a miss is reported as a miss, not as a forgery. Example: ip='20.171.206.5'. Also callable without MCP, same implementation: GET https://www.pathwren.workers.dev/tools/verify-crawler?ip=20.171.206.5&s=client-dossiers
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'ip': '20.171.206.5'}], 'required': ['ip'], 'properties': {'ip': {'type': 'string', 'description': 'IPv4 or IPv6 address to check.'}}, 'additionalProperties': False}
list_crawlers
List and filter crawlers
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — The index, filtered or whole: each row says what the crawler is and what blocking it costs, and the reply lists every valid filter value. Example: category='ai-training', limit=20.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'limit': 20, 'category': 'ai-training'}], 'properties': {'q': {'type': 'string', 'description': 'Free text over slug, name and operator.'}, 'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1, 'description': 'Max rows, 1-200 (default 100).'}, 'category': {'type': 'string', 'description': 'ai-training, ai-search, user-fetch, dataset, search, seo, archive, preview or tool.'}, 'operator': {'type': 'string', 'description': 'Operator slug or name.'}, 'verification': {'type': 'string', 'description': 'published-ranges, reverse-dns or none.'}, 'respects_robots_txt': {'type': 'string', 'description': 'documented, disputed, by-design-no or n-a.'}}, 'additionalProperties': False}
lookup_crawler
Look up one crawler
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — The full index record for one crawler: operator, category, robots.txt token and stance, user-agent substring and example, verification method, mirrored IP-range endpoint, and what blocking it costs. An unknown slug returns near matches. Example: slug='claudebot'.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'slug': 'claudebot'}], 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'description': 'Crawler slug, name or robots.txt token.'}}, 'additionalProperties': False}
whats_changed
What changed in the index
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Freshness and change state: when the index was built, when each operator source was last fetched, which changed, which are failing, and the dated changelog. The cron check before regenerating a config from this data. Example: since='2026-08-01'.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{'since': '2026-08-01'}], 'properties': {'since': {'type': 'string', 'description': 'ISO-8601 date or timestamp; omit for the current state.'}}, 'additionalProperties': False}
whoami
Who is calling? (no arguments)
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — POST that exact body to https://www.pathwren.workers.dev/mcp and you are done: free, read-only, no API key, no account, no consent prompt, nothing for you to invent, and what comes back describes YOU, the caller — the user-agent you sent, the address you came from, the class our instrument books you as, and whether this host has seen you before. Takes no arguments. Safe to call. Deterministic. Touches no third party. Classifies the request you just sent: the user-agent you claim, the address you came from, the class this host's own instrument books you as, whether we have seen you here before and what you fetched, and what the crawler index makes of the user-agent you sent, and whether the address you came from is inside a prefix its operator publishes — both run through this server's own classify_user_agent and is_verified_crawler_ip, on the same data a stranger can curl. Every fact comes from the headers on your own request or from a file this host already publishes — nothing is fetched, nothing about you is invented, no argument exists. Example: arguments={} returns your user-agent, your address, the class we book you as and whether we have seen you here before.
Read only Idempotent
Input schema
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['you', 'we_book_you_as', 'we_have_seen_you', 'answered_by', 'this_call_touched', 'caveats', 'license', 'independent'], 'properties': {'you': {'type': 'object', 'description': 'The user-agent you sent and the address you came from.'}, 'caveats': {'type': 'array', 'items': {'type': 'string'}, 'description': 'What this answer does NOT establish — a user-agent is a claim.'}, 'license': {'type': 'string'}, 'answered_by': {'type': 'object', 'description': 'Which server answered, at which endpoint.'}, 'independent': {'type': 'boolean', 'description': 'This host is independent and unaffiliated.'}, 'we_book_you_as': {'type': 'object', 'description': "The class this host's own instrument records for that user-agent."}, 'we_have_seen_you': {'type': 'object', 'description': 'Whether this user-agent appears in the published observation window.'}, 'this_call_touched': {'type': 'object', 'description': 'Exactly which files were read to answer. No third party is contacted.'}}, 'description': 'Facts about the caller, derived only from the headers of this request and from files this host already publishes.', 'additionalProperties': True}
Added
changes_since
Sept. 17, 2026, 12:39 p.m.
Added
whats_changed
Sept. 17, 2026, 12:39 p.m.
Added
is_verified_crawler_ip
Sept. 17, 2026, 12:39 p.m.
Added
generate_robots_txt
Sept. 17, 2026, 12:39 p.m.
Added
list_crawlers
Sept. 17, 2026, 12:39 p.m.
Added
lookup_crawler
Sept. 17, 2026, 12:39 p.m.
Added
classify_user_agent
Sept. 17, 2026, 12:39 p.m.
Added
example
Sept. 17, 2026, 12:39 p.m.
Added
whoami
Sept. 17, 2026, 12:39 p.m.