MCP Server For Garak LLM Vulnerability Scanner

@EdenYavin

Basic information

About MCP Server For Garak LLM Vulnerability Scanner

MCP Server for using Garak LLM vulnerability scanner

MCP Server For Garak LLM Vulnerability Scanner config

Add this server to your MCP-compatible client using the configuration below.

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

MCP Server For Garak LLM Vulnerability Scanner tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

Frequently asked questions

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).

Comments

More AI & Agents MCP servers

Agent Traffic Lab

ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lo

SlopIt: blogs for AI agents

SimbaStack

Blog MCP server for AI agents. One signup call returns a blog, an API key and a live URL; then your agent publishes markdown posts and gets public URLs back. Your agent does the writing; you get a dashboard for stats.

Tokenaissance

Rain

Tokenaissance is a online Personal Agent for Quant and Research investment available at https://tokenaissance.com.

xhostd

Agent-first hosting. From Claude, Cursor, or Codex, your agent can create an app, push code, and deploy it to a live HTTPS URL, with managed Postgres, custom domains, environment variables, backups, and rollback.

q-ring

I4cTime

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.