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-ai-mcp
JADX-AI-MCP is a plugin designed for the JADX decompiler that integrates the Model Context Protocol (MCP) to enable AI-powered live reverse engineering, vulnerability detection, and code analysis of Android APKs. It leverages large language models (LLMs) such as Claude to provide real-time, context-aware code review and recommendations. The project is part of the Zin MCP Suite and works in conjunction with the standalone JADX MCP Server, a Python server that facilitates communication between the JADX-AI-MCP plugin and LLMs via MCP. This setup allows for live interaction with the decompiled Android app context, enhancing the capabilities of static code analysis and reverse engineering. The plugin supports multiple AI agents and offers a variety of MCP tools that enable detailed inspection and analysis of Android APK components, including fetching class sources, methods, fields, smali code, AndroidManifest.xml content, resource files, and more. Users can perform quick analyses, identify vulnerabilities such as insecure API usage or hardcoded secrets, and gain insights into code obfuscation, permissions, and potential security risks. Additionally, the tool assists in reverse engineering tasks by deobfuscating and renaming classes and methods, inferring the purpose of smali methods, and identifying libraries or SDKs used. JADX-AI-MCP also supports static analysis features like listing network-related API calls, file I/O operations, and detecting potential leaks of device information or personally identifiable information (PII). It facilitates AI-driven code modifications, including refactoring, commenting, and rewriting code in different languages for analysis. The plugin is designed to be installed easily via JADX's plugin system or manually through provided releases. Overall, JADX-AI-MCP enhances the reverse engineering workflow by integrating AI capabilities directly into the JADX environment, making it a powerful tool for security researchers, developers, and analysts working with Android applications.
https://github.com/zinja-coder/jadx-ai-mcp
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.
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.
BlackSnufkin/LitterBox
LitterBox is a secure sandbox environment integrating with LLM agents via MCP to provide advanced malware analysis and testing capabilities for red and blue teams before deployment.