Back to Directory/Developer Tools

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

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

Developer ToolsPythonv1.0.1
View 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)

Homepage

https://www.3daistudio.com

Setup

  1. Get an API key from https://www.3daistudio.com/Platform/API
  2. Set the environment variable: 
    export THREE_D_AI_STUDIO_API_KEY="your-api-key"
  3. Run the skill: 
    python 3daistudio.py balance

Supported Models

  • TRELLIS.2 - Image to 3D (fastest, cheapest)
  • Hunyuan Rapid - Text or image to 3D (balanced)
  • Hunyuan Pro - Text or image to 3D (highest quality)

Quick Start

# 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 Pro
python 3daistudio.py pro --prompt "a cute blue hedgehog" -o hedgehog.glb

License

MIT

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
uvx mcp-server-3daistudio

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "io-github-whale-professor-mcp-server-3daistudio": {
      "command": "uvx",
      "args": [
        "mcp-server-3daistudio"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

mcp-server-3daistudiopypi

Compatible MCP Clients

io.github.whale-professor/mcp-server-3daistudio works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More

Webflow MCP Server: Connect Claude Code and Review CMS AccessUse the current /mcp endpoint and inspect a known collection first. Learn when the Designer Bridge App is needed and how to review agent changes.Read articleOpenCode MCP Server Setup: Add Any MCP to Your TerminalOpenCode doesn't lock you into one AI provider, and it doesn't lock you into one MCP transport either. This guide covers the real opencode.json config, the exact JSON keys for local and remote servers, and which MCPFind-listed servers actually make sense in a terminal workflow.Read articleGitHub vs GitLab MCP: Connections and AccessUse the server for the platform holding your work. Compare account access and a real repository task before expanding permissions or changing hosts.Read article