This MCP server (Kali MCP) connects an AI assistant using the MCP protocol to a Kali Linux toolset. The Kali side exposes a REST API (kali_server.py) with endpoints for executing commands and running common security tools (e.g., Nmap, Gobuster, Dirb, Nikto, SQLMap, Metasploit, Hydra, John the Ripper, WPScan, Enum4linux, and more). The MCP server (mcp_server.py) translates high-level MCP requests from the AI assistant into Kali API calls and returns results back to the AI. You can invoke network scans, web application assessments, password attacks, and information gathering via the provided functions, enabling automated pentesting workflows through the MCP client.

Prerequisites:

• Python 3.8+ on Kali Linux or a compatible Linux environment
• Kali Linux with required security tools installed
• Network access between MCP server and Kali API server

Installation steps:

1. Clone the repository: git clone <repository-url> cd kali-mcp-server

2. Create a Python virtual environment (optional butRecommended): python3 -m venv venv source venv/bin/activate

3. Install dependencies: pip install -r requirements.txt

4. Configure Kali API server (kali_server.py):

   • Ensure required tools are installed on Kali
   • Adjust API_PORT if needed (default 5000)
   • Save any tool-specific settings

5. Run the Kali API server: python kali_server.py

   defaults to port 5000

6. Configure MCP client (mcp.json) using the example below and adjust paths: { "mcpServers": { "kali_mcp": { "timeout": 180, "type": "stdio", "command": "python", "args": [ "path/to/mcp_server.py", "--server", "http://your-kali-ip:5000/" ] } } }

7. Run the MCP server: python mcp_server.py --server http://your-kali-ip:5000/

8. Start using the MCP-enabled AI assistant to issue commands that map to Kali tools via the MCP endpoints.

Tips and notes:

• Ensure the Kali API server is reachable from the MCP server (correct IP/port).
• Adjust timeout settings (COMMAND_TIMEOUT and MCP timeout) if tools run long-running tasks.
• Keep tools up to date on Kali to avoid missing features.
• For security, run in a controlled, authorized environment and monitor logs for sensitive output.
• If a tool is not found, verify that the corresponding binary is installed and the Kali API endpoint is enabled.
• You can extend mcp.json and kali_server.py to add more tools or endpoints as needed.
• Environment variables can be used to tune behavior (e.g., DEBUG_MODE, API_PORT).