io.github.whale-professor/mcp-server-3daistudio

Official

by whale-professor · Python

MCP server for 3D AI Studio — generate 3D models from text or images using Hunyuan and TRELLIS

Generate 3D models from text or images using AI.

README.md2 KBView on GitHub

3D AI Studio Skill

A skill for converting images and text prompts to 3D models using the 3D AI Studio API.

Owner

Whale Professor (@WhaleProfessor on Telegram)

Setup

Get an API key from https://www.3daistudio.com/Platform/API
Set the environment variable:
bash
```
export THREE_D_AI_STUDIO_API_KEY="your-api-key"
```
Or copy .env.example to .env and fill in your key.
Run the skill:
bash
```
python 3daistudio.py balance
```

Supported Models

Model	Input	Speed	Credits
TRELLIS.2	Image only	25s–4min	15–55
Hunyuan Rapid	Text or image	2–3min	35–55
Hunyuan Pro	Text or image	3–6min	60–100

Quick Start

bash

# Check balance
python 3daistudio.py balance

# Image to 3D with TRELLIS.2
python 3daistudio.py trellis --image photo.png -o model.glb

# Text to 3D with Hunyuan Rapid
python 3daistudio.py rapid --prompt "a wooden chair" -o chair.glb

# Text to 3D with Hunyuan Pro (best quality)
python 3daistudio.py pro --prompt "a cute blue hedgehog" -o hedgehog.glb

MCP Server

An MCP server is also included for use with Claude Desktop or Claude Code. See mcp-server-3daistudio/ for the installable package, or use mcp_server.py directly as a standalone server.

Documentation

GUIDE.md — Full usage guide with all options and examples
SKILL.md — Skill metadata and quick reference
CLAUDE.md — Instructions for AI agents

License

MIT

Install

Configuration

Environment variables

THREE_D_AI_STUDIO_API_KEYrequiredsecret

API key for 3D AI Studio

claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server-3daistudio": {
      "command": "uvx",
      "args": [
        "mcp-server-3daistudio"
      ],
      "env": {
        "THREE_D_AI_STUDIO_API_KEY": "<YOUR_THREE_D_AI_STUDIO_API_KEY>"
      }
    }
  }
}