ИИ-агенты
apify-mcp-server
MCP server that lets AI agents run thousands of Apify Store scrapers and crawlers as tools.
★ 10,1 тыс. звёздMIT
Смотреть руководство →// agents · 0x4m4/hexstrike-ai
hexstrike-ai
hexstrike-ai — проект с открытым исходным кодом из категории «ИИ-агенты» от 0x4m4 (0x4m4/hexstrike-ai на GitHub). У него 12 532 звезды на GitHub и 2 549 форков, он распространяется по лицензии MIT и последний раз обновлялся на GitHub 3 августа 2026.
MCP server letting AI agents run 150+ cybersecurity tools for authorized pentesting and research.
★ 12,5 тыс. звёзд⑂ 2,5 тыс. форковMITобновлено авг. 2026
▦ визуал — в README этого проекта нет встраиваемого скриншота,
поэтому здесь заглушка. Руководство ниже в любом случае полное.
поэтому здесь заглушка. Руководство ниже в любом случае полное.
// факты о проекте
Факты о проекте
- Репозиторий
- 0x4m4/hexstrike-ai
- Звёзды GitHub
- 12 532
- Форки
- 2 549
- Лицензия
- MIT
- Последнее обновление на GitHub
- 3 августа 2026
- Категория
- ИИ-агенты
- Тип страницы
- Полное руководство по установке
- Официальный сайт
- Official site
// как это работает
Как это работает
- Confirm authorization and isolation
Only test systems you own or have written authorization for, and plan to run HexStrike in a dedicated security-testing VM, as the README advises.
- Set up the environment
Clone the repo on a Kali Linux-style machine, create a virtualenv, install the Python requirements, and make sure the security tools you need are installed.
- Start the server
Run hexstrike_server.py (add --debug for detailed logs) and verify it is listening on port 8888.
- Connect your AI agent and scope a task
Point your MCP client at hexstrike_mcp.py, then describe an authorized assessment - for example network scanning or web application testing on your own site - and monitor activity in the dashboard.
// возможности
Почему его любят
150+ integrated security tools
One MCP interface fronts a comprehensive arsenal for network scanning, web testing, vulnerability assessment and more, across 35+ attack categories.
12+ autonomous AI agents
Specialized agents make decisions and manage workflows, chaining tools together for complete assessments.
Thousands of vulnerability templates
Nuclei integration with 4000+ templates gives broad, current vulnerability coverage.
Real-time monitoring
A live process dashboard (via the server's API) lets you watch, inspect and terminate agent-run processes.
Process and error management
The server tracks running processes and includes debug modes and troubleshooting tooling for MCP connections and missing binaries.
Built for Kali-style environments
Designed around the standard penetration-testing toolset, with checks such as which nmap/gobuster/nuclei to verify tool availability.
Advertisement
// запустите сами
Запустите сами
- Clone the repository
Clone HexStrike AI and enter the project directory.
git clone https://github.com/0x4m4/hexstrike-ai.git cd hexstrike-ai - Install dependencies
Create a virtual environment and install the Python requirements; install the underlying security tools (nmap, nuclei, etc.) from their official sources.
python3 -m venv hexstrike-dev source hexstrike-dev/bin/activate pip install -r requirements.txt - Start the server
Launch the HexStrike server, then configure your MCP client to run hexstrike_mcp.py so your agent can call the tools.
python3 hexstrike_server.py --port 8888 --debug
// сценарии использования
Что можно создать
- Running an authorized penetration test of your own company's website with an AI agent driving the tools.
- Automating reconnaissance and vulnerability scanning within a bug bounty program's scope.
- Solving CTF challenges in a lab environment with agent assistance.
- Red-team exercises in an isolated VM with organizational approval and dashboard oversight.
Advertisement
// вопросы и ответы
Вопросы и ответы
Who maintains HexStrike AI?
It was created by 0x4m4 and is owned and developed by OTT Cybersecurity LLC, with community contributions.
Is it free to use?
Yes, it is MIT-licensed. Legal and ethical use is limited to authorized testing, bug bounties within scope, CTFs and research on systems you own - the README is explicit about this.
Does it need a paid API key?
The server itself does not; the AI agent you connect (Claude, GPT, Copilot, etc.) uses your own subscription or API key.
How does HexStrike compare with PentestGPT?
PentestGPT is an agent framework that drives general coding-agent backends through a staged pipeline; HexStrike is an MCP tool server that exposes 150+ installed security tools to whichever MCP-capable agent you already use.
How do I get started?
On a Kali-style VM, clone the repo, pip install -r requirements.txt, run python3 hexstrike_server.py, and connect your MCP client via hexstrike_mcp.py.
// продолжить изучение
Похожие инструменты
ИИ-агенты
MobileBuildMCP
An MCP server and CLI that lets AI agents build, test and run iOS and macOS projects.
★ 6,5 тыс. звёздMIT
Смотреть руководство →ИИ-агенты
deep-research
Deep Research with any LLM: in-depth reports in minutes, with an SSE API and MCP server built in
★ 4,7 тыс. звёздMIT
Смотреть руководство →ИИ-агенты
excel-mcp-server
Excel MCP Server: let AI agents read, write, format, and chart real .xlsx workbooks — no Excel required
★ 4,2 тыс. звёздMIT
Смотреть руководство →ИИ-агенты
chrome-devtools-mcp
Chrome DevTools for coding agents: an MCP server that lets agents debug and inspect real Chrome
★ 53,1 тыс. звёздApache-2.0
Смотреть руководство →ИИ-агенты
matlab-mcp-server
Official MathWorks MCP server: drive MATLAB from AI coding agents.
★ 1,6 тыс. звёздNOASSERTION
Смотреть руководство →// альтернативы
Альтернативы: ИИ-агенты
Другие проекты из категории «ИИ-агенты» с наибольшим числом звёзд в каталоге LibreAI — реалистичный список альтернатив, если hexstrike-ai вам не подходит.
- openclaw★ 391,6 тыс.
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294,9 тыс.
An agentic skills framework & software development methodology that works.
- ECC★ 275,2 тыс.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252,0 тыс.
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245,5 тыс.
DeepSeek's plugin-based agent harness where everything is a plugin.
// ещё в категории agents
Больше проектов: ИИ-агенты
Соседние проекты из категории «ИИ-агенты» в каталоге, ближайшие по числу звёзд к hexstrike-ai — продолжайте изучать полку по обе стороны от него.
- ida-pro-mcp★ 12,5 тыс.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
- bisheng★ 12,0 тыс.
Enterprise LLM app platform: GenAI workflows, RAG, agents, model management, evaluation, fine-tuning.
- EverOS★ 13,4 тыс.
One portable, local-first memory layer for every AI agent - Markdown-native, user-owned and self-evolving.
- MemOS★ 11,8 тыс.
Self-evolving memory OS for LLMs and agents: persistent graph memory, hybrid retrieval, skill reuse.
- typescript-sdk★ 13,5 тыс.
The official TypeScript SDK for Model Context Protocol servers and clients.
- phoenix★ 11,7 тыс.
Observability and evaluation for AI apps — see what your agents do.
Получить hexstrike-ai
Бесплатно и открыто — забирайте исходный код, ставьте звезду репозиторию и начинайте создавать.