GhidraMCP

GhidraMCP

ghidraMCP is an MCP server that allows LLMs to autonomously reverse engineer applications by exposing core Ghidra functionality as tools for MCP clients.

Category
访问服务器

README

License GitHub release (latest by date) GitHub stars GitHub forks GitHub contributors Follow @lauriewired

ghidra_MCP_logo

ghidraMCP

ghidraMCP is an Model Context Protocol server for allowing LLMs to autonomously reverse engineer applications. It exposes numerous tools from core Ghidra functionality to MCP clients.

https://github.com/user-attachments/assets/36080514-f227-44bd-af84-78e29ee1d7f9

Features

MCP Server + Ghidra Plugin

  • Decompile and analyze binaries in Ghidra
  • Automatically rename methods and data
  • List methods, classes, imports, and exports

Installation

Ghidra 12.1.2 Compatible Fork — This fork updates the plugin to build and run on Ghidra 12.1.2.
The original upstream targets Ghidra 11.3.2.

Changes Made for Ghidra 12.1.2 Compatibility

The original plugin was built for Ghidra 11.3.2. To make it work on Ghidra 12.1.2, these changes were made:

  • extension.properties — Updated version and ghidraVersion from 11.3.2 to 12.1.2 so Ghidra accepts the extension.
  • pom.xml — Updated all Ghidra dependency version references from 11.3.2 to 12.1.2.
  • lib/GhidraMCP.jar — Recompiled the plugin against Ghidra 12.1.2 API JARs (no source code changes were needed — all APIs used by the plugin are stable across these versions).
  • README.md — Updated install/build instructions for Ghidra 12.1.2.

The plugin source code (GhidraMCPPlugin.java) required no modifications. Only the build configuration and metadata files were updated.

Prerequisites

Ghidra

Download the GhidraMCP-12.1.2.zip from this repository's releases. Then import it into Ghidra:

  1. Run Ghidra
  2. Select File -> Install Extensions
  3. Click the + button
  4. Select the GhidraMCP-12.1.2.zip
  5. Restart Ghidra
  6. Enable the plugin in File -> Configure -> Developer -> GhidraMCPPlugin
  7. Optional: Configure the port in Edit -> Tool Options -> GhidraMCP HTTP Server

Video Installation Guide:

https://github.com/user-attachments/assets/75f0c176-6da1-48dc-ad96-c182eb4648c3

MCP Clients

Theoretically, any MCP client should work with ghidraMCP. Three examples are given below.

Example 1: Claude Desktop

To set up Claude Desktop as a Ghidra MCP client, go to Claude -> Settings -> Developer -> Edit Config -> claude_desktop_config.json and add the following:

{
  "mcpServers": {
    "ghidra": {
      "command": "python",
      "args": [
        "/ABSOLUTE_PATH_TO/bridge_mcp_ghidra.py",
        "--ghidra-server",
        "http://127.0.0.1:8080/"
      ]
    }
  }
}

Alternatively, edit this file directly:

/Users/YOUR_USER/Library/Application Support/Claude/claude_desktop_config.json

The server IP and port are configurable and should be set to point to the target Ghidra instance. If not set, both will default to localhost:8080.

Example 2: Cline

To use GhidraMCP with Cline, this requires manually running the MCP server as well. First run the following command:

python bridge_mcp_ghidra.py --transport sse --mcp-host 127.0.0.1 --mcp-port 8081 --ghidra-server http://127.0.0.1:8080/

The only required argument is the transport. If all other arguments are unspecified, they will default to the above. Once the MCP server is running, open up Cline and select MCP Servers at the top.

Cline select

Then select Remote Servers and add the following, ensuring that the url matches the MCP host and port:

  1. Server Name: GhidraMCP
  2. Server URL: http://127.0.0.1:8081/sse

Example 3: 5ire

Another MCP client that supports multiple models on the backend is 5ire. To set up GhidraMCP, open 5ire and go to Tools -> New and set the following configurations:

  1. Tool Key: ghidra
  2. Name: GhidraMCP
  3. Command: python /ABSOLUTE_PATH_TO/bridge_mcp_ghidra.py

Building from Source (Ghidra 12.1.2)

  1. Copy the following JARs from your Ghidra 12.1.2 installation into lib/:

    • Ghidra/Features/Base/lib/Base.jar
    • Ghidra/Features/Decompiler/lib/Decompiler.jar
    • Ghidra/Framework/Docking/lib/Docking.jar
    • Ghidra/Framework/Generic/lib/Generic.jar
    • Ghidra/Framework/Project/lib/Project.jar
    • Ghidra/Framework/SoftwareModeling/lib/SoftwareModeling.jar
    • Ghidra/Framework/Utility/lib/Utility.jar
    • Ghidra/Framework/Gui/lib/Gui.jar
  2. Build with Maven:

    mvn clean package assembly:single
    

    Or compile directly with javac:

    javac --release 21 -cp $(find /path/to/ghidra_12.1.2_PUBLIC -name '*.jar' -path '*/lib/*' | tr '\n' ':') -d build src/main/java/com/lauriewired/GhidraMCPPlugin.java && jar cfm lib/GhidraMCP.jar src/main/resources/META-INF/MANIFEST.MF -C build com/
    

The generated zip (target/GhidraMCP-1.0-SNAPSHOT.zip) contains:

  • lib/GhidraMCP.jar
  • extension.properties
  • Module.manifest

Note: lib/.gitignore ignores all JARs — the Ghidra dependency JARs and the built GhidraMCP.jar are local only and not committed.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选