add_model_from_url
Integrate a URL-based chatbot model into the Enkrypt AI MCP Server by providing a configuration dictionary with model details, including URL, name, and version, for streamlined AI safety analysis.
Instructions
Add a new model using the provided configuration.
Args: config: A dictionary containing the url model configuration details. The structure of the ModelConfig is as follows: Example usage: { "model_saved_name": "example_model_name", # The name under which the model is saved. "model_version": "v1", # The version of the model. "testing_for": "URL", # The purpose for which the model is being tested. (Always URL) "model_name":"example_url", # The url of the chatbot site provided by user. "model_config": { "model_provider": "url", # Always fixed to 'url' "endpoint_url":"example_url", # Same as model_name "apikey":"none", # The API key to access the model. "input_modalities": ["text"], # Always fixed to ['text'] "output_modalities": ["text"], # Always fixed to ['text'] }, } Ask the user for the url before passing the config to the tool.
Returns: A dictionary containing the response message and details of the added model.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes |
Implementation Reference
- src/mcp_server.py:294-324 (handler)The @mcp.tool() decorator registers the 'add_model_from_url' tool, and the function implements the core logic by calling model_client.add_model with the provided config and returning the response as a dictionary. The docstring provides the input schema example.
@mcp.tool() def add_model_from_url(config: Dict[str, Any]) -> Dict[str, Any]: """ Add a new model using the provided configuration. Args: config: A dictionary containing the url model configuration details. The structure of the ModelConfig is as follows: Example usage: { "model_saved_name": "example_model_name", # The name under which the model is saved. "model_version": "v1", # The version of the model. "testing_for": "URL", # The purpose for which the model is being tested. (Always URL) "model_name":"example_url", # The url of the chatbot site provided by user. "model_config": { "model_provider": "url", # Always fixed to 'url' "endpoint_url":"example_url", # Same as model_name "apikey":"none", # The API key to access the model. "input_modalities": ["text"], # Always fixed to ['text'] "output_modalities": ["text"], # Always fixed to ['text'] }, } Ask the user for the url before passing the config to the tool. Returns: A dictionary containing the response message and details of the added model. """ # Add the model using the provided configuration add_model_response = model_client.add_model(config=copy.deepcopy(config)) # Return the response as a dictionary return add_model_response.to_dict()