Radare2 MCP Server

Name: Radare2 MCP Server
Author: dnakov

@dnakov

リポジトリホームページ

Radare2 MCP Server について

MCP stdio server for radare2

#radare2 #mcp #server #binary-analysis

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

トランスポート

stdio

公開者

dnakov

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "radare2-mcp": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "r2mcp",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Radare2 MCP Server?

An MCP server that integrates the radare2 binary analysis framework with AI agents like OpenCode, Mai, VSCode, Claude, and CLION. It is written in C using native radare2 APIs and supports local or remote r2/iaito sessions via r2pipe, with optional HTTP server mode and raw r2 command access.

How to use Radare2 MCP Server?

Install via r2pm -Uci r2mcp or build from source with make install. Configure your MCP client (Claude Desktop, VS Code, Zed) to use r2pm with args: ["-r", "r2mcp"]. Alternatively, run as an HTTP server with r2mcp -H <port> or as an r2 core plugin with the r2mcp start command inside a radare2 session.

Key features of Radare2 MCP Server

Fully written in C using native radare2 APIs.
Seamless binary analysis with radare2 integration.
Connect to local or remote r2/iaito via r2pipe.
Supports readonly mode, sandbox lock, and tool restrictions.
HTTP server mode with optional session multiplexing.
Optional raw access to r2 commands or JavaScript scripts.

Use cases of Radare2 MCP Server

Analyze binaries interactively with AI assistants like Claude or Copilot.
Debug and reverse engineer executables from within code editors (VS Code, Zed).
Run automated binary

「その他」の他のコンテンツ

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K