HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

GhostCrew is an AI agent framework for bug bounty hunting, red-team operations, pentesting, and operator education. It integrates LLM autonomy, multi-agent coordination, and MCP extensibility with a minimal core toolset, supported by RAG for context-aware reasoning, a persistent internal state, reproducible workflows, and interactive assistance.

The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in Artificial Intelligence systems. As traditional software security practices are not always sufficient for AI, this project provides a shared understanding and a common language for addressing the unique security challenges of the AI development lifecycle.

Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

Next-Gen Secret Scanner powered by Local AI (Ollama). Filters false positives by understanding code context.

Contexi let you interact with entire codebase or data with context using a local LLM on your system.

Comprehensive LLM protection toolset aligned to addressing OWASP vulnerabilities - https://genai.owasp.org/llm-top-10/

Comprehensive LLM AI Model protection | Protect your production GenAI LLM applications | cybersecurity toolset aligned to addressing OWASP vulnerabilities in Large Language Models - https://genai.owasp.org/llm-top-10/

AIDEFEND MCP is a local-first AI Security Defensive Assistant that brings the full AIDEFEND countermeasure library into your environment and turns static knowledge into actionable protection for LLMs and agentic AI systems — privately, securely, and on-device.

Repository for machine readable AI system card

Send huggingface datasets to multiple endpoints, compare results. Great for gaurdrail analysis across multiple implementations/models.

Comprehensive LLM AI Model protection - cybersecurity toolset aligned to addressing OWASP vulnerabilities - https://genai.owasp.org/llm-top-10/

A cross-provider AI model security scanner that evaluates HuggingFace, OpenRouter, and Ollama models for malicious content, unsafe code, license issues, and known vulnerabilities. Includes automated reports and risk scoring.