Kali MCP Server
Enables running Kali Linux security tools and commands in a containerized environment for semi-automated penetration testing, with background job management and out-of-band interaction detection.
README
Kali MCP Server
A Model Context Protocol (MCP) server that provides command execution capabilities in a containerized Kali Linux environment for semi-automated penetration testing and security research capabilities.
Demo
https://github.com/user-attachments/assets/demo.mp4
Watch the Kali MCP Server in action
Disclaimer
This tool is provided for educational and authorized security testing purposes only. Use at your own risk. The authors are not responsible for any misuse or damage caused by this software. Always ensure you have proper authorization before conducting security assessments.
Features
- Containerized Command Execution: Run Kali Linux security tools in a containerized environment
- Background Job Management: Long-running commands (>60s) automatically run as background jobs
- Interactsh Integration: Out-of-band interaction detection for blind vulnerabilities
- Service API Management: Centralized configuration for reconnaissance APIs (GitHub, Shodan, etc.)
- Workspace Management: Organized directory structure for pentest artifacts
Requirements
- Docker & Docker Compose
- MCP-compatible client (Claude Code, Gemini CLI, VS Code with Copilot, etc.)
Quick Start
-
Start the container:
docker compose up --build -d -
Verify it's running:
docker ps | grep kali-mcp-server -
Configure your MCP client:
⚠️ IMPORTANT: Disable any built-in terminal or command execution tools in your MCP client to prevent commands from being unintentionally executed on your host system instead of the Kali container. All security tools should run exclusively within the containerized environment for safety and isolation.
Claude Desktop:
claude mcp add --transport stdio kali-mcp-server "docker exec -i kali-mcp-server python3 /app/kali_server.py"
Gemini CLI:
gemini mcp add kali-mcp-server "docker exec -i kali-mcp-server python3 /app/kali_server.py"
VS Code (Copilot):
Create or edit .vscode/mcp.json in your workspace:
{
"servers": {
"kali-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"exec",
"-i",
"kali-mcp-server",
"python3",
"/app/kali_server.py"
]
}
}
}
Others
{
"mcpServers": {
"kali-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"exec",
"-i",
"kali-mcp-server",
"python3",
"/app/kali_server.py"
],
"env": {}
}
}
}
After configuration: Restart your MCP client to load the Kali MCP server.
Available Tools
Core MCP Tools
run_kali_command- Execute commands in Kali environmentget_job_status- Check background job statuslist_background_jobs- List all running jobscancel_job- Cancel a running jobget_workspace_info- Get workspace configuration
Interactsh Tools
start_interactsh- Start out-of-band interaction monitoringget_interactsh_status- Check interactsh worker statuspoll_interactsh- Retrieve recorded interactionsstop_interactsh- Stop interactsh worker
Service Management
get_service_tokens- Get configured API service tokens
Pre-installed Security Tools
- Network Scanning:
nmap,masscan - Web Testing:
dirb,ffuf,whatweb,nikto - DNS/Domain:
dig,whois,dnsrecon - Utilities:
curl,wget,jq,exiftool - Wordlists:
Seclists
Configuration
Edit config.toml to configure:
- Workspace directory structure
- Interactsh settings
- API service tokens (GitHub, Shodan, VirusTotal, etc.)
Security Notes
- Container runs with necessary privileges for security tools
- Network tools require elevated capabilities (NET_ADMIN, NET_RAW)
- All command execution is contained within the Docker environment
- API tokens should be configured securely in production
License
This project is an independent open-source contribution and is not affiliated with, endorsed by, or associated with OffSec or Kali Linux. Kali Linux is a trademark of Offensive Security.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。