Using these docs with AI tools

The site is built to be read by agents as well as people.

Markdown everywhere

Every documentation page has a plain-markdown twin at the same path with a .md extension. For example, the authentication guide is also available at /getting-started/authentication.md. Point a scraper or an LLM at the markdown URLs and skip the HTML.

Two index files cover the whole site:

• /llms.txt lists every page with a short description.
• /llms-full.txt contains the full text of the entire site in one file.

The raw OpenAPI documents are downloadable too:

• /specs/edge-consumer.json
• /specs/auth.json

Hosted MCP server

An MCP (Model Context Protocol) server runs at:

https://docs.merrows.ai/mcp

It speaks streamable HTTP and exposes three tools:

Tool	What it does
search_docs	Full-text search across all pages, returns titles, URLs, and snippets
read_doc	Returns a page's full markdown by path
get_openapi_spec	Returns the Edge or Auth OpenAPI document

To add it to Claude Code:

claude mcp add --transport http merrows-docs https://docs.merrows.ai/mcp

Or in any MCP client configuration:

{
  "mcpServers": {
    "merrows-docs": {
      "type": "http",
      "url": "https://docs.merrows.ai/mcp"
    }
  }
}

Local alternative

If you prefer not to depend on a hosted endpoint, mcpdoc serves the same content from the llms.txt index:

uvx mcpdoc --urls "MerrowsDocs:https://docs.merrows.ai/llms.txt"