Game Asset Generator using MCP and Hugging Face Spaces

What is Game Asset Generator using MCP and Hugging Face Spaces?

Game Asset Generator using MCP and Hugging Face Spaces is a tool that streamlines game asset creation by generating 2D and 3D assets from text prompts using AI models hosted on Hugging Face Spaces. It integrates with the Model Context Protocol (MCP) to enable seamless interaction with AI assistants like Claude Desktop. This tool is designed for game developers seeking rapid prototypes and AI enthusiasts exploring generative models.

How to use Game Asset Generator using MCP and Hugging Face Spaces?

Clone the repository, install dependencies (npm install), configure your Hugging Face API token and a duplicated 3D model space in a .env file, then run the server (e.g., npm start for local stdio transport, or node src/index.js --sse for remote SSE). Interact via an MCP client like Claude Desktop using commands such as generate_2d_asset prompt:"pixel art sword" or generate_3d_asset prompt:"isometric 3D castle".

Key features of Game Asset Generator using MCP and Hugging Face Spaces

• 2D asset generation from text prompts (e.g., pixel art sprites).
• 3D asset generation in OBJ and GLB formats.
• Supports multiple 3D model spaces: InstantMesh, Hunyuan3D-2, Hunyuan3D-2mini-Turbo.
• MCP integration for use with compatible clients like Claude Desktop.
• Automatic file management with local assets directory and resource URIs.
• Configurable 3D generation parameters via environment variables.

Use cases of Game Asset Generator using MCP and Hugging Face Spaces

• Rapidly prototype 2D sprites or pixel art for game projects.
• Generate 3D models from text descriptions for early-stage game design.
• Explore and experiment with AI generative models for asset creation.

FAQ from Game Asset Generator using MCP and Hugging Face Spaces

What are the prerequisites for using this tool?

You need Node.js 16+, Git, internet access, and a Hugging Face account with an API token. Optional: Claude Desktop or another MCP client for enhanced interaction.

How do I configure the 3D model generation space?

Duplicate one of the supported spaces (InstantMesh, Hunyuan3D-2, or Hunyuan3D-2mini-Turbo) to your Hugging Face account and set the MODEL_SPACE variable in .env to your-username/space-name. Obtain a Hugging Face token and set HF_TOKEN.

What transports are available and how do I run them?

The tool supports stdio transport (default: npm start or node src/index.js) for local use and SSE transport for remote access (node src/index.js --sse). Optional HTTPS can be enabled with --https if SSL certificates are provided.

Where are generated assets saved?

Assets are saved in the ./assets directory within the working directory. You can specify a custom working directory by passing it as an argument: node src/index.js /path/to/directory.

What are the differences between the supported 3D spaces?

InstantMesh uses a multi-step process (/preprocess, /generate_mvs, /make3d). Hunyuan3D-2 and Hunyuan3D-2mini-Turbo use a single-step endpoint (/generation_all). Hunyuan3D-2mini-Turbo additionally supports configurable turbo modes (Turbo, Fast, Standard), with corresponding default inference steps.