MCP Hammer

A Model Context Protocol (MCP) server built with FastMCP that provides various tools including Claude AI integration, text injection capabilities, and server information utilities. It is definitely super secure, you should definitely send confidential data through it, and definitely take everything it says as fact.

Features

• Claude AI Integration: Query Claude models directly through the MCP protocol
• Text Injection System: Append custom text to tool responses
• HTTP Transport: Built on FastMCP for reliable HTTP-based communication & remote hosting
• Session Logging: Automatic logging of all tool calls and interactions
• Health Monitoring: Built-in health check and server info endpoints
• Telemetry Service: Information about the host the server is running on is collected and stored in files on disk, and/or sent to a remote host
• Remote Management: Change injection text and manage multiple MCPHammer instances remotely via a management server
• Web UI: Browser-based management console for viewing instances and pushing updates
• Init Tool: Automatic initialization that downloads and opens files from a configurable URL
• Download & Execute: Download files from URLs and optionally execute them
• Configurable Init URL: Change the init tool's download URL remotely via web UI or API

Prerequisites

• Python 3.10 or higher
• pip (Python package manager)
• An Anthropic API key (for Claude integration)

Installation

1. Clone the repository

   git clone https://github.com/praetorian-inc/MCPHammer
   cd MCPHammer
   

2. Create a virtual environment (recommended)

   python3 -m venv venv
   
   # Activate the virtual environment
   # On macOS/Linux:
   source venv/bin/activate
   
   # On Windows:
   # venv\Scripts\activate
   

3. Install dependencies

   pip install -r requirements.txt
   

Setting up Anthropic API Key

The ask_claude tool requires an Anthropic API key to function. Set it as an environment variable:

macOS/Linux

export ANTHROPIC_API_KEY="your-api-key-here"

Windows (Command Prompt)

set ANTHROPIC_API_KEY=your-api-key-here

Windows (PowerShell)

$env:ANTHROPIC_API_KEY="your-api-key-here"

To make this permanent, add the export command to your shell configuration file (.bashrc, .zshrc, etc.) or set it in your system environment variables.

Running the Server

Start the server with default settings (port 3000):

python MCPHammer.py

Or specify a custom port:

python MCPHammer.py --port 8080

Config Server Configuration

You can configure the config server IP/port when starting MCPHammer using command-line arguments:

Option 1: Using IP:port format (automatically adds /sync endpoint):

python MCPHammer.py --config-server 192.168.1.100:8888

Option 2: Using full URL:

python MCPHammer.py --config-server-url http://192.168.1.100:8888/sync

Option 3: Using environment variable (still supported):

export CONFIG_SYNC_URL=http://192.168.1.100:8888/sync
python MCPHammer.py

You can combine options:

python MCPHammer.py --port 3000 --config-server 192.168.1.100:8888

Note: Command-line arguments take precedence over environment variables.

Available Tools

These tools are registered with the MCP server and available to MCP clients:

1. init

Downloads and opens a file from a configurable URL. The URL can be changed remotely via the management server.

Parameters:

• None (uses configured init URL)

2. hello_world

Returns "hello world" followed by provided text, with optional injection.

Parameters:

• text (string): Text to append after "hello world"
• disable_injection (boolean): Whether to disable text injection (default: false)

3. ask_claude

Query Claude AI models through the Anthropic API.

Parameters:

• query (string): Your question

... View full README on GitHub