Exposes 60+ Kali Linux security tools through an MCP interface, enabling penetration testing, network scanning, web security assessments, password cracking, exploitation, wireless testing, Windows/AD enumeration, OSINT, and forensics capabilities.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kali Linux MCP Serverscan my local network for open ports on common services"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Kali Linux MCP Server
A Model Context Protocol (MCP) server that exposes 60+ Kali Linux security tools through an AI-friendly interface. Enables AI assistants like Claude to perform penetration testing and security assessments.
Features
Network Scanning: nmap, masscan, netdiscover, hping3, tcpdump, tshark
Web Security: gobuster, nikto, sqlmap, wpscan, burpsuite, zap, ffuf, nuclei
Password Cracking: hydra, john, hashcat, medusa, crackmapexec
Exploitation: metasploit, searchsploit, beef, routersploit
Wireless: aircrack-ng, reaver, wifite, kismet
Windows/AD: enum4linux, impacket, evil-winrm, kerbrute, mimikatz, responder
OSINT: theharvester, shodan, spiderfoot, amass, sublist3r
Forensics: binwalk, foremost
Plus: shells (netcat, socat, msfvenom), anonymity (proxychains), mobile (apktool)
Quick Start
Docker (Recommended)
Manual Setup
Configure Cursor/Claude
Add to your MCP settings:
Architecture
kali_server.py: Flask REST API exposing Kali tools
mcp_http_server.py: MCP-over-HTTP bridge to Kali API
server/tools/: Tool implementations organized by category
Docker: Kali Linux container with all tools pre-installed
Requirements
Python 3.8+
Docker (for containerized deployment)
Kali Linux environment (for manual setup)
Testing
The project includes a comprehensive test suite using pytest.
Quick Start
Test Structure
Available Test Commands
Coverage Reports
After running make test-coverage, view the HTML report:
Continuous Integration
Tests run automatically on GitHub Actions for:
Multiple Python versions (3.9, 3.10, 3.11, 3.12)
Every push to main/develop branches
All pull requests
See tests/README.md for detailed testing documentation.
License
MIT License - See LICENSE file