[go: up one dir, main page]
Customer StoriesReadMe Blog
Guides
Start typing to search…
  1. AI
  2. MCP (Model Context Protocol)

ReadMe's MCP Server

Set up ReadMe's MCP server to manage your documentation through AI development tools.

With ReadMe's MCP server, you can do everything you normally would in ReadMe, like adding and editing pages, directly through our API.

Setting Up ReadMe's MCP Server

ReadMe hosts a remote MCP server at https://docs.readme.com/mcp. Configure your AI development tools to connect to this server using your ReadMe API key.

Installation Instructions

Choose your preferred AI development tool below:

Cursor

Installation Link

Add to Cursor

Manual Installation

Add the following to your mcp.json file:

{
  "mcpServers": {
    "ReadMe MCP": {
      "url": "https://docs.readme.com/mcp"
    }
  }
}
VS Code

Installation Link

Install in VS Code

Manual Installation

Open a terminal and run the following command:

code --add-mcp '{"type":"http","name":"ReadMe MCP","url":"https://docs.readme.com/mcp"}'

Then, from inside VS Code, open the .vscode/mcp.json file and click Start server.

Claude Code

Open a terminal and run the following command:

claude mcp add --transport http ReadMe MCP https://docs.readme.com/mcp

From within Claude Code, you can use the /mcp command to get more information about the server.

Claude Desktop
  1. Open Claude Desktop and navigate to Settings > Connectors > Add Custom Connector
  2. Enter the name as ReadMe MCP
  3. Enter the remote MCP server URL as https://docs.readme.com/mcp
Windsurf

Copy the following JSON to your Windsurf MCP config file:

{
  "mcpServers": {
    "ReadMe MCP": {
      "serverUrl": "https://docs.readme.com/mcp"
    }
  }
}
ChatGPT
  1. Navigate to Settings > Connectors
  2. Add a custom connector with the server URL: https://docs.readme.com/mcp
  3. It should then be visible in the Composer > Deep research tool
  4. You may need to add the server as a source
📘

In Team, Enterprise, and Edu workspaces, only workspace owners and admins have permission to add connectors.

⚠️

Connectors can only be used with Deep Research

Gemini CLI

Add the following JSON to your Gemini CLI configuration file (~/.gemini/settings.json):

{
  "mcpServers": {
    "ReadMe MCP": {
      "httpUrl": "https://docs.readme.com/mcp",
      "headers": {
        "Accept": "application/json, text/event-stream"
      }
    }
  }
}
Codex

Requirements: Docker

Add the following to your Codex config file (~/.codex/config.toml):

[mcp_servers.ReadMe_MCP]
command = "docker"
args = ["run", "--rm", "-t", "ghcr.io/sparfenyuk/mcp-proxy:v0.3.2-alpine", "https://docs.readme.com/mcp", "--transport=streamablehttp"]
⚠️

Codex does not support MCP servers with OAuth2 authentication.

Authentication

If you want to execute API requests you will need to pass in an API key. You can do this in two ways depending on your client.

Option 1: Direct Headers

{
  "readmeApi": {
    "url": "https://docs.readme.com/mcp",
    "headers": {
      "authorization": "Bearer rdme_xn..."
    }
  }
}

Option 2: Using mcp-remote

Use mcp-remote to handle authentication. Update your MCP config:

{
  "mcpServers": {
    "readmeAPI": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://docs.readme.com/mcp",
        "--header",
        "Authorization: ${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer rdme_xn..."
      }
    }
  }
}
⚠️

Note: Claude Desktop (Windows) has a bug where spaces inside args aren't escaped when it invokes npx. Simply remove the whitespace after Authorization: to work around this bug.

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

  1. Open your AI editor (Cursor, VS Code, etc.)
  2. Start a new chat with the AI assistant
  3. Ask about ReadMe - try questions like:
    • "How do I [common use case]?"
    • "Show me an example of [API functionality]"
    • "Create a [integration type] using ReadMe"

Updated 2 days ago