curl -s https://www.pathwren.workers.dev/mcp-triage.json   # this page, as JSON

Crawler Log Triage — MCP server

Connect it: one paste, one call

https://www.pathwren.workers.dev/mcp/triage
no auth, read-only, public

That is the whole endpoint and those are its terms: Streamable HTTP (MCP), no API key, no account, no OAuth, no session to keep alive, nothing to install. Every tool is read-only, and none of them will fetch a URL on your behalf.

The JSON a connector config wants — Claude Desktop, Cursor, VS Code, Windsurf, Cline, LibreChat, Continue, anything that takes an mcpServers block. Complete as it stands; there is no field to fill in:

{
  "mcpServers": {
    "crawler-log-triage": {
      "type": "streamable-http",
      "url": "https://www.pathwren.workers.dev/c/mcp-connector/mcp/triage"
    }
  }
}

Claude Code takes one line instead:

claude mcp add --transport http crawler-log-triage https://www.pathwren.workers.dev/c/mcp-connector/mcp/triage

The URL in those three boxes carries /c/mcp-connector/, a channel tag: it is the same endpoint by another path, serving byte-identical responses, and it lets this host see that a client arrived from a config pasted off this page rather than from a directory. Strip the prefix and https://www.pathwren.workers.dev/mcp/triage is the canonical URL — both work, and nothing about the answer changes.

Then call no_arguments_triage_this_hosts_own_crawler_log first. It takes no arguments at all, so there is nothing to invent and nothing to look up before you can see this server work — the subject of the answer is this host's own published crawler log, run through the real engine:

curl -s https://www.pathwren.workers.dev/c/mcp-connector/mcp/triage \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_triage_this_hosts_own_crawler_log","arguments":{}}}' \
  | jq -r '.result.content[0].text' | head -3

This host's own published log, triaged: 54761 requests over 400 distinct user-agent strings, 31% identified against the index.
(unidentified): 37793 requests (69%)
Anthropic: 6847 requests (12.5%)

Those are the answer's own first three lines, from one real run on 2026-09-06 — the log grows, so run the curl and read today's. The tool takes no arguments because its subject is not you: it is the request log THIS host publishes, so every caller gets the same bytes. It is the same parser, the same crawler index and the same operator-prefix verification that triage_log runs on a file you paste — including the 69% it cannot identify, which is the number a demo would have hidden. The rest of the answer is the rollup by operator, by category and by crawler, the log it built line by line so you can re-run it yourself, and the browser-shaped strings kept apart from the crawlers. Nothing is fetched to answer it, no argument exists. triage_my_request is the second zero-argument call and answers about YOU — your own requests to this host, triaged the same way; whoami is the third and works unchanged on every MCP server here; example is the fourth. All four are safe first calls.

Paste your access log. Get back what is crawling you, who runs it, what it costs to block, and which lines are lying about who they are. Streamable HTTP, stateless, no key, no signup. Every tool is read-only.

# three lines of a log, one call, no account
curl -s https://www.pathwren.workers.dev/mcp/triage \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"triage_log",
       "arguments":{"log":"66.249.66.1 Googlebot/2.1\n203.0.113.9 Googlebot/2.1\n412 GPTBot/1.2"}}}' \
  | jq -r '.result.structuredContent.rows[] | "\(.identified)\t\(.operator)\t\(.verdict)"'

Googlebot	Google	verified
Googlebot	Google	impersonation
GPTBot	OpenAI	unverifiable

With a real file, the shape you actually want:

curl -s https://www.pathwren.workers.dev/mcp/triage \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d "$(jq -Rs '{jsonrpc:"2.0",id:1,method:"tools/call",
       params:{name:"summarize_by_operator",arguments:{log:.}}}' < access.log)" \
  | jq -r '.result.structuredContent.by_operator[] | "\(.requests)\t\(.operator)\t\(.share_pct)%"'

Tools

What it eats

Formats are detected per line, so a messy paste is fine and a mixed file is fine:

The usual way to produce the third one: awk -F'"' '{print $6}' access.log | sort | uniq -c | sort -rn | head -50

How is this different from /mcp?

ai-crawler-index answers questions about one thing — this user-agent, this IP, this crawler, this stance. It is a reference. This server does not answer questions about crawlers at all: it takes your evidence, a log you already have, and gives back a decision about it. One call in, per-line verdicts plus a rollup plus a config out. Different input, different unit of work, no tool in common — same index underneath, so the two agree by construction. Run both.

What it will not do

It has no side effects and no write path. It has no tool that fetches a URL, and no tool that takes one — it works on text you paste, and nothing else. That is deliberate: a log-analysis tool that will fetch an arbitrary URL for whoever is talking to it is an SSRF proxy with a friendly description, so this one cannot be asked.

Operators who verify by reverse DNS (24 of them, including Bing, Apple and DuckDuckGo) cannot be checked without a lookup, so instead of doing one it hands you the exact dig command and says the result is unknown until you run it. A user-agent is a claim, not a proof; every answer says which of the two you are holding.

Protocol versions 2025-06-18, negotiated per call. server/discover answers for clients on 2026-07-28, initialize for everyone else. Same index as /data/agents.json, refreshed every six hours. Listed in the official MCP Registry as dev.workers.pathwren.www/crawler-log-triage.

This page as markdown: /c/smithery-direct/mcp-triage.md — the same text, no markup to strip, no JavaScript, no key, CC0. Every page here has one: add .md to any address (also .mdx, <page>.html.md, <page>.html.mdx), or send Accept: text/markdown to this one. All of them in a single index: /c/smithery-direct/sitemap.md.