llms.txt for agents

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.ux-xd/llms-txt",
  "description": "Any site's llms.txt: find the covering index, read its linked docs as markdown, search sections.",
  "title": "llms.txt for agents",
  "repository": {
    "url": "https://github.com/ux-xd/llms-txt-mcp",
    "source": "github"
  },
  "version": "0.1.1",
  "websiteUrl": "https://llmstxtmcp.dev",
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://llmstxtmcp.dev/mcp"
    }
  ],
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "auth": "none",
      "category": "documentation",
      "factory": "agie",
      "keywords": [
        "llms.txt",
        "llms-full.txt",
        "documentation",
        "docs",
        "markdown",
        "agent-readable",
        "markdown for agents",
        "context"
      ],
      "not_for": "General web scraping or crawling (one fetch per rung, never link-following), pages behind logins, generating or auditing a site's own llms.txt, or searching the whole web for documentation.",
      "tools": [
        "llms_index",
        "llms_page",
        "llms_search"
      ],
      "when_to_use": "The user needs a product's or library's own documentation and the site may publish llms.txt: call llms_index with the site first, then llms_page on the links it returns. Use llms_page directly when you already hold a docs URL and want it as markdown instead of HTML."
    }
  }
}