phantom-secops

markl-a/phantom-secops

★ 0 stars Python AI/LLM Updated today

Multi-agent SecOps research playground — red/blue team simulation built on phantom-mesh. MCP server exposing recon/exploit/detect/respond tools to Claude Code, Cursor, or any MCP-compatible runtime.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "phantom-secops": {
      "command": "uvx",
      "args": [
        "phantom-secops"
      ]
    }
  }
}

Or install with pip: pip install phantom-secops

README Excerpt

> 唯讀、純文字、受治理的資安維運「大腦」,建構於多代理執行階段 [phantom-mesh](https://github.com/markl-a/phantom-mesh) 之上。兩件事:① 紅藍隊 SOC 概念展示(以 **MTTD** 對照),② 本機優先的端點自我健檢(主機姿態 / CVE / 入侵偵測 → 單一優先行動清單)。哲學:**不造引擎,造大腦**。 📄 完整文件(定位/快速上手/狀態+路線圖/OSS 方向/倫理紅線):見 **[docs/phantom-secops.md](docs/phantom-secops.md)** ｜倫理與法律界線:[ETHICS.md](ETHICS.md)

Topics

agent-frameworkai-agentanthropicblue-teamclaudedefensive-securitykill-chainllmmcp-servermttdmulti-agentnmapnucleiowasp-juice-shoppython

phantom-secops

Quick Install

README Excerpt

Topics

Related AI/LLM Servers