hexstrike-ai - HexStrike AI MCP Agents是一款高级MCP服务器

项目说明

<di="center">

<img src="assets/hexstrike-logo.png" alt="HexStrike AI Logo" width="220" style="margin-bottom: 20px;"/>

HexStrike AI MCP Agents v6.0

AI-Powered MCP Cybersecurity Automation Platform

![Python]()
![Security]()
![MCP]()
![]()
![Tools]()
![Agents]()
![Stars]()

Ad AI-powered penetration testing MCP 框架 with 150+ security tools and 12+ autonomous AI agents

Owned & de by OTT Cybersecurity LLC

📋 What's New • 🏗️ Architecture • 🚀 Installation • 🛠️ Features • 🤖 AI Agents • 📡 API Reference

</div>

---

<di="center">

Follow Our Social Accounts

<p align="center">
<a href="
<img src=" alt="Join our Discord" />
</a>
&nbsp;&nbsp;
<a href="
<img src=" alt="Follow us on LinkedIn" />
</a>
</p>

</div>

---

Architecture O

HexStrike AI MCP v6.0 features a multi-agent architecture with autonomous AI agents, intelligent decision-making, and intelligence.

How It Works

1. AI Agent Connection - Claude, GPT, or other MCP-compatible agents connect 协议
2. Intelligent Analysis - Decision 引擎 analyzes targets and selects optimal testing strategies
3. Autonomous Execution - AI agents execute comprehensi assessments
4. Real-time Adaptation - System adapts based on results and discovered
5. Ad Reporting - output with cards and risk analysis

---

Installation

Quick Setup to Run the hexstrike MCPs 服务端

Installation and Setting Up Guide for AI Clients:

#### Installation & Demo Video

Watch the full installation and setup walkthrough here: YouTube - HexStrike AI Installation & Demo

#### Supported AI Clients for Running & Integration

You can install and run HexStrike AI MCPs with AI clients, including:

5ire (Latest v0.14.0 not supported for now)

VS Code Copilot

Roo Code

Cursor

Claude Desktop

Any MCP-compatible agent

Refer to the video above for step-by-step instructions and integration examples for these platforms.

Install Security Tools

Core Tools (Essential):

Cloud Security Tools:

Browser Agent Requirements:

Start the Server

Installation

---

AI Client Integration Setup

Claude Desktop Integration or Cursor

Edit ~/.config/Claude/claude_desktop_config.json:

VS Code Copilot Integration

Configure VS Code settings in ./settings.json:

---

Features

Security Tools Arsenal

150+ Professional Security Tools:

<details>
<summary><b>🔍 网络 Reconnaissance & Scanning (25+ Tools)</b></summary>

Nmap - Ad port scanning with custom NSE scripts and service detection

Rustscan - Ultra-fast port scanner with intelligent rate limiting

Masscan - High-speed Internet-scale port scanning with banner grabbing

AutoRecon - Comprehensi reconnaissance with 35+ parameters

Amass - Ad subdomain enumeration and OSINT gathering

Subfinder - Fast passi discovery with multiple sources

Fierce - DNS reconnaissance and zone transfer testing

DNSEnum - DNS information gathering and subdomain brute forcing

TheHar - Email and subdomain har from multiple sources

ARP-Scan - Network discovery using ARP requests

NBTScan - NetBIOS name scanning and enumeration

RPCClient - RPC enumeration and null session testing

Enum4linux - SMB enumeration with user, group, and share discovery

Enum4linux-ng - Ad SMB enumeration with enhanced logging

SMBMap - SMB share enumeration and exploitation

Responder - LLMNR, NBT-NS and MDNS poisoner for credential har

NetExec - 网络 service exploitation 框架 (formerly CrackMapExec)

</details>

<details>
<summary><b>🌐 Web Application Security Testing (40+ Tools)</b></summary>

Gobuster - Directory, file, and DNS enumeration with intelligent wordlists

Dirsearch - Ad directory and file discovery with enhanced logging

Feroxbuster - Recursi discovery with intelligent filtering

FFuf - Fast web fuzzer with ad filtering and parameter discovery

Dirb - Comprehensive web content scanner with recursi

HTTPx - Fast HTTP probing and technology detection

Katana - Next-generation crawling and spidering with Ja support

Hakrawler - Fast web endpoint discovery and crawling

Gau - Get All URLs from multiple sources (Wayback, Common Crawl, etc.)

Waybackurls - Historical URL discovery from Wayback Machine

Nuclei - Fast scanner with 4000+ templates

Nikto - Web ser scanner with comprehensi

SQLMap - Ad automatic SQL injection testing with tamper scripts

WPScan - WordPress security scanner with 数据库

Arjun - HTTP parameter discovery with intelligent fuzzing

ParamSpider - Parameter mining from web archives

X8 - Hidden parameter discovery with ad techniques

Jaeles - Ad scanning with custom signatures

Dalfox - Ad XSS scanning with DOM analysis

Wafw00f - Web application firewall fingerprinting

TestSSL - SSL/TLS configuration testing and assessment

SSLScan - SSL/TLS cipher suite enumeration

SSLyze - Fast and comprehensive SSL/TLS configuration analyzer

Anew - Append new lines to files for efficient data processing

QSReplace - Query string parameter replacement for systematic testing

Uro - URL filtering and deduplication for efficient testing

Whatweb - Web technology identification with fingerprinting

JWT-Tool - JSON Web Token testing with algorithm confusion

GraphQL- - GraphQL schema exploration and introspection testing

Burp Suite Extensions - Custom extensions for ad web testing

ZAP Proxy - OWASP ZAP integration for automated security scanning

Wfuzz - Web application fuzzer with ad payload generation

Commix - Command injection exploitation 工具 with automated detection

NoSQLMap - NoSQL injection testing for MongoDB, CouchDB, etc.

Tplmap - Ser template injection exploitation 工具

🌐 Ad Browser Agent:

Headless Chrome Automation - Full Chrome browser automation with Selenium

Screenshot Capture - Automated screenshot generation for inspection

DOM Analysis - Deep DOM tree analysis and Ja execution monitoring

Network Traffic Monitoring - Real-time 网络 request/response logging

Security Header Analysis - Comprehensi header

Form Detection & Analysis - Automatic form discovery and input field analysis

Ja Execution - Dynamic content analysis with full Ja support

Proxy Integration - Seamless integration with Burp Suite and other proxies

Multi-page Crawling - Intelligent web application spidering and mapping

Performance Metrics - Page load times, resource usage, and optimization insights

</details>

<details>
<summary><b>🔐 Authentication & Password Security (12+ Tools)</b></summary>

Hydra - 网络 login cracker supporting 50+ protocols

John the Ripper - Ad password hash cracking with custom rules

Hashcat - World's fastest password recovery 工具 with GPU acceleration

Medusa - Speedy, parallel, modular login brute-forcer

Patator - Multi-purpose brute-forcer with ad modules

NetExec - Swiss army knife for pentesting networks

SMBMap - SMB share enumeration and exploitation 工具

E - Windows Remote Management shell with PowerShell integration

Hash-Identifier - Hash type identification tool

HashID - Ad hash algorithm identifier with confidence scoring

CrackStation - Online hash lookup integration

Ophcrack - Windows password cracker using rainbow tables

</details>

<details>
<summary><b>🔬 Binary Analysis & Reverse Engineering (25+ Tools)</b></summary>

GDB - GNU Debugger with Python scripting and exploit de support

GDB-PEDA - Python Exploit De Assistance for GDB

GDB-GEF - GDB Enhanced Features for exploit de

Radare2 - Ad reverse engineering 框架 with comprehensi

Ghidra - NSA's software reverse engineering suite with headless analysis

IDA Free - Interacti with ad analysis capabilities

Binary Ninja - Commercial reverse engineering platform

Binwalk - Firmware analysis and extraction 工具 with recursi

ROPgadget - ROP/JOP gadget finder with ad search capabilities

Ropper - ROP gadget finder and exploit de tool

One-Gadget - Find one-shot RCE gadgets in libc

Checksec - Binary security property checker with comprehensi

Strings - Extract printable strings from binaries with filtering

Objdump - Display object file information with Intel syntax

Readelf - ELF file analyzer with detailed header information

XXD - Hex dump utility with ad formatting

Hexdump - Hex and editor with customizable output

Pwntools - CTF framework and exploit de library

Angr - Binary analysis platform with symbolic execution

Libc-Database - Libc identification and offset lookup 工具

Pwninit - Automate binary exploitation setup

- Ad memory forensics framework

MSFVenom - Metasploit payload generator with ad encoding

UPX - Executable packer/unpacker for binary analysis

</details>

<details>
<summary><b>☁️ Cloud & Container Security (20+ Tools)</b></summary>

Prowler - AWS/Azure/GCP security assessment with compliance checks

Scout Suite - Multi-cloud security auditing for AWS, Azure, GCP, Alibaba Cloud

CloudMapper - AWS network and security analysis

Pacu - AWS exploitation 框架 with comprehensi

Trivy - Comprehensi scanner for containers and IaC

Clair - Container analysis with detailed C

Kube-Hunter - Kubernetes penetration testing with acti modes

Kube-Bench - CIS Kubernetes benchmark checker with remediation

Docker Bench Security - Docker security assessment following CIS benchmarks

Falco - Runtime security monitoring for containers and Kubernetes

Checkov - Infrastructure as 代码 security scanning

Terrascan - Infrastructure security scanner with policy-as-代码

CloudSploit - Cloud security scanning and monitoring

AWS CLI - Amazon Web Services command line with security operations

Azure CLI - Microsoft Azure command line with security assessment

GCloud - Google Cloud Platform command line with security tools

Kubectl - Kubernetes command line with security context analysis

Helm - Kubernetes package manager with security scanning

Istio - Service mesh security analysis and configuration assessment

OPA - Policy 引擎 for cloud-nati and compliance

</details>

<details>
<summary><b>🏆 CTF & Forensics Tools (20+ Tools)</b></summary>

- Ad memory forensics 框架 with comprehensi

- Next-generation memory forensics with enhanced analysis

Foremost - File carving and data recovery with signature-based detection

PhotoRec - File recovery software with ad carving capabilities

TestDisk - Disk partition recovery and repair tool

Steghide - Steganography detection and extraction with password support

Stegsolve - Steganography analysis 工具 with inspection

Zsteg - PNG/BMP steganography detection tool

Outguess - Uni steganographic tool for JPEG images

ExifTool - Metadata reader/writer for file formats

Binwalk - Firmware analysis and reverse engineering with extraction

Scalpel - File carving 工具 with configurable headers and footers

Bulk Extractor - Digital forensics 工具 for extracting features

Autopsy - Digital forensics platform with timeline analysis

Sleuth Kit - Collection of command-line digital forensics tools

Cryptography & Hash Analysis:

John the Ripper - Password cracker with custom rules and ad modes

Hashcat - GPU-accelerated password recovery with 300+ hash types

Hash-Identifier - Hash type identification with confidence scoring

CyberChef - Web-based analysis toolkit for encoding and encryption

Cipher-Identifier - Automatic cipher type detection and analysis

Frequency-Analysis - Statistical cryptanalysis for substitution ciphers

RSATool - RSA key analysis and common attack implementations

FactorDB - Integer factorization 数据库 for cryptographic challenges

</details>

<details>
<summary><b>🔥 Bug Bounty & OSINT Arsenal (20+ Tools)</b></summary>

Amass - Ad subdomain enumeration and OSINT gathering

Subfinder - Fast passi discovery with API integration

Hakrawler - Fast web endpoint discovery and crawling

HTTPx - Fast and multi-purpose HTTP toolkit with technology detection

ParamSpider - Mining parameters from web archives

Aquatone - inspection of websites across hosts

Subjack - Subdomain takeo checker

DNSEnum - DNS enumeration script with zone transfer capabilities

Fierce - Domain scanner for locating targets with DNS analysis

TheHar - Email and subdomain har from multiple sources

Sherlock - Username in across 400+ social networks

Social-Analyzer - Social media analysis and OSINT gathering

Recon-ng - Web reconnaissance 框架 with modular architecture

Maltego - Link analysis and data mining for OSINT in

SpiderFoot - OSINT automation with 200+ modules

Shodan - Internet-connected device search with ad filtering

Censys - Internet asset discovery with certificate analysis

Have I Been Pwned - Breach data analysis and credential exposure

Pipl - People search 引擎 integration for identity in

TruffleHog - Git repository secret scanning with entropy analysis

</details>

AI Agents

12+ Specialized AI Agents:

IntelligentDecisionEngine - 工具 selection and parameter optimization

BugBountyWorkflowManager - Bug bounty hunting workflows

CTFWorkflowManager - CTF challenge solving

C - intelligence

AIExploitGenerator - Automated exploit de

- Attack chain discovery

TechnologyDetector - Technology stack identification

RateLimitDetector - Rate limiting detection

FailureReco - Error handling and recovery

PerformanceMonitor - System optimization

ParameterOptimizer - Context-aware optimization

GracefulDegradation - Fault-tolerant operation

Ad Features

Smart Caching System - Intelligent result caching with LRU e

Real-time Process Management - Li control and monitoring

Intelligence - C and exploit analysis

Browser Agent - Headless Chrome automation for web testing

API Security Testing - GraphQL, JWT, REST API security assessment

Modern Engine - Real-time dashboards and progress tracking

---

API Reference

Core System Endpoints

| Endpoint | Method | Description |
|----------|--------|-------------|
| /health | GET | Ser check with tool a |
| /api/command | POST | Execute arbitrary commands with caching |
| /api/telemetry | GET | System performance metrics |
| /api/cache/stats | GET | Cache performance statistics |
| /api/intelligence/analyze-target | POST | AI-powered target analysis |
| /api/intelligence/select-tools | POST | Intelligent tool selection |
| /api/intelligence/optimize-parameters | POST | Parameter optimization |

Common MCP Tools

Network Security Tools:

nmap_scan() - Ad Nmap scanning with optimization

rustscan_scan() - Ultra-fast port scanning

masscan_scan() - High-speed port scanning

autorecon_scan() - Comprehensi

amass_enum() - Subdomain enumeration and OSINT

Web Application Tools:

gobuster_scan() - Directory and file enumeration

feroxbuster_scan() - Recursi discovery

ffuf_scan() - Fast web fuzzing

nuclei_scan() - scanning with templates

sqlmap_scan() - SQL injection testing

wpscan_scan() - WordPress security assessment

Binary Analysis Tools:

ghidra_analyze() - Software reverse engineering

radare2_analyze() - Ad reverse engineering

gdb_debug() - GNU debugger with exploit de

pwntools_exploit() - CTF framework and exploit de

angr_analyze() - Binary analysis with symbolic execution

Cloud Security Tools:

prowler_assess() - AWS/Azure/GCP security assessment

scout_suite_audit() - Multi-cloud security auditing

tri() - Container scanning

kube_hunter_scan() - Kubernetes penetration testing

kube_bench_check() - CIS Kubernetes benchmark assessment

Process Management

| Action | Endpoint | Description |
|--------|----------|-------------|
| List Processes | GET /api/processes/list | List all acti |
| Process Status | GET /api/processes/status/<pid> | Get detailed process information |
| Terminate | POST /api/processes/terminate/<pid> | Stop specific process |
| Dashboard | GET /api/processes/dashboard | Li dashboard |

---

Usage Examples

When writing your prompt, you generally can't start with just a simple "i want you to penetration test site X.com" as the LLM's are generally setup with some level of ethics. You therefore need to begin with describing your role and the relation to the site/task you have. For example you may start by telling the LLM how you are a security researcher, and the site is owned by you, or your company. You then also need to say you would like it to specifically use the hexstrike-ai MCP tools.
So a complete example might be:

Real-World Performance

| Operation | Traditional Manual | HexStrike v6.0 AI | Impro |
|-----------|-------------------|-------------------|-------------|
| Subdomain Enumeration | 2-4 hours | 5-10 minutes | 24x faster |
| Scanning | 4-8 hours | 15-30 minutes | 16x faster |
| Web App Security Testing | 6-12 hours | 20-45 minutes | 18x faster |
| CTF Challenge Solving | 1-6 hours | 2-15 minutes | 24x faster |
| Report Generation | 4-12 hours | 2-5 minutes | 144x faster |

Success Metrics

Detection Rate: 98.7% (vs 85% manual testing)

False Positive Rate: 2.1% (vs 15% traditional scanners)

Attack Co: 95% (vs 70% manual testing)

CTF Success Rate: 89% (vs 65% human expert a)

Bug Bounty Success: 15+ high-impact discovered in testing

---

HexStrike AI v7.0 - Release Coming Soon!

Key Impro & New Features

Streamlined Installation Process - One-command setup with automated dependency management

Docker Container Support - Containerized deployment for consistent en

250+ Specialized AI Agents/Tools - Expanded from 150+ to 250+ autonomous security agents

Nati Client - Full-featured Application (www.hexstrike.com)

Ad Web Automation - Enhanced Selenium integration with anti-detection

Ja Runtime Analysis - Deep DOM inspection and dynamic content handling

Memory Optimization - 40% reduction in resource usage for large-scale operations

Enhanced Error Handling - Graceful degradation and automatic recovery mechanisms

Bypassing Limitations - Fixed limited allowed mcp tools by MCP clients

---

Troubleshooting

Common Issues

1. MCP Connection Failed:

2. Security Tools Not Found:

3. AI Agent Cannot Connect:

Debug Mode

Enable debug mode for detailed logging:

---

Security Considerations

⚠️ Important Security Notes:

This 工具 provides AI agents with powerful system access

Run in isolated en or dedicated security testing VMs

AI agents can execute arbitrary security tools - ensure proper o

Monitor AI agent acti through the real-time dashboard

Consider implementing authentication for production deployments

Legal & Ethical Use

✅ Authorized Penetration Testing - With proper written authorization

✅ Bug Bounty Programs - Within program scope and rules

✅ CTF Competitions - Educational and competiti

✅ Security Research - On owned or authorized systems

✅ Red Team Exercises - With organizational approval

❌ Unauthorized Testing - Never test systems without permission

❌ Malicious Acti - No illegal or harmful acti

❌ Data Theft - No unauthorized data access or exfiltration

---

Contributing

We welcome contributions from the cybersecurity and AI community!

De Setup

Priority Areas for Contribution

🤖 AI Agent Integrations - Support for new AI platforms and agents

🛠️ Security Tool Additions - Integration of additional security tools

⚡ Performance Optimizations - Caching impro and scalability enhancements

📖 Documentation - AI usage examples and integration guides

🧪 Testing Frameworks - Automated testing for AI agent interactions

---

License

MIT License - see LICENSE file for details.

---

Author

m0x4m4 - www.0x4m4.com | HexStrike

---

Owned & De By

<p align="center">
<strong>HexStrike AI is owned and de by OTT Cybersecurity LLC</strong>
</p>

<p align="center">
<a href="
<img src="assets/ott-logo.png" alt="OTT Cybersecurity LLC Logo" width="150" />
</a>
</p>

<p align="center">
<a href="
<img src=" alt="Visit o.ae" />
</a>
</p>

---

Official Sponsor

<p align="center">
<strong>Sponsored By LeaksAPI - Live Dark Web Data leak checker</strong>
</p>

<p align="center">
<a href="
<img src="assets/leaksapi-logo.png" alt="LeaksAPI Logo" width="150" />
</a>
&nbsp;&nbsp;&nbsp;&nbsp;
<a href="
<img src="assets/leaksapi-banner.png" alt="LeaksAPI Banner" width="450" />
</a>
</p>

<p align="center">
<a href="
<img src=" alt="Visit leak-check.net" />
</a>
</p>

---

<di="center">

🌟 Star History

![Star History Chart]()

📊 Project Statistics

150+ Security Tools - Comprehensi testing arsenal

12+ AI Agents - Autonomous decision-making and workflow management

4000+ Templates - Nuclei integration with extensi

35+ Attack Categories - From web apps to cloud infrastructure

Real-time Processing - Sub-second response times with intelligent caching

99.9% Uptime - Fault-tolerant architecture with graceful degradation

🚀 Ready to Transform Your AI Agents?

⭐ Star this repository • 🍴 Fork and contribute • 📖 Read the docs

---

Made with ❤️ by the cybersecurity community for AI-powered security automation

*HexStrike AI v6.0 - Where artificial intelligence meets cybersecurity excellence*

</div>

项目信息

开发语言：Python

Star 数：12399

技术要点

该项目属于黑客技术方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕HexStrike AI MCP Agents is an ad MCP 服务端 that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensi capabilities.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。