mcp-luma-dream-machine

Instructions

Implementation Reference

• src/luma_ai_mcp_server/server.py:375-398 (handler)

  The main handler function that implements the core logic for the 'upscale_generation' tool, including validation, API request to Luma's upscale endpoint, and response formatting.

  async def upscale_generation(parameters: dict) -> str:
      """Upscale a video generation."""
      try:
          generation_id = parameters.get("generation_id")
          if not generation_id:
              raise ValueError("generation_id parameter is required")
  
          resolution = parameters.get("resolution")
          if not resolution:
              raise ValueError("resolution parameter is required")
  
          request_data = {"generation_type": "upscale_video", "resolution": resolution}
          result = await _make_luma_request(
              "POST", f"/generations/{generation_id}/upscale", request_data
          )
  
          return (
              f"Upscale initiated for generation {generation_id}\n"
              f"Status: {result['state']}\n"
              f"Target resolution: {resolution}"
          )
      except Exception as e:
          logger.error(f"Error in upscale_generation: {str(e)}", exc_info=True)
          return f"Error upscaling generation {generation_id}: {str(e)}"

• src/luma_ai_mcp_server/server.py:149-152 (schema)

  Pydantic BaseModel defining the input schema for the 'upscale_generation' tool, specifying required fields: generation_id and resolution.

  class UpscaleGenerationInput(BaseModel):
      generation_id: str
      resolution: Resolution

• src/luma_ai_mcp_server/server.py:523-527 (registration)

  Tool registration in the list_tools() function, defining the tool name, description, and input schema for 'upscale_generation'.

  Tool(
      name=LumaTools.UPSCALE_GENERATION,
      description="Upscales a video generation to higher resolution",
      inputSchema=UpscaleGenerationInput.model_json_schema(),
  ),

• src/luma_ai_mcp_server/server.py:575-577 (registration)

  Dispatch/registration in the call_tool() match statement, routing calls to 'upscale_generation' to the handler function.

  case LumaTools.UPSCALE_GENERATION:
      result = await upscale_generation(arguments)
      return [TextContent(type="text", text=result)]

• src/luma_ai_mcp_server/server.py:100-100 (helper)

  Enum constant defining the tool name string 'upscale_generation' within LumaTools.

  UPSCALE_GENERATION = "upscale_generation"