GhidraMCP

Stale
GitHub Java Apache-2.0

Description

MCP server for Ghidra reverse engineering platform, enabling AI agents to autonomously perform binary analysis and vulnerability discovery.

Key Features

  • MCP server for Ghidra enabling LLMs to autonomously perform binary reverse engineering
  • Decompile and analyze binaries with automatic renaming of methods and data
  • List all methods, classes, imports, and exports, exposing core Ghidra functionality to MCP clients
  • Compatible with multiple MCP clients including Claude Desktop, Cline, and 5ire
  • Open source under Apache 2.0 license with source build support and configurable port settings

Use Cases

💡 Security researchers use AI-assisted analysis to quickly analyze malware and discover vulnerabilities
💡 Reverse engineers drive binary code understanding and refactoring through natural language instructions
💡 Accelerate binary function identification and analysis in CTF competitions and vulnerability research
💡 Security teams automate auditing and compliance checking of closed-source software
💡 Educational settings helping students understand reverse engineering concepts and binary analysis workflows

Strengths & Limitations

Strengths

  • High community interest (9.9k stars)
  • Permissive open-source license (Apache-2.0)
  • Responsive to issues, low backlog

⚠️ Limitations

  • No updates in over 14 months

Quick Start

1. Install Ghidra and Python 3
2. Download the GhidraMCP plugin from Releases
3. Install the extension in Ghidra (File → Install Extensions)
4. Enable the GhidraMCP plugin and configure the port
5. Configure the MCP client (e.g., Claude Desktop) config to point to bridge_mcp_ghidra.py
6. Load a binary file and start analyzing via AI conversation

Related Projects

Burp AI Agent

1.5k · Kotlin
Active A

A Burp Suite extension that adds MCP tooling, AI-assisted analysis, privacy controls, and passive or active scanning to security testing workflows.

burp-suitesecuritymcp +2
  • · 11 AI backends — Burp AI built-in, Ollama, LM Studio, NVIDIA NIM, Perplexity, Gemini CLI, Claude CLI, Codex CLI, and more
  • · 53+ MCP tools — expose Burp Suite capabilities to any MCP client for autonomous AI-driven security testing
  • · 62 vulnerability classes — passive and active AI scanners covering injection, auth, crypto, and more

ToolHive

2.1k · Go
Active A

An enterprise-grade platform for running and managing MCP servers with containerized deployment, security isolation, network policies, resource limits, and unified management of large-scale MCP server fleets via Kubernetes or Docker.

mcptoolsgo +4
  • · Isolated container-based MCP server execution with per-request identity and access policy enforcement
  • · Modular architecture: Gateway, Registry Server, Runtime, and Portal for enterprise-grade MCP management
  • · Kubernetes operator for fleet management with CRDs, multi-namespace support, and ingress integration

Archestra

4.2k · TypeScript
Active A

Enterprise AI Platform with guardrails, MCP registry, gateway and orchestrator — comprehensive AI agent governance and management.

typescriptmcpsecurity +2
  • · Kubernetes-native MCP orchestrator — runs MCP servers in K8s managing state, API keys, and OAuth centrally
  • · Private MCP registry with governance — share self-hosted and third-party MCPs across your organization
  • · Non-probabilistic security engine preventing data exfiltration via tool guardrails and the Lethal Trifecta defense

Damn Vulnerable MCP Server

1.3k · Python
Stale C

A deliberately vulnerable MCP server for security education, containing multiple MCP protocol vulnerability scenarios to help developers understand and prevent agent security risks.

mcpsecurityvulnerability +2
  • · 10 progressive difficulty challenges covering MCP security vulnerabilities
  • · Covers prompt injection, tool poisoning, rug pull, and token theft attacks
  • · Docker-based lab environment for hands-on security training