list_models
Retrieve available models by type (ollama, openai, huggingface, ggml) for use as attack or target models in Garak-MCP's LLM vulnerability scanner.
Instructions
List all available models for a given model type.
Those models can be used for the attack and target models.
Args:
model_type (str): The type of model to list (ollama, openai, huggingface, ggml)
Returns:
list[str]: A list of available models.Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model_type | Yes |
Implementation Reference
- src/server.py:118-131 (handler)MCP tool handler for 'list_models'. Decorated with @mcp.tool() to register and execute the tool logic by calling ModelConfig.list_models.
@mcp.tool() def list_models(model_type: str) -> list[str]: """ List all available models for a given model type. Those models can be used for the attack and target models. Args: model_type (str): The type of model to list (ollama, openai, huggingface, ggml) Returns: list[str]: A list of available models. """ return GarakServer().config.list_models(model_type) - src/server.py:118-118 (registration)Registration of the 'list_models' tool using FastMCP's @mcp.tool() decorator.
@mcp.tool() - src/config.py:89-103 (helper)Helper method in ModelConfig that implements the core logic for listing models by delegating to type-specific model getters.
def list_models(self, model_type: str) -> List[str]: """ List available models for a given model type. Args: model_type (str): The type of model (ollama, openai, huggingface, ggml) Returns: List[str]: List of available model names """ if model_type not in self.model_types: raise ValueError(f"Invalid model type: {model_type}") return self.model_types[model_type]["models"]() - src/config.py:35-44 (helper)Helper function to fetch Ollama models via API.
def _get_ollama_models(self) -> List[str]: """Get list of installed Ollama models""" try: response = requests.get('http://localhost:11434/api/tags') response.raise_for_status() data = response.json() return [model['name'] for model in data.get('models', [])] except requests.exceptions.RequestException as e: print(f"Error fetching Ollama models: {e}") return []