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
Wh0am123/MCP-Kali-Server
MCP Kali Server is a specialized lightweight API bridge designed to connect Model Context Protocol (MCP) clients, such as Claude Desktop and 5ire, to a Linux machine running Kali Linux. This connection enables the execution of terminal commands remotely through an API, facilitating AI-assisted penetration testing and cybersecurity tasks. The server allows AI models to run various terminal commands like nmap, nxc, curl, wget, and gobuster, which are essential tools for network scanning, web application interaction, and security assessments. The primary use case of MCP Kali Server is to empower AI-driven offensive security testing by integrating AI endpoints like OpenAI, Claude, and DeepSeek with Kali Linux. This integration allows AI to suggest and execute commands to solve Capture The Flag (CTF) challenges, automate reconnaissance, and exploitation tasks in real-time. The server exposes a controlled API that lets MCP applications send custom requests and receive structured outputs, making it highly suitable for red teamers, bug bounty hunters, and CTF players. Installation involves cloning the repository on a Linux machine that will act as the MCP server and running the provided Python script. MCP clients can then connect to this server from Windows or Linux machines by configuring their MCP client applications accordingly. The project also supports advanced use cases like memory forensics using Volatility and disk forensics with SleuthKit, enabling automation of complex forensic analysis tasks. MCP Kali Server is designed with offensive security professionals in mind, providing a powerful tool to leverage AI capabilities in cybersecurity operations. It emphasizes ethical use and educational purposes, with a disclaimer against unauthorized or malicious activities. Overall, this project represents a significant advancement in integrating AI with practical cybersecurity tools through the Model Context Protocol.
https://github.com/Wh0am123/MCP-Kali-Server
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.