ghidra-mcp
Ghidra MCP Server provides over 200 tools for AI-driven reverse engineering.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 2.6k
- Source
- mcp-github
- Repository
- github.com/bethington/ghidra-mcp
Overview
Ghidra MCP Server is a production-ready Model Context Protocol (MCP) server that bridges Ghidra's powerful reverse engineering capabilities with modern AI tools and automation frameworks. It offers 251 MCP tools, battle-tested AI workflows, and the most comprehensive Ghidra-MCP integration, including P-code simulation, real-time debugger integration, and PCode-graph data flow analysis. The tool supports full write access, enabling renaming, typing, annotating, creating structures, executing scripts, and more. Ideal for developers and teams tackling complex reverse engineering tasks.
Capabilities
- ▪251 MCP tools
- ▪Full write access
- ▪P-code simulation
- ▪Real-time debugger integration
- ▪PCode-graph data flow analysis
- ▪Cross-binary document transfer
Use cases
Setup
Refer to the installation guide in the GitHub repository: https://github.com/bethington/ghidra-mcp
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which versions of Ghidra does Ghidra MCP support?
Supports Ghidra version 12.1.2.
How do I run the Ghidra MCP Server?
It can be run in headless mode or GUI mode, and supports Docker deployment.
Related skills
pstack-claude
Provides rigorous workflows for multiple agents, supporting Claude Code, Codex, and more.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.