Promptfuzzer MCP

🚀 Lightweight MCP (Model Context Protocol) Server for Garak LLM Vulnerability Scanner

This is a lightweight MCP server designed for the Garak LLM vulnerability scanner, offering various tools to manage models and conduct vulnerability scans.

🚀 Quick Start

This server provides a set of tools to interact with the Garak LLM vulnerability scanner. You can list available model types, models, and probes, get reports, and run attacks.

✨ Features

Tool Overview

📚 Documentation

Detailed Explanation

• list_model_types

  • List all model types available for attacks.
  • Returns a list of supported model types (ollama, openai, huggingface, ggml).

• list_models

  • List available models for a specified model type.
  • Input parameters:
    • model_type (string, required): The model type to list (ollama, openai, huggingface, ggml).
  • Returns a list of available models of the specified type.

• list_garak_probes

  • List all available Garak attacks/probes.
  • Returns a list of available probes/attacks.

• get_report

  • Get the report of the last run.
  • Returns the path to the report file.

• run_attack

  • Run an attack using a given model and probe.
  • Input parameters:
    • model_type (string, required): The model type to use.
    • model_name (string, required): The name of the model to use.
    • probe_name (string, required): The name of the attack/probe to use.
  • Returns a list of discovered vulnerabilities.

📦 Installation

Prerequisites

1. Python 3.11 or higher: This project requires Python 3.11 or newer.

   # Check your Python version
   python --version
   

2. Install uv: A fast Python package installer and resolver.

   pip install uv
   

   Or use Homebrew:

   brew install uv
   

3. Optional: Ollama: If you want to run attacks on ollama models, make sure the Ollama server is running.

   ollama serve
   

Installation Steps

1. Clone this repository:

   git clone https://github.com/BIGdeadLock/Garak-MCP.git
   

2. Configure your MCP host (Claude Desktop, Cursor, etc.):

   {
     "mcpServers": {
       "garak-mcp": {
         "command": "uv",
         "args": ["--directory", "Path to Garak-MCP", "run", "garak-server"],
         "env": {}
       }
     }
   }
   

Test Environment

• [X] Cursor
• [X] Claude Desktop

📄 Future Plans

• [ ] Add support for Smithery AI: Docker and configuration
• [ ] Improve the reporting functionality
• [ ] Test and validate OpenAI models (GPT-3.5, GPT-4)
• [ ] Test and validate HuggingFace models
• [ ] Test and validate local GGML models