Skip to main content
Glama

download_sketchfab_model

Download and import Sketchfab 3D models into Blender using their unique identifier (UID) for AI-assisted 3D modeling and scene creation.

Instructions

Download and import a Sketchfab model by its UID.

Parameters:

  • uid: The unique identifier of the Sketchfab model

Returns a message indicating success or failure. The model must be downloadable and you must have proper access rights.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uidYes

Implementation Reference

  • The core handler function for the 'download_sketchfab_model' tool. It is decorated with @mcp.tool() for registration and implements the logic by sending a socket command to the Blender addon with the model UID, then parsing and returning the result.
    @mcp.tool()
    def download_sketchfab_model(
        ctx: Context,
        uid: str
    ) -> str:
        """
        Download and import a Sketchfab model by its UID.
        
        Parameters:
        - uid: The unique identifier of the Sketchfab model
        
        Returns a message indicating success or failure.
        The model must be downloadable and you must have proper access rights.
        """
        try:
            
            blender = get_blender_connection()
            logger.info(f"Attempting to download Sketchfab model with UID: {uid}")
            
            result = blender.send_command("download_sketchfab_model", {
                "uid": uid
            })
            
            if result is None:
                logger.error("Received None result from Sketchfab download")
                return "Error: Received no response from Sketchfab download request"
                
            if "error" in result:
                logger.error(f"Error from Sketchfab download: {result['error']}")
                return f"Error: {result['error']}"
            
            if result.get("success"):
                imported_objects = result.get("imported_objects", [])
                object_names = ", ".join(imported_objects) if imported_objects else "none"
                return f"Successfully imported model. Created objects: {object_names}"
            else:
                return f"Failed to download model: {result.get('message', 'Unknown error')}"
        except Exception as e:
            logger.error(f"Error downloading Sketchfab model: {str(e)}")
            import traceback
            logger.error(traceback.format_exc())
            return f"Error downloading Sketchfab model: {str(e)}"
  • Input/output schema and description provided in the function docstring, defining the 'uid' parameter as required string input.
    """
    Download and import a Sketchfab model by its UID.
    
    Parameters:
    - uid: The unique identifier of the Sketchfab model
    
    Returns a message indicating success or failure.
    The model must be downloadable and you must have proper access rights.
    """
  • The @mcp.tool() decorator registers this function as an MCP tool.
    @mcp.tool()
  • Companion 'search_sketchfab_models' tool used to find model UIDs before downloading with download_sketchfab_model.
    def search_sketchfab_models(
        ctx: Context,
        query: str,
        categories: str = None,
        count: int = 20,
        downloadable: bool = True
    ) -> str:
        """
        Search for models on Sketchfab with optional filtering.
        
        Parameters:
        - query: Text to search for
        - categories: Optional comma-separated list of categories
        - count: Maximum number of results to return (default 20)
        - downloadable: Whether to include only downloadable models (default True)
        
        Returns a formatted list of matching models.
        """
        try:
            
            blender = get_blender_connection()
            logger.info(f"Searching Sketchfab models with query: {query}, categories: {categories}, count: {count}, downloadable: {downloadable}")
            result = blender.send_command("search_sketchfab_models", {
                "query": query,
                "categories": categories,
                "count": count,
                "downloadable": downloadable
            })
            
            if "error" in result:
                logger.error(f"Error from Sketchfab search: {result['error']}")
                return f"Error: {result['error']}"
            
            # Safely get results with fallbacks for None
            if result is None:
                logger.error("Received None result from Sketchfab search")
                return "Error: Received no response from Sketchfab search"
                
            # Format the results
            models = result.get("results", []) or []
            if not models:
                return f"No models found matching '{query}'"
                
            formatted_output = f"Found {len(models)} models matching '{query}':\n\n"
            
            for model in models:
                if model is None:
                    continue
                    
                model_name = model.get("name", "Unnamed model")
                model_uid = model.get("uid", "Unknown ID")
                formatted_output += f"- {model_name} (UID: {model_uid})\n"
                
                # Get user info with safety checks
                user = model.get("user") or {}
                username = user.get("username", "Unknown author") if isinstance(user, dict) else "Unknown author"
                formatted_output += f"  Author: {username}\n"
                
                # Get license info with safety checks
                license_data = model.get("license") or {}
                license_label = license_data.get("label", "Unknown") if isinstance(license_data, dict) else "Unknown"
                formatted_output += f"  License: {license_label}\n"
                
                # Add face count and downloadable status
                face_count = model.get("faceCount", "Unknown")
                is_downloadable = "Yes" if model.get("isDownloadable") else "No"
                formatted_output += f"  Face count: {face_count}\n"
                formatted_output += f"  Downloadable: {is_downloadable}\n\n"
            
            return formatted_output
        except Exception as e:
            logger.error(f"Error searching Sketchfab models: {str(e)}")
            import traceback
            logger.error(traceback.format_exc())
            return f"Error searching Sketchfab models: {str(e)}"
  • Helper tool to check if Sketchfab integration (required for download_sketchfab_model) is enabled.
    @mcp.tool()
    def get_sketchfab_status(ctx: Context) -> str:
        """
        Check if Sketchfab integration is enabled in Blender.
        Returns a message indicating whether Sketchfab features are available.
        """
        try:
            blender = get_blender_connection()
            result = blender.send_command("get_sketchfab_status")
            enabled = result.get("enabled", False)
            message = result.get("message", "")
            if enabled:
                message += "Sketchfab is good at Realistic models, and has a wider variety of models than PolyHaven."        
            return message
        except Exception as e:
            logger.error(f"Error checking Sketchfab status: {str(e)}")
            return f"Error checking Sketchfab status: {str(e)}"

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description only mentions return type (message) and prerequisites. It does not disclose side effects (e.g., scene modification), idempotency, rate limits, or error handling beyond success/failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is short and presents action first, then parameter and return. It could group the prerequisite line more efficiently, but overall is well-structured and not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, description covers the basic action and prerequisites but lacks usage guidance and behavioral context, making it minimally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Coverage is 0%, so description must compensate. However, it merely restates 'uid: The unique identifier of the Sketchfab model' from the schema without adding format, examples, or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it downloads and imports a Sketchfab model by UID, distinguishing it from sibling tools like search_sketchfab_models and download_polyhaven_asset.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Specifies prerequisites (model must be downloadable, proper access rights) and return value, but does not explicitly mention when to use this tool over alternatives or that the UID likely comes from search_sketchfab_models.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.