0x4m4/hexstrike-ai

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.

What it solves

HexStrike AI 是一個資安自動化平台，簡化複雜的滲透測試與安全評估。它透過提供統一框架，讓 AI 代理人能自主選擇工具、最佳化參數並執行攻擊鏈，解決了手動協調數十種不同安全工具的問題。

How it works

平台採用基於 Model Context Protocol (MCP) 的多代理人架構。它透過 FastMCP 伺服器連接 AI 客戶端（如 Claude、GPT 或 Cursor）。「Intelligent Decision Engine」會分析目標並選擇最佳策略，然後由專門的自主代理人（如 BugBounty、CTF 或 CVE Intelligence 代理人）執行。這些代理人可使用超過 150 種整合的安全工具，涵蓋網路、Web、雲端與二進位分析領域。

Who it’s for

此平台設計給滲透測試人員、漏洞賞金獵人、CTF（Capture The Flag）玩家與想要自動化偵測與利用階段的安全研究人員。

Highlights

  • Massive Tool Integration: Access to 150+ professional tools including Nmap, SQLMap, Nuclei, and Ghidra.
  • Autonomous Agents: 12+ specialized agents for tasks like exploit generation and vulnerability intelligence.
  • MCP Compatible: Integrates directly with AI clients like Claude Desktop, VS Code Copilot, and Cursor.
  • Advanced Browser Agent: Features headless Chrome automation for DOM analysis, screenshot capture, and network traffic monitoring.
  • Multi-Domain Coverage: Supports network reconnaissance, web app security, cloud/container auditing, and binary reverse engineering.