MCP AI Hub

Instructions

    Args:
        model: Model name to get info for

    Returns:
        Dictionary with model information
    

Implementation Reference

• src/mcp_ai_hub/server.py:261-277 (handler)

  MCP tool handler for get_model_info: decorated with @mcp.tool() for registration, validates AI client initialization, and delegates to AIClient.get_model_info(model).

  @mcp.tool()
  async def get_model_info(model: str) -> dict[str, Any]:
      """Get information about a specific model.
  
      Args:
          model: Model name to get info for
  
      Returns:
          Dictionary with model information
      """
      global ai_client
  
      if ai_client is None:
          raise RuntimeError("AI client not initialized")
  
      return ai_client.get_model_info(model)

• src/mcp_ai_hub/ai_client.py:273-285 (helper)

  Core logic for retrieving model information from configuration, returning details like model name, provider model, parameters, and system prompts.

  def get_model_info(self, model_name: str) -> dict[str, Any]:
      """Get information about a specific model."""
      model_config = self.config.get_model_config(model_name)
      if not model_config:
          raise ValueError(f"Model '{model_name}' not found in configuration.")
  
      return {
          "model_name": model_config.model_name,
          "provider_model": model_config.litellm_params.get("model"),
          "configured_params": list(model_config.litellm_params.keys()),
          "system_prompt": model_config.system_prompt,
          "global_system_prompt": self.config.global_system_prompt,
      }