What are the prerequisites for ghidraMCP?
You need Ghidra installed, Python 3, and the MCP Python SDK.
@LaurieWired
基本信息
MCP Server for Ghidra
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ghidra": {
"command": "python",
"args": [
"/ABSOLUTE_PATH_TO/bridge_mcp_ghidra.py",
"--ghidra-server",
"http://127.0.0.1:8080/"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
ghidraMCP is a Model Context Protocol (MCP) server that allows LLMs to autonomously reverse engineer applications by exposing core Ghidra functionality to MCP clients. It includes both a Ghidra plugin and a Python MCP bridge.
Install Ghidra and the GhidraMCP plugin via the release ZIP, then run the Python MCP bridge script (bridge_mcp_ghidra.py) with appropriate transport and server settings. Clients like Claude Desktop, Cline, or 5ire can then connect to the bridge to issue reverse‑engineering commands.
You need Ghidra installed, Python 3, and the MCP Python SDK.
Download the latest release ZIP, then in Ghidra go to `File` → `Install Extensions`, click the `+` button, select the ZIP, and restart Ghidra. Ensure the plugin is enabled in `File` → `Configure` → `Developer`.
The README provides examples for Claude Desktop, Cline, and 5ire, but states that any MCP client should work theoretically.
The bridge script supports command‑line arguments for transport (`--transport sse` or default stdio), MCP host/port, and Ghidra server URL. Defaults are localhost:8080 for both.
Yes. Copy required Ghidra JARs into the project’s `lib/` directory and run `mvn clean package assembly:single`. The generated ZIP includes the plugin and resources.
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
MCP Toolbox for Databases is an open source MCP server for databases.
Open-source MCP to use Blender with any LLM
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Model Context Protocol Servers
评论