Kali Security MCP — Security skill for Claude Code
连接kali linux与ClaudeCode等主流大模型进行全面CTF挑战及渗透测试的MCP,附带192个kali渗透工具,只要你有大模型,就能搞全面渗透.
How to install Kali Security MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open SeaC-25/Kali-Security-MCP and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Kali Security MCP does
连接kali linux与ClaudeCode等主流大模型进行全面CTF挑战及渗透测试的MCP,附带192个kali渗透工具,只要你有大模型,就能搞全面渗透.
Alternatives in Security
- Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★
- Trail Of Bits Claude-code-config — Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c 1.6k ★
- Cve MCP Server — Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS sco 1.2k ★
README
Kali MCP Server
    
**🤖 AI 驱动的智能渗透测试框架**
*通过 MCP 协议将 193 个 Kali Linux 安全工具与 AI 无缝集成*
[English](#english) | [中文](#中文)
中文
🎯 简介
Kali MCP Server 是一个基于 Model Context Protocol (MCP) 的智能安全测试框架(**v6.0**),将 Kali Linux 的 **200+ 个**专业安全工具与 AI 助手(如 Claude)深度集成。支持自动化渗透测试、CTF 竞赛解题、漏洞评估等场景。
✨ 核心特性
| 特性 | 说明 |
|---|---|
| 200+ 安全工具 | 涵盖信息收集、漏洞扫描、密码攻击、Web 测试、PWN 等 |
| 声明式工具注册表 | v6.0 重构:消灭 elif 地狱,统一工具路由 |
| 结构化输出解析 | Nmap/Gobuster/Nuclei 等关键工具结果智能解析 |
| 多智能体协作 | 19 个复杂工具通过 Agent 协作执行,支持任务分发 |
| CTF 竞赛模式 | 自动 Flag 检测,Web/PWN/Crypto/Misc 全类型一键解题 |
| APT 攻击模拟 | 完整的 MITRE ATT&CK 框架支持,自适应攻击链 |
| Session 生命周期管理 | TTL 自动过期(4h),后台清理,防内存泄漏 |
| 本地执行模式 | 无需额外后端服务器,直接调用系统工具 |
| PWN 自动化 | 集成 pwnpasi:ROP 分析、堆漏洞检测、符号执行、模糊测试 |
📁 项目结构
MCP-Kali-Server/
├── mcp_server.py # 主 MCP 服务器入口
├── kali_mcp/
│ ├── core/ # 核心引擎 (50+ 模块)
│ │ ├── local_executor.py # 本地命令执行器
│ │ ├── tool_registry.py # v6.0 声明式工具注册表
│ │ ├── tool_router.py # 工具路由器
│ │ ├── output_parsers/ # 结构化输出解析器
│ │ ├── session.py # 会话管理 (TTL/自动清理)
│ │ ├── hybrid_decision_engine.py # 混合决策引擎
│ │ ├── agent_coordinator.py # 多智能体协调器
│ │ ├── ctf_agent_framework.py # CTF 多 Agent 框架
│ │ ├── react_engine.py # ReAct 推理引擎
│ │ └── llm_brain.py # LLM 自主决策
│ ├── mcp_tools/
Related Skills
Mr Robot
An ADR-driven security framework for Kali — a HackTheBox co-pilot orchestrating Hat-persona Claude agents acro
Kali Pentest
Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 s
Web Pentest
An experimental Claude Code skill for orchestrating authorized web application penetration tests on Kali Linux
MCP Security Checklist (SlowMist)
Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening.
Google MCP Security Servers
Security Operations and Threat Intelligence MCP servers.
Agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Related Agents
Fleet Ops
Use PROACTIVELY and automatically — do not wait to be asked — for macOS + Kali fleet operations: SSH, liveness
Box
System and config assistant for chryzsh's Kali VM. Use for "fix my tmux/zshrc/shell config", dotfiles changes,
Genesis Security Reviewer
Security-reviews Genesis code changes. Use for diffs touching auth, credentials/secrets, financial transaction