docs.dev

AI & agent access

Ask AI in the docs, markdown for every page, llms.txt, and a built-in MCP server — your docs are readable by humans and agents alike.

Docs published with docs.dev aren't just a website — they're a corpus that AI assistants and coding agents can consume directly. Everything on this page ships with every site, no configuration required.

Ask AI

Every docs site includes an Ask AI assistant — the floating button in the bottom-right corner of any docs page. It answers questions using only your documentation, streams its answers, and links to the pages it used.

Like AI writing in the editor, the assistant runs on Workers AI in your Cloudflare account: no API keys, no per-seat AI pricing, no message quotas imposed by us. If the deployment has the AI binding (the default wrangler.jsonc does), the assistant is live; without it, the button simply doesn't render.

Markdown for every page

Append .md to any docs URL to get the page as raw markdown — the convention agents already expect:

curl https://your-site.example/docs/getting-started.md

Every page also has a copy as markdown button and view options for opening the page directly in AI tools.

llms.txt

Two standard index files are generated from your content on every build:

  • /llms.txt — an index of all pages with descriptions, linking to the markdown version of each page.
  • /llms-full.txt — the entire docs corpus concatenated as one markdown document, for tools that want everything in a single fetch.

MCP server

Every site serves a Model Context Protocol endpoint at /mcp, so MCP clients can search and read your docs during a conversation or coding session. For Claude Code:

claude mcp add --transport http my-docs https://your-site.example/mcp

Or in any client that accepts JSON configuration:

{
  "mcpServers": {
    "my-docs": { "url": "https://your-site.example/mcp" }
  }
}

The server exposes three tools:

ToolWhat it does
search_docsSearch pages by keyword; returns titles, URLs, and snippets.
read_pageFetch one page as markdown by its URL or path.
list_pagesList every page with its title and description.

No authentication is required — the MCP server exposes exactly what the public site already serves.

On this page