kali-tools-mcp

kali-tools-mcp

Exposes a hardened Docker container with Kali Linux security tools (nmap, sqlmap, dig, whois, etc.) as MCP tools, enabling network reconnaissance, web analysis, and vulnerability scanning through natural language commands.

Category
访问服务器

README

Kali Tools MCP Server (Docker)

This project builds a hardened Docker image containing:

  • A Node.js MCP server (Streamable HTTP transport)
  • A selected security toolset (nmap, sqlmap, dig, whois, openssl, curl, netcat, dnsutils, plus Chromium for browser exploration)

Installation & Setup

Prerequisites

  • Docker (for containerized deployment)
  • Node.js 18+ (for local development)
  • npm

Install dependencies

npm install

Build the Docker image

docker build -t kali-tools-mcp:latest .

Run the server

Option 1: Local development

npm start

By default, the server listens on http://0.0.0.0:3000. Override with environment variables:

HOST=127.0.0.1 PORT=8080 npm start

Option 2: Docker (detached)

docker run -d --name kali-tools-mcp --rm -p 3000:3000 kali-tools-mcp:latest

Option 3: Docker (hardened runtime)

docker run -d --name kali-tools-mcp --rm \
  -p 3000:3000 \
  --read-only \
  --tmpfs /tmp:rw,noexec,nosuid,size=64m \
  --cap-drop ALL \
  --security-opt no-new-privileges:true \
  --pids-limit 256 \
  --memory 512m \
  --cpus 1.0 \
  kali-tools-mcp:latest

Health check

curl http://localhost:3000/health

Stop the container

docker stop kali-tools-mcp

MCP Configuration

Endpoint

http://localhost:3000/mcp

Example MCP client config

Use this in an MCP-compatible client that supports Streamable HTTP servers:

{
  "mcpServers": {
    "kali-tools": {
      "type": "streamable-http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Exposed Tools

Reconnaissance & Discovery

  • nmap_scan: Run nmap with a controlled set of options (-sV, -sT, -Pn, -A, -F)
  • dig_lookup: Resolve DNS records via dig (A, AAAA, CNAME, MX, TXT, NS)
  • whois_lookup: Fetch WHOIS information for a domain

Web & TLS Analysis

  • http_headers_check: Fetch HTTP response headers from a URL (supports redirect following and insecure TLS)
  • website_explore: Open a website in Playwright and return a structured summary of the page
  • website_interact_form: Fill form fields in Playwright and optionally submit the form
  • playwright_cli: Run bounded Playwright CLI commands (--version, install, screenshot, pdf, show-trace)
  • tls_certificate_check: Inspect TLS certificate and handshake details for a host
  • nmap_ssl_cipher_scan: Enumerate supported TLS ciphers on a target

Vulnerability Scanning

  • sqlmap_url_scan: Run a bounded sqlmap check against a URL
  • nmap_vuln_scan: Run nmap vulnerability NSE scripts against a host

Configuration & Limits

  • Tool timeout: 60 seconds (120 seconds for vulnerability scans)
  • Max output: 12,000 characters (truncated if exceeded)
  • Max buffer: 10 MB per execution
  • Options constraints: Commands enforce strict argument whitelisting to prevent abuse

Security & Authorization

⚠️ Important: Run scans only on systems you own or have explicit written permission to test.

  • The image uses a slim base and runs as a non-root user.
  • The server limits command arguments and output size to reduce abuse and accidental overload.
  • All tool executions are bounded by timeouts and resource constraints.
  • Environment variables default to listening on all interfaces (0.0.0.0); restrict to 127.0.0.1 for local-only access.

Development

Project structure

.
├── Dockerfile          # Container definition
├── package.json        # Node.js dependencies & metadata
├── README.md           # This file
└── src/
    └── server.js       # MCP server implementation

License & Disclaimer

Use responsibly. The authors are not responsible for misuse of this software. Ensure all scans are authorized.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选