Metasploit MCP Server

by xcape-inc

306 downloads
Not rated
GitHub

About

It is an MCP server that provides a standardized interface for AI models to interact with the Metasploit Framework through Python. It enables module management, module execution, and session management via Metasploit's RPC (MSFRPC).

Details

Author
xcape-inc
Downloads
306
Categories
Other

- List, search, and get details on Metasploit modules
- Execute modules with custom options
- Get and set module options
- List and inspect active sessions
- Write data to and read data from sessions
- Run commands in sessions

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Metasploit MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Python 3.12+, Metasploit with MSFRPC enabled, and uv. Clone the repository and run uv pip install -r requirements.txt. Create a .env file with RPC credentials and host/port settings. Start msfrpcd with the appropriate password, then launch the server using uv --directory <path> run python main.py --role viewer.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "metasploit mcp server": {
            "chatsploit-mpc": {
                "command": "uv",
                "args": [
                    "pip",
                    "install",
                    "-r",
                    "requirements.txt"
                ]
            }
        }
    }
}

McpServers

{
    "chatsploit-mpc": {
        "command": "uv",
        "args": [
            "pip",
            "install",
            "-r",
            "requirements.txt"
        ]
    }
}

Metasploit MCP Server

A Model Context Protocol (MCP) server for interacting with the Metasploit Framework through Python. This server provides a standardized interface for AI models to interact with Metasploit's functionality.

Features

- Module Management
- List available modules
- Get detailed module information
- Search for modules
- Module Execution
- Execute modules with custom options
- Get and set module options
- Session Management
- List active sessions
- Get session information
- Read/write to sessions
- Execute commands in sessions

Prerequisites

- Python 3.12 or higher
- Metasploit Framework with MSFRPC enabled
- MCP client library
- uv (Python package installer)

Installation

1. Clone this repository
2. Install dependencies:

   uv pip install -r requirements.txt

Configuration

Create a .env file with the following settings:

MSF_RPC_USERNAME=your_username
MSF_RPC_PASSWORD=your_password
MSF_RPC_HOST=127.0.0.1
MSF_RPC_PORT=55553
MSF_RPC_SSL=false

Usage

1. Start the Metasploit RPC server:

   msfrpcd -P your_password -S -a 127.0.0.1

2. Run the MCP server (this is also how your MCP client can run this server):

   uv --directory <path you cloned to> run python main.py --role viewer

Available Tools

Module Management

- list_modules: List available Metasploit modules - module_info: Get detailed information about a specific module - search_modules: Search for modules matching a query

Module Execution

- execute_module: Execute a module with specified options - get_options: Get available options for a module - set_option: Set an option for a module

Session Management

- list_sessions: List all active sessions - session_info: Get detailed information about a session - session_write: Write data to a session - session_read: Read data from a session - run_command: Execute a command in a session

License

MIT License

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.