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
invariantlabs-ai/mcp-scan
MCP-Scan is a comprehensive security tool designed specifically for the Model Context Protocol (MCP) ecosystem. It provides both static and dynamic scanning capabilities to detect and prevent a variety of security vulnerabilities that can affect MCP connections. These vulnerabilities include prompt injections, tool poisoning, cross-origin escalations, and rug pull attacks, which are critical threats in the context of MCP-based systems. The tool operates in two primary modes: static scanning and proxy monitoring. The static scanning mode (`mcp-scan scan`) analyzes installed MCP servers and their configurations to identify malicious tool descriptions and potential security issues before they can be exploited. This mode supports scanning configurations from popular MCP clients such as Claude, Cursor, and Windsurf, making it versatile for different MCP environments. The dynamic proxy mode (`mcp-scan proxy`) acts as a real-time monitoring layer that intercepts MCP traffic on the user's machine. It continuously audits and logs MCP interactions, enforcing security policies through guardrails that can detect and block suspicious activities such as unauthorized tool calls, data leaks including personally identifiable information (PII), and indirect prompt injections. Users can define custom guardrailing policies to tailor the security enforcement to their specific needs. MCP-Scan integrates with Invariant Guardrails, a policy enforcement framework, to provide advanced security checks and customizable rules. This integration allows for detailed inspection and control over MCP tool calls and responses, enhancing the security posture of MCP deployments. The tool is designed with privacy in mind, not storing or logging user data beyond what is necessary for security analysis. It also offers a local-only mode for users who prefer to avoid external API calls, though with reduced accuracy. Overall, MCP-Scan is a vital security solution for developers and organizations leveraging the Model Context Protocol, helping them safeguard their MCP infrastructure against emerging threats and maintain secure, reliable operations.
https://github.com/invariantlabs-ai/mcp-scan
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.
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.
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.