BlenderMCP

Instructions

Implementation Reference

• src/blender_mcp/server.py:742-796 (handler)

  The primary handler function for the 'generate_hyper3d_model_via_images' tool. It validates input images (paths or URLs), encodes local images to base64, processes bbox_condition using helper, and sends 'create_rodin_job' command to Blender backend. The docstring serves as the tool schema defining parameters and usage.
  @mcp.tool() def generate_hyper3d_model_via_images( ctx: Context, input_image_paths: list[str]=None, input_image_urls: list[str]=None, bbox_condition: list[float]=None ) -> str: """ Generate 3D asset using Hyper3D by giving images of the wanted asset, and import the generated asset into Blender. The 3D asset has built-in materials. The generated model has a normalized size, so re-scaling after generation can be useful. Parameters: - input_image_paths: The **absolute** paths of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in MAIN_SITE mode. - input_image_urls: The URLs of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in FAL_AI mode. - bbox_condition: Optional. If given, it has to be a list of ints of length 3. Controls the ratio between [Length, Width, Height] of the model. Only one of {input_image_paths, input_image_urls} should be given at a time, depending on the Hyper3D Rodin's current mode. Returns a message indicating success or failure. """ if input_image_paths is not None and input_image_urls is not None: return f"Error: Conflict parameters given!" if input_image_paths is None and input_image_urls is None: return f"Error: No image given!" if input_image_paths is not None: if not all(os.path.exists(i) for i in input_image_paths): return "Error: not all image paths are valid!" images = [] for path in input_image_paths: with open(path, "rb") as f: images.append( (Path(path).suffix, base64.b64encode(f.read()).decode("ascii")) ) elif input_image_urls is not None: if not all(urlparse(i) for i in input_image_paths): return "Error: not all image URLs are valid!" images = input_image_urls.copy() try: blender = get_blender_connection() result = blender.send_command("create_rodin_job", { "text_prompt": None, "images": images, "bbox_condition": _process_bbox(bbox_condition), }) succeed = result.get("submit_time", False) if succeed: return json.dumps({ "task_uuid": result["uuid"], "subscription_key": result["jobs"]["subscription_key"], }) else: return json.dumps(result) except Exception as e: logger.error(f"Error generating Hyper3D task: {str(e)}") return f"Error generating Hyper3D task: {str(e)}"
• src/blender_mcp/server.py:697-704 (helper)

  Supporting helper function used by the tool to normalize and validate the bbox_condition parameter into a list of integers scaled to 0-100 range.
  def _process_bbox(original_bbox: list[float] | list[int] | None) -> list[int] | None: if original_bbox is None: return None if all(isinstance(i, int) for i in original_bbox): return original_bbox if any(i<=0 for i in original_bbox): raise ValueError("Incorrect number range: bbox must be bigger than zero!") return [int(float(i) / max(original_bbox) * 100) for i in original_bbox] if original_bbox else None
• src/blender_mcp/server.py:749-760 (schema)

  The docstring of the handler function defines the input schema (parameters with types and descriptions) and output for the MCP tool.
  """ Generate 3D asset using Hyper3D by giving images of the wanted asset, and import the generated asset into Blender. The 3D asset has built-in materials. The generated model has a normalized size, so re-scaling after generation can be useful. Parameters: - input_image_paths: The **absolute** paths of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in MAIN_SITE mode. - input_image_urls: The URLs of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in FAL_AI mode. - bbox_condition: Optional. If given, it has to be a list of ints of length 3. Controls the ratio between [Length, Width, Height] of the model. Only one of {input_image_paths, input_image_urls} should be given at a time, depending on the Hyper3D Rodin's current mode. Returns a message indicating success or failure.
• src/blender_mcp/server.py:742-742 (registration)

  The @mcp.tool() decorator registers the function as an MCP tool, using its docstring as schema.
  @mcp.tool()