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
morluto/rea
REA (Reverse Engineer Anything) is an MCP server that gives AI coding agents tools for reverse-engineering software across multiple layers: native binaries, JavaScript and Electron applications, .NET assemblies, WebAssembly artifacts, EVM bytecode, and websites. Instead of hand-writing analysis scripts, an agent calls REA's MCP tools to inspect a target without access to its source code, and REA returns structured findings together with the evidence behind them: pseudocode, assembly, strings, symbols and call graphs for native binaries; module graphs and Electron process boundaries for JavaScript/Electron apps; and decoded sections for WASM or EVM bytecode. A matching CLI (rea) exposes the same analysis workflows directly from the terminal, so results and scripting are not tied to agent use. Setup is handled by npx rea-agents setup, which registers the MCP server with the chosen agent (Claude Code, Codex, Cursor, Gemini CLI, Grok Build and others), installs matching workflow instructions, and can optionally install a disassembler such as Hopper with the user's approval; existing installations of Hopper, Ghidra, or IDA are reused when present. Static JavaScript/Electron analysis works without any external disassembler. The intended workflow is feature replication: a developer points their agent at a target application's feature, REA traces the relevant code and produces the supporting evidence, and the agent uses that trail to explain the behavior or implement an equivalent feature in the developer's own project. The project is written primarily in TypeScript, distributed as the rea-agents npm package, licensed under MIT, and actively maintained with frequent releases. It targets security researchers, reverse engineers, and developers who want to understand or reimplement observed application behavior without access to the original source.
https://github.com/morluto/rea
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.
miscusi-peek/cheatengine-mcp-bridge
This project integrates AI agents with Cheat Engine via the Model Context Protocol (MCP) to automate reverse engineering, memory analysis, and game modding tasks using natural language commands.