What is MCP?

Model Context Protocol (MCP) is an open standard that gives AI assistants a live connection to external tools and data. Think of it like a USB port for AI — instead of pasting your docs into a chat window, your AI tool connects directly and can read, search, and act on your content in real time.

Two MCP Servers with ReadMe

ReadMe supports two distinct MCP servers depending on what you want to accomplish:

	For	What it does
ReadMe's MCP Server	You — the doc author	Search, read, and update your ReadMe documentation through AI
Your Project's MCP Server	Your API users	Give their AI tools live access to your API spec and docs

Connect to this MCP Server

Configure your MCP client to connect to the ReadMe MCP server.

Server URL

Defaults to ReadMe's MCP server — replace with your own project URL if needed

Authentication and filters— API keys, projects, and branch settings

URL Parameters

Customize which project or version branch to connect to.

projects (Enterprise only)

Filter to specific projects. Comma-separated list.

branch

Use a specific ReadMe branch. Stable version by default.

Search tools (search, fetch) are not available when using a branch.

Authentication

API Authentication Key (optional)

Authentication to pass to the API for execute functionality. Find yours under Account Settings → API Keys (starts with rdme_).

Private Project Access (optional)

If your project requires login to view, choose the matching auth type below.

Your Connection URL

https://docs.readme.com/mcp

Manual Installation

// .cursor/mcp.json
{
  "mcpServers": {
    "readme": {
      "url": "https://docs.readme.com/mcp"
    }
  }
}

Next Steps

ReadMe's MCP Server — use AI to manage and update your own ReadMe docs
Your Project's MCP Server — let your users' AI tools connect to your API
ReadMe MCP Use Cases — ready-to-use prompts for common workflows
Your API MCP Use Cases — example workflows for your users