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
Nexus-Router/nexus
Nexus is a comprehensive AI governance and security platform designed to unify and control multiple Model Context Protocol (MCP) servers, APIs, and large language model (LLM) providers through a single, unified endpoint. It enables users to aggregate various MCP servers that communicate via STDIO, SSE, and HTTP protocols, providing a centralized interface to manage and route requests across different AI services. Nexus supports major LLM providers such as OpenAI, Anthropic, Google, and AWS Bedrock, including full tool calling capabilities, making it a versatile solution for integrating diverse AI models and tools. The platform features intelligent context-aware tool search using natural language queries, allowing users to efficiently find and utilize connected tools. Configuration is flexible and managed through a TOML-based system with environment variable substitution, facilitating easy customization and deployment. Security is a core aspect of Nexus, with built-in protections including CORS, CSRF, OAuth2, and TLS support, alongside multi-level rate limiting that can be backed by in-memory or Redis stores. Nexus is designed for ease of deployment, available as a Docker container or as a standalone binary, with straightforward installation options for Linux, Windows (WSL), and macOS. It supports various MCP server types, including local subprocesses, SSE endpoints, and streamable HTTP servers, with detailed configuration options for authentication, header insertion, and access control based on user groups. This project is highly relevant to the Model Context Protocol ecosystem, providing a robust infrastructure for aggregating, governing, and securing AI services and tools. It facilitates seamless integration and management of multiple MCP servers and LLM providers, making it an essential tool for organizations looking to centralize AI operations and enforce governance policies effectively.
https://github.com/Nexus-Router/nexus
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.