投稿ログイン

MCP Server For Garak LLM Vulnerability Scanner

@EdenYavin

リポジトリ

MCP Server For Garak LLM Vulnerability Scanner について

MCP Server for using Garak LLM vulnerability scanner

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT license

ランタイム

python

トランスポート

stdio

公開者

EdenYavin

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Server For Garak LLM Vulnerability Scanner?

A lightweight MCP server that integrates the Garak LLM vulnerability scanner, enabling AI assistants to list model types, models, probes, run attacks, and retrieve reports. It is intended for developers and security researchers assessing LLM robustness.

How to use MCP Server For Garak LLM Vulnerability Scanner?

Install prerequisites (Python 3.11+, uv), clone the repository, then configure your MCP host (e.g., Cursor, Claude Desktop) with the provided JSON entry pointing to the garak-server script via uv run. Invoke tools like run_attack with required parameters (model_type, model_name, probe_name).

Key features of MCP Server For Garak LLM Vulnerability Scanner

List available model types (ollama, openai, huggingface, ggml)
List all available models for a given type
List all available Garak probes/attacks
Run an attack with specified model and probe
Get the report path of the last run

Use cases of MCP Server For Garak LLM Vulnerability Scanner

Security audit of a local Ollama model against known probes
Automated vulnerability scanning of OpenAI or HuggingFace models
Batch testing of multiple probes on a single model
Integration with Cursor or Claude Desktop for on-demand scanning
Generating and retrieving detailed attack reports

FAQ from MCP Server For Garak LLM Vulnerability Scanner

What prerequisites are needed?

Python 3.11 or higher, uv (install via pip install uv or Homebrew), and optionally Ollama running (ollama serve) for local models.

Where does the report data live?

The get_report tool returns the path to the report file from the last run; the README does not specify the exact directory.

Which MCP hosts are supported?

Tested on Cursor and Claude Desktop; configuration JSON is provided for these.

What transport or authentication is used?

The README does not mention transport or authentication details. It uses the MCP protocol, likely stdio transport via the uv command.

Are there known limitations?

Future steps include Docker/Smithery support, improved reporting, and validation for OpenAI, HuggingFace, and local GGML models (currently untested).

コメント

「AI とエージェント」の他のコンテンツ

Perplexity MCP Server

DaInfernalCoder

A Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon

MCP Claude Code

MCP implementation of Claude Code capabilities and more

MCP-LLM Bridge

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

Intervals.icu MCP Server

Model Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.

MCP Server - Remote MacOs Use

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App