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
svnscha/mcp-windbg
mcp-windbg is a Model Context Protocol (MCP) server designed to facilitate AI-driven analysis of Windows crash dumps by integrating with WinDBG/CDB debugger tools. This project acts as a bridge between large language models (LLMs) and WinDBG, enabling natural language interaction and command execution for crash dump analysis. The core functionality allows AI models to execute debugger commands, providing a powerful productivity enhancement for crash dump triage and analysis. Users can query the system in natural language to perform various debugging tasks such as examining call stacks, analyzing heap addresses, inspecting memory, and investigating exceptions, all through AI-assisted interpretation of WinDBG commands. The project is not a fully automated crash resolution tool but rather a Python wrapper around CDB that leverages the expertise of LLMs combined with user domain knowledge. It supports integration with Visual Studio Code and GitHub Copilot, enabling seamless use of MCP features within popular development environments. The server requires Python 3.10+, Windows OS with Debugging Tools for Windows installed, and an LLM that supports the Model Context Protocol. Key features include the ability to open and analyze crash dump files, run specific WinDBG commands, list dump files in directories, and unload dumps to free resources. The project emphasizes natural language-based "vibe" analysis, allowing users to ask the AI to inspect specific areas of a crash dump and provide explanations or insights. This approach facilitates first-level triage and categorization of crash dumps, making it useful for both simple and complex debugging scenarios. The repository includes setup instructions, usage guidelines, integration tips for VS Code and Copilot, and troubleshooting advice for common issues like missing CDB executables or symbol path configuration. The project is open-source under the MIT license and aims to enhance crash dump analysis workflows by combining AI capabilities with traditional debugging tools.
https://github.com/svnscha/mcp-windbg
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.
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.