Skip to main content
Glama
cnitlrt

Headless IDA MCP Server

by cnitlrt

致谢

该项目建立在以下工作基础之上:

无头 IDA MCP 服务器

如果您想直接将服务器作为 cli 应用程序运行,而不是以交互方式运行 IDA 插件,您可以选择它。

项目描述

该项目使用 IDA Pro 的无头模式来分析二进制文件,并通过 MCP 提供一套工具来管理和操作函数、变量等。

Related MCP server: idalib-mcp-headless

先决条件

安装

  1. 克隆项目到本地:

    git clone https://github.com/cnitlrt/headless-ida-mcp-server.git 
    cd headless-ida-mcp-server
  2. 安装依赖项:

    uv python install 3.12
    uv venv --python 3.12
    uv pip install -e .

配置

  1. 复制示例环境文件:

    cp .env_example .env
  2. .env中配置以下环境变量:

    • IDA_PATH : IDA Pro 的无头可执行文件 (idat) 的路径,例如/home/ubuntu/idapro/idat

    • PORT :MCP 服务器的端口号,例如8888

    • HOST :MCP 服务器的主机地址,例如127.0.0.1

    • TRANSPORT :MCP 传输模式( ssestdio

用法

  1. 启动服务器:

    uv run headless_ida_mcp_server
  2. 使用 MCP 客户端连接到服务器:

    调试:

    npx -y @modelcontextprotocol/inspector

    或者

    {
    "mcpServers": {
       "ida": {
          "command": "/path/to/uv",
          "args": ["--directory","path/to/headless-ida-mcp-server","run","headless_ida_mcp_server"]
       }
    }
    }

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    C
    maintenance
    A headless IDA Pro MCP server that enables AI agents to automatically open, analyze, and query multiple binary files simultaneously without manual GUI interaction. It provides 36 tools for tasks like decompilation, disassembly, and cross-reference analysis through IDA's idalib library.
    12
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    A headless MCP server that manages multiple independent IDA Pro worker processes for reverse engineering, supporting database operations and debug tools.
    20
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Headless MCP server for IDA Pro enabling on-demand database loading and programmatic reverse engineering workflows via MCP tools.
    18
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server that exposes IDA Pro's disassembler and Hex-Rays decompiler as tools and resources, enabling parallel binary analysis with multiple agents through a supervisor.
    22 PyPI
    1
    MIT