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
apktool-mcp-server is a Model Context Protocol (MCP) server designed to integrate Apk Tool with advanced large language models (LLMs) like Claude for live, AI-assisted reverse engineering and vulnerability analysis of Android APK files. This project is part of Zin's Reverse Engineering MCP Suite and aims to automate and enhance the process of analyzing Android applications by combining the powerful decompilation capabilities of Apk Tool with the contextual understanding and code review capabilities of LLMs. The server enables real-time interaction where users can decompile APKs, review smali code, parse AndroidManifest.xml files, and receive AI-driven recommendations and vulnerability detection insights. The server supports a variety of MCP tools that facilitate detailed APK analysis, including building APKs from decoded projects, extracting and modifying smali files and resources, searching for patterns in code, and cleaning projects for rebuilding. It also provides specific functions to analyze permissions, detect hardcoded URLs, identify security risks like exported activities, and modify code to insert logging or patch vulnerabilities. apktool-mcp-server is designed to work seamlessly with local LLMs through the Zin MCP Client and supports integration with Claude Desktop for enhanced AI capabilities. The project is still in early development but offers a comprehensive suite of features for security researchers, reverse engineers, and developers interested in Android application security and analysis. It is distributed under the Apache 2.0 license and requires Python 3.10+. Overall, apktool-mcp-server represents a cutting-edge tool that leverages AI and MCP to streamline and improve the reverse engineering workflow for Android APKs, making it easier to uncover vulnerabilities, understand app behavior, and perform static analysis with AI assistance.
https://github.com/zinja-coder/apktool-mcp-server
A comprehensive open-source library featuring 754 structured cybersecurity skills for AI agents, mapped to five industry frameworks to provide expert-level guidance.
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.
ida-pro-mcp is an MCP server for IDA Pro that enables advanced reverse engineering capabilities through MCP-based interactions and automation.
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.
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.
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.
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.
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.