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

See which discovery files a host serves - llms.txt, agent card, mcp.json.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Check Discovery Documents: 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,
  • Explain Document: 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
  • Validate Llms Txt: 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 link

What data it sees

Do you need an account

No: the server works without sign-in

See which discovery files a host serves - llms.txt, agent card, mcp.json. Free, no key, no signup. Direct endpoint, no gateway: https://www.pathwren.workers.dev/c/smithery-direct/mcp/doctor (streamable HTTP, no key, no signup). Tools: check_discovery_documents, validate_llms_txt, llms_txt_from_sitemap, validate_agent_card, explain_document, example. Call the example tool with no arguments for a worked answer against real data before you write any code. What it does and how, in one page: https://www.pathwren.workers.dev/c/smithery-direct/mcp-doctor.html

How to connect

How to connect Agent Discovery Doctor - llms.txt, agent card, mcp.json to Claude

The server address to paste into Claude settings:

https://agent-discovery-doctor--pathwren.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Agent Discovery Doctor - llms.txt, agent card, mcp.json to ChatGPT

The server address to paste into ChatGPT settings:

https://agent-discovery-doctor--pathwren.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Agent Discovery Doctor - llms.txt, agent card, mcp.json to Cursor

The server address to paste into Cursor settings:

https://agent-discovery-doctor--pathwren.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (7)

Raw names from tools/list. Only developers need these.

check_discovery_documentsProbes 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'.
explain_documentOne 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.
validate_llms_txtChecks 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.
llms_txt_from_sitemapPaste 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'.
validate_agent_cardValidates 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.
whoamiTakes 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 which of the 22 discovery documents this catalogue tracks your own client has been observed asking this host for — the dates, the status it took, and what it would have cost had the file been missing. 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.
exampleTakes 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.