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
miscusi-peek/cheatengine-mcp-bridge
The Cheat Engine MCP Bridge project facilitates a powerful synergy between large language models (LLMs) like Claude, Cursor, and Copilot, and the memory analysis capabilities of Cheat Engine. It leverages the Model Context Protocol (MCP) to allow AI agents to interact directly with a target process's memory space, enabling automated reverse engineering, pointer scanning, and memory manipulation through natural language queries. The core idea is to transform days or weeks of manual memory analysis into minutes of AI-driven conversation with program memory. The system works by setting up a Python-based MCP server (`mcp_cheatengine.py`) that communicates with a Lua script running within Cheat Engine. This Lua script then uses Cheat Engine's API to perform various operations on the target process, including reading/writing memory, following pointer chains, disassembling code, analyzing functions, identifying C++ RTTI, setting hardware breakpoints, and even performing invisible tracing using DBVM. The project provides an extensive set of MCP tools covering memory access, analysis, debugging, process lifecycle management, memory allocation, code injection, and symbol management. Installation involves setting up the Python MCP server and loading the Lua bridge script in Cheat Engine. It supports both named pipes (Windows-only) and TCP relay for flexible deployment, allowing the MCP server to run remotely or in different environments like WSL. This bridge empowers AI agents to accelerate game modding, trainer creation, security audits, and general reverse engineering by providing an intelligent, conversational interface to complex memory analysis tasks.
https://github.com/miscusi-peek/cheatengine-mcp-bridge
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.