import ConnectDocsMcpPrompt from '/snippets/connect-docs-mcp-prompt.mdx';

We want to make our documentation as accessible as possible. We've included several ways for you to use these docs programmatically through AI assistants, code editors, and direct integrations, such as Model Context Protocol (MCP).

On any page in our documentation, you'll find a contextual menu dropdown in the top right corner:

This includes our llms.txt, MCP server connection, and other quick access options such as ChatGPT and Claude.

Our documentation exposes two complementary Model Context Protocol (MCP) servers that let AI applications query LangChain content in real-time. For the best results, we recommend connecting both:

Adding both gives your coding agent access to the full picture: the why and how from the guides, plus the exact API details from the reference docs.

If you're using Claude Code, run these commands in your terminal to add both servers to your current project:

claude mcp add --transport http docs-langchain https://docs.langchain.com/mcp
claude mcp add --transport http reference-langchain https://reference.langchain.com/mcp

The commands above add the MCP servers only to your current project/working directory. To add them globally and access them in all projects, add the user scope by including `--scope user`:

```bash
claude mcp add --transport http docs-langchain --scope user https://docs.langchain.com/mcp
claude mcp add --transport http reference-langchain --scope user https://reference.langchain.com/mcp
```

1. Open Claude Desktop
2. Go to Settings > Connectors
3. Add both MCP server URLs:
   • https://docs.langchain.com/mcp
   • https://reference.langchain.com/mcp

If you're using OpenAI Codex CLI, run these commands in your terminal to add both servers globally:

codex mcp add langchain-docs --url https://docs.langchain.com/mcp
codex mcp add langchain-reference --url https://reference.langchain.com/mcp

Add the following to your MCP settings configuration file:

{
  "mcpServers": {
    "docs-langchain": {
      "url": "https://docs.langchain.com/mcp"
    },
    "reference-langchain": {
      "url": "https://reference.langchain.com/mcp"
    }
  }
}

Add both servers to your user-level ~/.deepagents/.mcp.json file to make them available in every Deep Agents Code project, or add them to a project-level .mcp.json file for only that project:

{
  "mcpServers": {
    "docs-langchain": {
      "type": "http",
      "url": "https://docs.langchain.com/mcp"
    },
    "reference-langchain": {
      "type": "http",
      "url": "https://reference.langchain.com/mcp"
    }
  }
}

Launch or restart dcode to load the servers. In an interactive session, run /mcp to inspect server status and loaded tools. For discovery locations and precedence rules, see MCP tools.

Add the following to your MCP settings configuration file:

{
  "servers": {
    "docs-langchain": {
      "url": "https://docs.langchain.com/mcp"
    },
    "reference-langchain": {
      "url": "https://reference.langchain.com/mcp"
    }
  }
}

Add the following to your MCP settings configuration file:

{
  "mcpServers": {
    "docs-langchain": {
      "serverUrl": "https://docs.langchain.com/mcp"
    },
    "reference-langchain": {
      "serverUrl": "https://reference.langchain.com/mcp"
    }
  }
}

For more information about using Mintlify's MCP servers, see the official Mintlify documentation.

Have questions or feedback? Let us know in our community forum.