Kali Linux Penetration Testing Tools MCP server

Kali MCP Server is a lightweight API bridge that connects AI models to your Linux terminal, allowing AI to execute commands for penetration testing, CTF challenges, and security testing. This tool enables AI-assisted security operations by providing a structured way for AI endpoints to interact with command-line tools.

Installation

Setting Up the MCP Server

Install the server on your Linux machine (preferably Kali Linux):

git clone https://github.com/Wh0am123/MCP-Kali-Server.git
cd MCP-Kali-Server
python3 kali_server.py

This will start the server on port 5000 of your Linux machine.

Configuring MCP Clients

The MCP client needs to be configured to connect to your server.

Claude Desktop Configuration

1. Edit the Claude Desktop configuration file located at: C:\Users\USERNAME\AppData\Roaming\Claude\claude_desktop_config.json

2. Add the following configuration:

{
    "mcpServers": {
        "kali_mcp": {
            "command": "python3",
            "args": [
                "/absolute/path/to/mcp_server.py",
                "http://LINUX_IP:5000/"
            ]
        }
    }
}

Replace LINUX_IP with the IP address of your Linux machine and ensure the path to mcp_server.py is correct.

5ire Desktop Configuration

For the 5ire application:

1. Add a new MCP with the command: python3 /absolute/path/to/mcp_server.py http://LINUX_IP:5000

2. The application will automatically generate the necessary configuration files.

Usage Examples

Once configured, you can use your AI assistant to perform various security tasks:

Basic Terminal Commands

You can ask the AI to execute basic terminal commands:

• Network scanning with nmap
• Directory enumeration with tools like gobuster or dirbuster
• Web requests using curl or wget

CTF Challenge Solving

For CTF web challenges, you can instruct the AI to:

1. Analyze the challenge
2. Perform reconnaissance with appropriate tools
3. Identify vulnerabilities
4. Execute exploitation techniques
5. Extract flags

Penetration Testing Assistance

The MCP server enables AI to assist with:

• Automated reconnaissance
• Vulnerability scanning
• Exploitation suggestion
• Post-exploitation activities

Memory and Disk Forensics

The system can also be used for:

• Memory forensics using Volatility (process enumeration, DLL injection checks)
• Disk forensics with SleuthKit (timeline generation, file carving)

Security Considerations

When using the MCP Kali Server:

• Always run the server in a controlled environment
• Ensure network connections are secured
• Be mindful of the commands being executed
• Use only for legitimate security testing with proper authorization

The MCP server provides AI with terminal access, so always verify the commands before allowing execution, especially when working with sensitive systems.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.