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
fiddlecube/compliant-llm
Compliant LLM is a comprehensive toolkit designed to build secure and compliant AI agents and Model Context Protocol (MCP) servers. It supports multiple large language model (LLM) providers and ensures adherence to major compliance frameworks such as NIST, ISO, HIPAA, GDPR, OWASP, and others. The toolkit is widely used by information security, compliance, and generative AI teams to guarantee that their AI systems meet internal policies and external regulatory requirements. Key features include security testing against over eight attack strategies like prompt injection, jailbreaking, and context manipulation, compliance analysis for various frameworks, and support for multiple LLM providers through LiteLLM. It also offers an interactive visual dashboard for analyzing test results, end-to-end testing capabilities, and detailed reporting with actionable insights. The project supports a broad range of LLM providers including OpenAI, Anthropic, Gemini, Mistral, Groq, Deepseek, Azure, vLLM Ollama, Ollama, Nvidia Nim, and Meta Llama. Installation is straightforward via pip, and users can run a dashboard to configure providers and execute security and compliance tests. The roadmap includes plans for full application penetration testing, compliant and logged MCP servers, support for additional compliance frameworks like the EU AI Act, multimodal testing, CI/CD integration, access control checks, and internal audits. The project emphasizes security and privacy, tracking only anonymized usage statistics with an opt-out option. It is open to community contributions and provides extensive documentation and support channels including Discord, GitHub, and social media. Overall, Compliant LLM is a vital tool for organizations aiming to secure and ensure compliance of their AI systems, particularly those implementing MCP servers and AI agents.
https://github.com/fiddlecube/compliant-llm
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.