MCP.so
登录

MCP Server For Garak LLM Vulnerability Scanner

@EdenYavin

代码仓库

关于 MCP Server For Garak LLM Vulnerability Scanner

MCP Server for using Garak LLM vulnerability scanner

基本信息

分类

AI 与智能体

许可证

MIT license

运行时

python

传输方式

stdio

发布者

EdenYavin

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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).

评论

AI 与智能体 分类下的更多 MCP 服务器

mcp-hfspace MCP Server 🤗

evalstate

MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

387

meGPT - upload an author's content into an LLM

adrianco

Code to process many kinds of content by an author into an MCP server

287

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

Intervals.icu MCP Server

mvilanova

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

311

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797