Skip to main content
This documentation site is built for AI agents. Every page is available as clean markdown, and the site exposes an MCP server and llms.txt for programmatic discovery.

​
MCP server

The docs site runs a Model Context Protocol server that lets AI tools search and read documentation directly. Server URL: https://docs.andiai.com/mcp

​
Claude Code

claude mcp add andi-docs --transport streamable-http https://docs.andiai.com/mcp

​
Claude web and desktop

Add this to your MCP server settings: 
{
  "mcpServers": {
    "andi-docs": {
      "url": "https://docs.andiai.com/mcp"
    }
  }
}

​
Cursor

Add to your .cursor/mcp.json: 
{
  "mcpServers": {
    "andi-docs": {
      "url": "https://docs.andiai.com/mcp"
    }
  }
}

​
VS Code

Add to your VS Code settings (JSON): 
{
  "mcp": {
    "servers": {
      "andi-docs": {
        "type": "http",
        "url": "https://docs.andiai.com/mcp"
      }
    }
  }
}

​
llms.txt

The site publishes llms.txt files that list all documentation pages with direct markdown URLs.
FileContents
/llms.txtPage titles and descriptions with markdown links
/llms-full.txtFull page content inlined as markdown
Use /llms.txt for discovery and navigation. Use /llms-full.txt when you need the complete documentation in a single request.

​
Markdown content negotiation

Any docs page returns clean markdown when requested with the Accept: text/markdown header. The markdown response is ~30x smaller than HTML and includes YAML frontmatter. 
curl -H "Accept: text/markdown" https://docs.andiai.com/getting-started/quickstart
The response includes headers for automated discovery:
  • Link headers pointing to /llms.txt and /llms-full.txt
  • X-Llms-Txt header with the llms.txt URL

​
LLM-ready search responses

The Search API supports a format=context parameter that returns results as markdown optimized for LLM context windows. See response format for details.

​
AI crawler access

The site’s robots.txt explicitly allows AI crawlers including GPTBot, ClaudeBot, and PerplexityBot.