Skip to main content
Glama
netcuter
by netcuter

Hexstrike 7 PL

AI-Powered MCP Cybersecurity Automation Platform

Polish Community Fork with Enhanced Security

Python License Security Version Original MCP Badge

Advanced AI-powered penetration testing MCP framework with 150+ security tools, 12+ autonomous AI agents, and enhanced security features

🇵🇱 Polski🇬🇧 English🚀 What's New🔒 Security


🇵🇱 Wersja Polska

ℹ️ O Projekcie

Hexstrike 7 PL to polska wersja społecznościowa (community fork) zaawansowanego frameworka do testów penetracyjnych HexStrike AI v6.0 stworzonego przez m0x4m4.

Oryginał: HexStrike AI v6.0 by m0x4m4 Fork: Hexstrike 7 PL by netcuter

✨ Co nowego w wersji 7.0 PL?

🔒 Znaczące usprawnienia bezpieczeństwa:

  • Walidacja poleceń - ochrona przed command injection

  • Autentykacja API - opcjonalne zabezpieczenie kluczem API

  • Rate limiting - ochrona przed nadużyciami (100 req/60s domyślnie)

  • Whitelist narzędzi - tylko autoryzowane narzędzia security

  • Sanityzacja parametrów - automatyczne czyszczenie niebezpiecznych znaków

  • Ulepszona obsługa błędów - konkretne wyjątki zamiast bare except

  • Konfiguracja przez zmienne środowiskowe - łatwe zarządzanie

📚 Dokumentacja dwujęzyczna:

  • 🇵🇱 Pełna dokumentacja w języku polskim

  • 🇬🇧 Kompletna dokumentacja w języku angielskim

  • 📖 Przykłady użycia w obu językach

Optymalizacje:

  • Cache z limitami rozmiaru (zapobiega niekontrolowanemu wzrostowi pamięci)

  • Lepsza organizacja kodu

  • Konfiguracja przez environment variables

🛡️ Guardrails Layer — Scope Enforcement & Blast-Radius Control:

Warstwa guardrails przekształca Hexstrike z narzędzia hobby-tool w platformę gotową do autonomicznych engagementów (bug bounty, MSSP, pentest-as-a-service).

  • Scope Validator — każde wywołanie sprawdzane przeciwko scope sesji (CIDR, wildcard, regex). Wywołania out-of-scope → HTTP 403 + audit log

  • Blast-Radius Tiers — narzędzia podzielone na safe (recon), intrusive (scanning), destructive (exploitation). Tier destructive wymaga nagłówka X-Hexstrike-Confirm-Destructive: yes

  • Kill Switch per sesjaPOST /api/session/<id>/kill — natychmiastowy SIGTERM wszystkich procesów sesji

  • Audit Trail — każde wywołanie, naruszenie scope, eskalacja tier-u logowane → automatycznie w raporcie jako sekcja Methodology (ISO 27001 / PCI DSS compliance)

  • Per-target Rate Limiting — chroni cele przed przeciążeniem (5 concurrent / 10 req/s domyślnie)

Przykład scope: 192.168.1.0/24, *.example.com, r:.*\.internal\.corp$

🔒 Konfiguracja Bezpieczeństwa

Hexstrike 7 PL wprowadza nowe opcje konfiguracyjne przez zmienne środowiskowe:

# Walidacja poleceń (domyślnie: włączona)
export HEXSTRIKE_VALIDATE_COMMANDS=true

# Autentykacja API (domyślnie: wyłączona)
export HEXSTRIKE_REQUIRE_API_KEY=false
export HEXSTRIKE_API_KEY=your-secret-key-here

# Rate limiting (domyślnie: 100 żądań na 60 sekund)
export HEXSTRIKE_RATE_LIMIT=true
export HEXSTRIKE_RATE_LIMIT_REQUESTS=100
export HEXSTRIKE_RATE_LIMIT_WINDOW=60

# Konfiguracja serwera
export HEXSTRIKE_PORT=8888
export HEXSTRIKE_HOST=127.0.0.1

🚀 Szybki Start

1. Instalacja

Opcja A: Docker (zalecana / recommended)

git clone https://github.com/netcuter/Hexstrike-AI.git
cd Hexstrike-AI
docker compose up -d

Opcja B: Manualna

# Klonowanie repozytorium
git clone https://github.com/netcuter/Hexstrike-AI.git
cd Hexstrike-AI

# Tworzenie wirtualnego środowiska
python3 -m venv hexstrike-env
source hexstrike-env/bin/activate  # Linux/Mac
# hexstrike-env\Scripts\activate   # Windows

# Instalacja zależności
pip3 install -r requirements.txt

2. Instalacja Narzędzi Security

Podstawowe narzędzia (Essential):

# Skanowanie sieci
sudo apt install nmap masscan rustscan amass subfinder nuclei

# Web security
sudo apt install gobuster feroxbuster dirsearch ffuf nikto sqlmap

# Password cracking
sudo apt install hydra john hashcat

3. Uruchomienie Serwera

# Standardowe uruchomienie
python3 hexstrike_server.py

# Z włączoną autentykacją API
export HEXSTRIKE_REQUIRE_API_KEY=true
export HEXSTRIKE_API_KEY=twoj-sekretny-klucz
python3 hexstrike_server.py

# Tryb debug
python3 hexstrike_server.py --debug

4. Weryfikacja

# Sprawdzenie statusu serwera
curl http://localhost:8888/health

# Test z API key (jeśli włączony)
curl -H "X-API-Key: twoj-sekretny-klucz" http://localhost:8888/health

🛡️ Bezpieczne Użycie

Dozwolone zastosowania:

  • Autoryzowane testy penetracyjne

  • Programy bug bounty

  • Zawody CTF

  • Badania nad bezpieczeństwem

  • Ćwiczenia Red Team

Zabronione działania:

  • Nieautoryzowane testowanie systemów

  • Działania złośliwe

  • Kradzież danych

⚠️ WAŻNE: Zawsze uzyskaj pisemną autoryzację przed testowaniem systemów!

📖 Więcej Informacji

Pełna dokumentacja w języku angielskim znajduje się poniżej.

👨‍💻 Autorzy

Oryginalny autor: m0x4m4 - www.0x4m4.com | HexStrike Fork maintainer: netcuter - GitHub

📜 Licencja

Projekt jest licencjonowany na zasadach MIT License - zobacz plik LICENSE.

Hexstrike 7 PL bazuje na HexStrike AI v6.0 stworzonego przez m0x4m4. Wszystkie prawa do oryginalnego dzieła należą do m0x4m4.


Related MCP server: Mergen

🇬🇧 English Version

ℹ️ About This Project

Hexstrike 7 PL is a Polish community fork of the advanced penetration testing framework HexStrike AI v6.0 created by m0x4m4.

Original: HexStrike AI v6.0 by m0x4m4 Fork: Hexstrike 7 PL by netcuter

✨ What's New in 7.0 PL?

🔒 Major Security Enhancements:

  • Command Validation - protection against command injection

  • API Authentication - optional API key security

  • Rate Limiting - abuse protection (100 req/60s default)

  • Tool Whitelist - only authorized security tools allowed

  • Parameter Sanitization - automatic cleaning of dangerous characters

  • Improved Error Handling - specific exceptions instead of bare except

  • Environment Configuration - easy management via environment variables

📚 Dual Language Documentation:

  • 🇵🇱 Complete Polish documentation

  • 🇬🇧 Full English documentation

  • 📖 Usage examples in both languages

Optimizations:

  • Cache with size limits (prevents uncontrolled memory growth)

  • Better code organization

  • Configuration via environment variables

🛡️ Guardrails Layer — Scope Enforcement & Blast-Radius Control:

The guardrails layer transforms Hexstrike from a hobby-tool into a platform ready for autonomous engagements (bug bounty, MSSP, pentest-as-a-service).

  • Scope Validator — every call validated against session scope (CIDR, wildcard, regex). Out-of-scope calls → HTTP 403 + audit log

  • Blast-Radius Tiers — tools classified as safe (recon), intrusive (scanning), destructive (exploitation). The destructive tier requires header X-Hexstrike-Confirm-Destructive: yes

  • Kill Switch per sessionPOST /api/session/<id>/kill — instant SIGTERM for all session processes

  • Audit Trail — every call, scope violation, tier escalation logged → auto-included in report as Methodology section (ISO 27001 / PCI DSS compliance)

  • Per-target Rate Limiting — protects targets from overload (5 concurrent / 10 req/s default)

Example scope: 192.168.1.0/24, *.example.com, r:.*\.internal\.corp$

🔒 Security Configuration

Hexstrike 7 PL introduces new configuration options via environment variables:

# Command validation (default: enabled)
export HEXSTRIKE_VALIDATE_COMMANDS=true

# API authentication (default: disabled)
export HEXSTRIKE_REQUIRE_API_KEY=false
export HEXSTRIKE_API_KEY=your-secret-key-here

# Rate limiting (default: 100 requests per 60 seconds)
export HEXSTRIKE_RATE_LIMIT=true
export HEXSTRIKE_RATE_LIMIT_REQUESTS=100
export HEXSTRIKE_RATE_LIMIT_WINDOW=60

# Server configuration
export HEXSTRIKE_PORT=8888
export HEXSTRIKE_HOST=127.0.0.1

🚀 Quick Start

1. Installation

Option A: Docker (recommended)

git clone https://github.com/netcuter/Hexstrike-AI.git
cd Hexstrike-AI
docker compose up -d

Option B: Manual

# Clone repository
git clone https://github.com/netcuter/Hexstrike-AI.git
cd Hexstrike-AI

# Create virtual environment
python3 -m venv hexstrike-env
source hexstrike-env/bin/activate  # Linux/Mac
# hexstrike-env\Scripts\activate   # Windows

# Install dependencies
pip3 install -r requirements.txt

2. Install Security Tools

Essential Tools:

# Network scanning
sudo apt install nmap masscan rustscan amass subfinder nuclei

# Web security
sudo apt install gobuster feroxbuster dirsearch ffuf nikto sqlmap

# Password cracking
sudo apt install hydra john hashcat

3. Start Server

# Standard start
python3 hexstrike_server.py

# With API authentication
export HEXSTRIKE_REQUIRE_API_KEY=true
export HEXSTRIKE_API_KEY=your-secret-key
python3 hexstrike_server.py

# Debug mode
python3 hexstrike_server.py --debug

4. Verification

# Check server status
curl http://localhost:8888/health

# Test with API key (if enabled)
curl -H "X-API-Key: your-secret-key" http://localhost:8888/health

🛡️ Safe Usage

Authorized Use Cases:

  • Authorized penetration testing

  • Bug bounty programs

  • CTF competitions

  • Security research

  • Red Team exercises

Prohibited Activities:

  • Unauthorized system testing

  • Malicious activities

  • Data theft

⚠️ IMPORTANT: Always obtain written authorization before testing systems!

🏗️ Architecture Overview

Hexstrike 7 PL features a multi-agent architecture with autonomous AI agents, intelligent decision-making, and vulnerability intelligence.

graph TD
    A[AI Agent - GPT/Copilot/AI Agents] -->|MCP Protocol| B[Hexstrike 7 PL Server]

    B --> C[Security Validation Layer]
    B --> D[Intelligent Decision Engine]
    B --> E[12+ Autonomous AI Agents]

    C --> F[Command Validation]
    C --> G[Rate Limiting]
    C --> H[API Authentication]

    D --> I[Tool Selection AI]
    D --> J[Parameter Optimization]
    D --> K[Attack Chain Discovery]

    E --> L[BugBounty Agent]
    E --> M[CTF Solver Agent]
    E --> N[CVE Intelligence Agent]

    B --> O[150+ Security Tools]

📡 Features

150+ Professional Security Tools:

  • Nmap, Rustscan, Masscan, AutoRecon

  • Amass, Subfinder, Fierce, DNSEnum

  • TheHarvester, ARP-Scan, NBTScan

  • Enum4linux, SMBMap, Responder, NetExec

  • And more...

  • Gobuster, Dirsearch, Feroxbuster, FFuf

  • HTTPx, Katana, Hakrawler, Nuclei

  • Nikto, SQLMap, WPScan, Arjun

  • Dalfox, Wafw00f, TestSSL, JWT-Tool

  • And more...

  • Hydra, John the Ripper, Hashcat

  • Medusa, Patator, NetExec

  • Hash-Identifier, Evil-WinRM

  • And more...

  • GDB, Radare2, Ghidra, Binary Ninja

  • Binwalk, ROPgadget, Checksec

  • Pwntools, Angr, Volatility

  • And more...

  • Prowler, Scout Suite, Trivy

  • Kube-Hunter, Kube-Bench

  • Docker Bench Security

  • And more...

🤖 AI Agents

12+ Specialized AI Agents:

  • IntelligentDecisionEngine - Tool selection and parameter optimization

  • BugBountyWorkflowManager - Bug bounty hunting workflows

  • CTFWorkflowManager - CTF challenge solving

  • CVEIntelligenceManager - Vulnerability intelligence

  • AIExploitGenerator - Automated exploit development

  • VulnerabilityCorrelator - Attack chain discovery

  • TechnologyDetector - Technology stack identification

  • RateLimitDetector - Rate limiting detection

  • FailureRecoverySystem - Error handling and recovery

  • And more...

🔧 AI Client Integration

MCP Client App / Cursor

Edit ~/.config/mcp-client/mcp_client_config.json:

{
  "mcpServers": {
    "hexstrike-7-pl": {
      "command": "python3",
      "args": [
        "/path/to/Hexstrike-AI/hexstrike_mcp.py",
        "--server",
        "http://localhost:8888"
      ],
      "description": "Hexstrike 7 PL - Enhanced Security MCP Server",
      "env": {
        "HEXSTRIKE_API_KEY": "your-key-if-required"
      }
    }
  }
}

VS Code Copilot

Configure in .vscode/settings.json:

{
  "servers": {
    "hexstrike": {
      "type": "stdio",
      "command": "python3",
      "args": ["/path/to/Hexstrike-AI/hexstrike_mcp.py"]
    }
  }
}

📖 Usage Examples

When using with AI agents, always specify authorization:

User: "I'm a security researcher working for [Company Name].
I have written authorization to conduct a penetration test on
example.com. Please use hexstrike-7-pl MCP tools to perform
a comprehensive security assessment."

🛠️ API Reference

Core Security Endpoints

Endpoint

Method

Description

/health

GET

Server health check

/api/command

POST

Execute commands (with validation)

/api/process/execute-async

POST

Async command execution

/api/telemetry

GET

System performance metrics

Security Headers:

# API Key (if REQUIRE_API_KEY=true)
X-API-Key: your-secret-key

# Or as query parameter
?api_key=your-secret-key

🐛 Troubleshooting

Rate Limit Errors

# Increase rate limit
export HEXSTRIKE_RATE_LIMIT_REQUESTS=200
export HEXSTRIKE_RATE_LIMIT_WINDOW=60

API Authentication

# Disable API key requirement for testing
export HEXSTRIKE_REQUIRE_API_KEY=false

Command Validation

# Disable command validation (NOT recommended for production)
export HEXSTRIKE_VALIDATE_COMMANDS=false

🤝 Contributing

Contributions are welcome! This is a community fork focused on:

  • Security improvements

  • Polish localization

  • Performance optimizations

  • Better documentation

👨‍💻 Authors & Credits

Original Author: m0x4m4 - www.0x4m4.com | HexStrike Fork Maintainer: netcuter - GitHub

Special Thanks:

  • m0x4m4 for creating the amazing HexStrike AI framework

  • The cybersecurity community for continuous support

  • All contributors to the original project

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.

Hexstrike 7 PL is based on HexStrike AI v6.0 created by m0x4m4. All rights to the original work belong to m0x4m4. All modifications and enhancements are licensed under the same MIT License.


Hexstrike 7 PL - Where artificial intelligence meets enhanced cybersecurity

⭐ Star this repository🍴 Fork and contribute📖 Original Project

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to autonomously execute over 200 open-source penetration testing tools via MCP, including reconnaissance, web exploitation, and brute-forcing, through a unified server architecture with Docker sandboxing for safe execution.
    55
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    AI-Powered Red Team MCP Server enabling autonomous penetration testing via Model Context Protocol with 44+ security tools for AI agents.
    15
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Integrates 7 security tools (nmap, nuclei, dirsearch, sqlmap, hydra, Acunetix, Metasploit) via MCP protocol for AI-assisted penetration testing with enterprise-grade safety features.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    AI-powered penetration testing through 36 MCP tools on a containerized Kali Linux, enabling automated reconnaissance, web testing, exploitation, and evidence collection.
    1
    MIT