Skip to content

Agent Discovery Doctor - llms.txt, agent card, mcp.json

dev.workers.pathwren.www/agent-discovery-doctorwww.pathwren.workers.devstreamable-httpv1.4.0Scanned

{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

8 tools: 4 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 4 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 0
  • 5 findings, 2 high

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Agent Discovery Doctor - llms.txt, agent card, mcp.json can do

The Agent Discovery Doctor - llms.txt, agent card, mcp.json is published by www.pathwren.workers.dev, a domain the MCP Registry verified. It has 8 tools. It can create or change data (4 tools: no_arguments_check_this_hosts_own_discovery_documents, example, check_discovery_documents and llms_txt_from_sitemap), but cannot delete data. 4 tools only read.

1 tool reads private data (whoami); 2 tools bring in text other people can write (whoami and check_discovery_documents).

The fixed checks matched 5 findings, 2 of them high severity (tool-shadowing and sensitive-path). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 15, 2026, version 1.4.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Changes things 4Claude Code: ask
  • check_discovery_documentsFIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Probes 22 docum…Reads text others write1 finding

    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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • High

      The description refers to "mcp.json".

      Matched text

      description: "...gent card, owners.json, oauth metadata, mcp.json, apis.json, openapi, robots, sitemap —..."

      What this check looks for
    Description, as the server wrote it
    FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Probes 22 documents agents and trust indexes ask for — llms.txt, agent card, owners.json, oauth metadata, mcp.json, apis.json, openapi, robots, sitemap — as served, missing, gated or 200-with-HTML soft-404, and says who asks for each missing one. Refuses private, ephemeral and its own hosts. Example: host='example.com'.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • example{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"example","arguments":{}}} — POST that exact body to https://www.pathwren.workers.dev/mcp/doctor and you are done: fr…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
    {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"example","arguments":{}}} — POST that exact body to https://www.pathwren.workers.dev/mcp/doctor 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 — validate_llms_txt, 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 — validate_llms_txt on a four-line llms.txt held as a constant in this file: it exercises the H1, the blockquote summary and an H2 link section, which is the whole format — and it fetches nothing, from us or from anyone — 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 validate_llms_txt with {"text":"# Site\n\n> One line.\n\n## Docs\n\n- [Guide](https://e.com/g): start here."} and returns its real answer.

    Annotations the server declares

    • title: Run the worked example
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • llms_txt_from_sitemapFIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Paste sitemap.x…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
    FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Paste sitemap.xml, or one URL per line, and get a draft llms.txt: URLs grouped into H2 sections by path, titles from slugs, lastmod kept, and a TODO wherever only you can write the sentence. A sitemap index is reported as one. Example: xml='https://e.com/docs/a\nhttps://e.com/blog/b'.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • no_arguments_check_this_hosts_own_discovery_documentsTAKES NO ARGUMENTS.2 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.

    Findings

    • Warn

      The description names a tool "beside" that this server does not list.

      Matched text

      description: "...ings answer one question each under the tool named beside them: /mcp (whoami), /mcp/lint (whoami)..."

      What this check looks for
    • Warn

      The description contains "Every other tool", wording about other tools or servers.

      Matched text

      description: "...e are here too and take nothing either. Every other tool on this server wants a file pasted in;..."

      What this check looks for
    Description, as the server wrote it
    TAKES NO ARGUMENTS. POST {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} to https://www.pathwren.workers.dev/mcp/doctor — the answer is the whole agent-discovery catalogue checked against THIS host — every document this server tracks, whether this host serves it, its size and content type, which ones are missing, and the part only this server can add: the named clients it has watched ask for each file, when, and the status that request took. There is nothing to fill in: the input schema is literally empty, `arguments: {}` and no `arguments` key at all both work, and the subject is a file this host already publishes, so the answer does not depend on you at all. No key, no account, no OAuth, no session to open first, read-only, and nothing for you to invent. Nothing is fetched to build it — no request leaves this edge, and none is made to you. whoami and example are here too and take nothing either. Every other tool on this server wants a file pasted in; this one wants nothing. The siblings answer one question each under the tool named beside them: /mcp (whoami), /mcp/lint (whoami), /mcp/triage (no_arguments_triage_this_hosts_own_crawler_log), /mcp/robots (no_arguments_lint_this_hosts_robots_txt), /mcp/netcheck (no_arguments_report_the_crawler_ip_ranges_this_host_mirrors), /mcp/markdown (markdown_lane_self_report). Example: the complete call, exactly as written, nothing to fill in — {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} returns a present/missing verdict per tracked document with its byte size, the group each belongs to, the score out of the catalogue, and the observed askers per document with the date and status each one got.

    Annotations the server declares

    • title: No arguments: the discovery check this server runs on a host you name, run on this host
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 4Show 4 read-only tools
  • explain_documentFIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — One catalogue e…No findings

    Why it is in this group

    • The name "explain_document" says "explain": a word for reading.
    Description, as the server wrote it
    FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — One catalogue entry: what the document is for, the named clients observed asking this host for it with dates and the status they took, what a 404 costs, and the spec URL. No argument lists all 22. Example: name='owners.json' names the bot that asks for it twice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_agent_cardFIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Validates a pas…No findings

    Why it is in this group

    • The name "validate_agent_card" says "validate": a word for reading.
    Description, as the server wrote it
    FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Validates a pasted /.well-known/agent-card.json against the nine fields A2A marks required and each skill's id/name/description/tags, and warns on capabilities declared true that a reader will then try. Example: json='{"name":"a"}' returns the eight missing fields.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_llms_txtFIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Checks pasted l…No findings

    Why it is in this group

    • The name "validate_llms_txt" says "validate": a word for reading.
    Description, as the server wrote it
    FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"no_arguments_check_this_hosts_own_discovery_documents","arguments":{}}} — Checks pasted llms.txt against the format: one H1, a blockquote summary, H2 sections of `- [name](url): notes`. Errors and warnings with line numbers and fixes, plus the parsed links. Text in, nothing fetched. Example: text='# Site' warns it has no summary and no sections.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • whoami{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — POST that to https://www.pathwren.workers.dev/mcp/doctor and the answer is the user-agent…Reads private dataReads text others write2 findings

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "document": it reads documents.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.

    Findings

    • High

      The description refers to "mcp.json".

      Matched text

      description: "...logue tracks (llms.txt, the agent card, mcp.json, apis.json, oauth-protected-resource…)..."

      What this check looks for
    • Warn

      The description names a tool "beside" that this server does not list.

      Matched text

      description: "...u, same empty arguments, each under the tool named beside its path: /mcp (whoami), /mcp/lint (who..."

      What this check looks for
    Description, as the server wrote it
    {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — POST that to https://www.pathwren.workers.dev/mcp/doctor and the answer is the user-agent you sent, the class this host's own instrument books it as, whether we have logged you here before — and the part only this server can answer: which of the discovery documents this catalogue tracks (llms.txt, the agent card, mcp.json, apis.json, oauth-protected-resource…) a client like yours has been observed asking THIS host for, when, and what status it took. Takes no arguments. Safe to call. Deterministic. Touches no third party. Nothing is fetched to build it: every fact comes from the headers on your own request or from a file this host already publishes. Only this server answers the last part — its five siblings answer one other question each about you, same empty arguments, each under the tool named beside its path: /mcp (whoami), /mcp/lint (whoami), /mcp/triage (no_arguments_triage_this_hosts_own_crawler_log), /mcp/robots (no_arguments_lint_this_hosts_robots_txt), /mcp/netcheck (no_arguments_report_the_crawler_ip_ranges_this_host_mirrors), /mcp/markdown (markdown_lane_self_report) on https://www.pathwren.workers.dev. Example: arguments={} returns your user-agent, your address, the class we book you as, whether we have seen you here before, and which agent-discovery documents this host has watched a client like yours ask for — the dates, and the status each request took.

    Annotations the server declares

    • title: Who is calling?
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:53 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.pathwren.workers.dev/c/mcp-registry-official/mcp/doctor: tools/list returned 8 tools to an anonymous client, including no_arguments_check_this_hosts_own_discovery_documents (write), example (write), check_discovery_documents (write), llms_txt_from_sitemap (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 high3 warn

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-discovery-doctor https://www.pathwren.workers.dev/c/mcp-registry-official/mcp/doctor
claude mcp add --transport http agent-discovery-doctor https://www.pathwren.workers.dev/c/mcp-registry-official/mcp/doctor

Run in a terminal.

Claude Code permissions

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

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-discovery-doctor__whoami",
      "mcp__agent-discovery-doctor__explain_document",
      "mcp__agent-discovery-doctor__validate_llms_txt",
      "mcp__agent-discovery-doctor__validate_agent_card"
    ],
    "ask": [
      "mcp__agent-discovery-doctor__no_arguments_check_this_hosts_own_discovery_documents",
      "mcp__agent-discovery-doctor__example",
      "mcp__agent-discovery-doctor__check_discovery_documents",
      "mcp__agent-discovery-doctor__llms_txt_from_sitemap"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-discovery-doctor. Review it before you use it.

Capability tags behind 2 rules
  • mcp__agent-discovery-doctor__whoami private-data, untrusted-input
  • mcp__agent-discovery-doctor__check_discovery_documents untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/dev.workers.pathwren.www/agent-discovery-doctor/verify?hash=875539ae518745e076c565784ab7cb2f0fdf5b67c8a89c90ccef3fa314aef2ae" | jq -e '.changed == false'

Pinned hash 875539ae5187, from Nov 15, 2026, 05:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/dev.workers.pathwren.www/agent-discovery-doctor/changes.xml

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

Badge

Anlyon Radar badge for dev.workers.pathwren.www/agent-discovery-doctor
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.pathwren.www/agent-discovery-doctor.svg)](https://radar.anlyon.com/servers/dev.workers.pathwren.www/agent-discovery-doctor)

Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.

Agent Discovery Doctor - llms.txt, agent card, mcp.json: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Agent Discovery Doctor - llms.txt, agent card, mcp.json safe?

No scan can promise that. What its definitions show: 8 tools, 4 of which can change, send or delete something, and 5 findings (2 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agent Discovery Doctor - llms.txt, agent card, mcp.json delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Agent Discovery Doctor - llms.txt, agent card, mcp.json do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Agent Discovery Doctor - llms.txt, agent card, mcp.json have?

8 tools: 4 write, 4 read. no_arguments_check_this_hosts_own_discovery_documents, example, check_discovery_documents, llms_txt_from_sitemap, whoami, explain_document, validate_llms_txt and validate_agent_card.

Does the Agent Discovery Doctor - llms.txt, agent card, mcp.json need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Agent Discovery Doctor - llms.txt, agent card, mcp.json send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Agent Discovery Doctor - llms.txt, agent card, mcp.json changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.