mukul975/Anthropic-Cybersecurity-Skills
A comprehensive open-source library featuring 754 structured cybersecurity skills for AI agents, mapped to five industry frameworks to provide expert-level guidance.
Awesome MCP › Security & Reverse Engineering
zinja-coder/jadx-mcp-server
JADX-MCP-SERVER is a fully automated Model Context Protocol (MCP) server designed to work in conjunction with the JADX-AI-MCP plugin, enabling advanced reverse engineering capabilities for Android APKs. This project facilitates communication between local large language models (LLMs) such as Claude and the JADX decompiler environment, allowing for live analysis, vulnerability detection, manifest parsing, and code review of decompiled Android applications. The server acts as a bridge that connects LLM clients to the JADX-AI-MCP plugin via HTTP requests, enabling real-time interaction with the decompiled app context. This interaction supports a variety of MCP tools that provide functionalities like fetching class names and sources, searching methods and classes by keywords, and retrieving method sources, all aimed at enhancing the reverse engineering workflow. The project is part of Zin's Reverse Engineering MCP Suite and is currently undergoing a modular refactor to improve scalability and maintainability by separating core server logic, route handlers, and UI components. Despite the refactor pause on new features, the project continues to receive bug fixes and critical optimizations. The server is implemented in Python and works with a modified version of JADX GUI, integrating tightly with the MCP protocol to provide a seamless experience for reverse engineers using AI assistance. JADX-MCP-SERVER supports multiple AI agents and offers tools that help users perform quick analyses, find vulnerabilities, and debug APKs efficiently. It is designed to be a powerful assistant during the reverse engineering process, leveraging AI to provide context-aware code reviews and recommendations. The project is open source under the Apache 2.0 license and is part of a suite that includes APKTool-MCP-Server and ZIN-MCP-Client, creating a comprehensive ecosystem for Android reverse engineering with AI. Keywords extracted include: MCP server, JADX, JADX-AI-MCP plugin, reverse engineering, Android APK, LLM, Claude, vulnerability analysis, manifest parsing, decompiler, live code review, AI recommendations, modular architecture, Python server, AI-assisted debugging, open source, Apache 2.0 license, Zin's Reverse Engineering MCP Suite.
https://github.com/zinja-coder/jadx-mcp-server
Also in Security & Reverse Engineering
NVIDIA/SkillSpector
NVIDIA security scanner for AI agent skills and MCP tooling that detects prompt injection, data exfiltration, MCP tool poisoning and least-privilege problems, and can itself be run as an MCP server inside agent sessions.
mrexodia/ida-pro-mcp
ida-pro-mcp is an MCP server for IDA Pro that enables advanced reverse engineering capabilities through MCP-based interactions and automation.
LaurieWired/GhidraMCP
GhidraMCP is an MCP server that integrates Ghidra's reverse engineering capabilities with MCP clients, enabling automated binary analysis and decompilation through large language models.
invariantlabs-ai/mcp-scan
MCP-Scan is a security tool that statically and dynamically scans and monitors Model Context Protocol (MCP) connections to detect and prevent vulnerabilities such as prompt injections, tool poisoning, and cross-origin escalations.
zinja-coder/jadx-ai-mcp
JADX-AI-MCP is a JADX plugin integrating Model Context Protocol to enable AI-powered live reverse engineering, vulnerability detection, and code analysis of Android APKs using large language models like Claude.
mariocandela/beelzebub
Beelzebub is a secure low-code honeypot framework leveraging large language models and the Model Context Protocol (MCP) to detect and analyze cyber attacks, including prompt injection attempts against LLM agents.
svnscha/mcp-windbg
mcp-windbg is a Model Context Protocol server that enables AI models to analyze Windows crash dumps using WinDBG through natural language interaction and command execution.