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.

CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

Watchtower is a simple AI-powered penetration testing automation CLI tool that leverages LLMs and LangGraph to orchestrate agentic workflows that you can use to test your websites locally. Generate useful pentest reports for your websites.

A user-friendly command-line toolkit for WiFi network scanning, handshake capture, and vulnerability reporting—compatible with Termux (Android), Kali Linux, and WSL. For ethical hacking, learning, and authorized penetration testing only.

CyberX-AI-Digital-Twin is an AI-powered cybersecurity platform that uses digital twin technology to simulate, detect, and analyze cyber threats in a safe, isolated environment. Ideal for researchers, developers, and educators to test and enhance network security.

⚙️ Enable AI agents to conduct autonomous penetration testing on any Linux distribution with a persistent and robust Model Context Protocol server.

Mergen is an MCP server that gives your AI a real red team brain. It doesn't just run tools, it picks the right ones, chains them together, and actually makes sense of the output. Built by pentesters, for pentesters who are tired of babysitting scripts.

AAPP‑MART is an AI-Autonomous Attack Path Prediction & Multi‑Agent Red Team Simulation Engine designed for attack simulation, automated threat modeling, adversary emulation, and enterprise‑grade cybersecurity validation aligned with MITRE ATT&CK.

Proof-of-concept for persistent manipulation of LLM outputs by modifying quantized weights in a GGUF model file while the inference server is running

Scorton is an open-source behavioral cybersecurity framework that makes human trust measurable and programmable. Built with Rust, Python and NodeJS it helps developers and security teams predict, score, and improve human-driven cyber risk and awareness.

🔍 Automate research tasks with the Autonomous Research Agent, utilizing intelligent queries and parallel searches to create concise, comprehensive reports.

An awesome list of resources on AI cyber deception, exploring adversarial machine learning techniques used to deceive and secure systems

Collect and download benign Windows PE executables from marketplace sources for research and machine learning

🐻 BearStrike AI: High-Signal Pentesting Console (MCP-First, Model-Agnostic). Build fast, low-noise security workflows with queue-first execution, skills-aware planning, and 150+ integrated tools.

🤖 Build advanced AI agents with a collection of production-ready applications using modern frameworks for single and multi-agent systems.

Common Attack Pattern Enumerations and Classifications (CAPEC™) - AI-RAG

🍯 Discover AI-driven deception resources, including honeypots, datasets, and research, to enhance your defense against cyber threats and adversarial attacks.

Lightweight AI coding CLI — local-first (oMLX), cloud-ready with automated but configurable bechmarks

SentinelScan is a web-based, AI-powered Automated Reconnaissance and Vulnerability Reporting platform. Users input a target domain and receive a structured, AI-generated security report in under 20 seconds.