Radare2 MCP

🚀 Using the MCP Server of Radare2

An MCP server for integrating Radare2 with AI assistants like Claude.

🚀 Quick Start

This is an MCP server designed to integrate Radare2 with AI assistants such as Claude, enabling seamless interaction between them.

✨ Features

This implementation provides a simple MCP server supporting the following features:

• Utilize a direct stdin/stdout communication model.
• Offer basic tool functionalities.
• Achieve seamless integration of binary analysis with Radare2.
• Support direct interaction between Radare2 and AI assistants.
• Enable file exploration and inspection.

📦 Installation

The simplest way is to use r2pm for installation:

$ r2pm -Uci r2mcp

With this command, the r2mcp executable will be copied to the bindir directory of r2pm. However, this executable does not need to be run directly from the terminal, as it only works when the MCP service handler of the AI language model is started.

📚 Documentation

Configuration

In the Claude Desktop application, press CMD + , to open the developer settings, edit the configuration file, and restart the client. Here's what needs to be added to the configuration file:

Claude Desktop Integration

To use this server with Claude Desktop, update your Claude configuration file:

1. Locate your Claude Desktop configuration file:
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
   • Linux: ~/.config/Claude/claude_desktop_config.json
2. Add the following content to the configuration file:

{
  "mcpServers": {
    "radare2": {
      "command": "r2pm",
      "args": ["-r", "r2mcp"]
    }
  }
}

Docker

You can also use Docker to run r2mcp.

docker build -t r2mcp .

Then, update your Claude Desktop configuration file to use the Docker image:

{
  "mcpServers": {
    "radare2": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "-v", "/tmp/data:/data", "r2mcp"]
    }
  }
}