Get the FREE Ultimate OpenClaw Setup Guide →

Unity-AI-ProBuilder

AI-powered 3D modeling tools for Unity ProBuilder. Enables AI assistants to create and manipulate editable meshes through natural language commands. Create primitive shapes, extrude faces, bevel edges, apply materials, merge objects, and perform advanced mesh operations like bridging and subdivision.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio ivanmurzak-unity-ai-probuilder docker run -i unity-ai-probuilder-image \
  --env MCP_LOG_LEVEL="info or debug" \
  --env UNITY_ACCESS_TOKEN="your-unity-access-token (if required)"

How to use

Unity AI ProBuilder exposes AI-assisted ProBuilder tooling inside Unity through the MCP (Model Context Protocol) framework. The server wraps a collection of ProBuilder-powered commands, enabling natural-language or structured prompts to create and modify 3D geometry, adjust mesh attributes, and apply materials. Commands cover core operations such as creating primitive shapes, extruding faces, beveling edges, merging objects, and performing advanced mesh edits like bridging and subdivision. You can perform semantic face selection by direction (up, down, left, right) to streamline editing workflows and rapidly prototype levels or procedural geometry.

To use the tools, connect your MCP client to the Unity AI ProBuilder server and invoke the available commands (for example: probuilder-create-shape to generate shapes, probuilder-extrude to extend faces, probuilder-merge-objects to combine meshes, or probuilder-bevel to soften edges). The toolset is designed to be scriptable from natural language prompts or structured API calls, enabling AI-assisted design within Unity scenes and prefabs. The package also exposes inspection commands like probuilder-get-mesh-info to inspect the geometry and mesh attributes as you iterate.

How to install

Prerequisites:

  • Unity installed (supported versions listed in the project documentation).
  • Basic familiarity with OpenUPM if using the Unity package approach.
  • Access to the Unity project where you want to install the ProBuilder tools.

Option A: Install via OpenUPM (recommended for runtime integration)

  1. Ensure OpenUPM CLI is installed: follow the OpenUPM installation guide.
  2. In your Unity project folder, run:
openupm add com.ivanmurzak.unity.mcp.probuilder
  1. Open Unity and let the package import automatically. The MCP server tooling will be available through the Unity editor environment.

Option B: Install via installer (if a prebuilt package is provided)

  1. Download the AI ProBuilder Installer package from the releases page.
  2. In Unity, go to Assets > Import Package > Custom Package and select the downloaded installer.
  3. Follow the prompts to complete the installation and enable MCP integration within your project.

Additional notes

Notes for operators:

  • The Unity ProBuilder MCP integration relies on the OpenUPM package name com.ivanmurzak.unity.mcp.probuilder. Ensure the package registry is accessible from your environment.
  • If you encounter connectivity issues with the MCP server, verify Docker is running (if using the docker option) and that the container image unity-ai-probuilder-image is available or buildable.
  • Environment variables (like UNITY_ACCESS_TOKEN or MCP_LOG_LEVEL) can help with authentication and troubleshooting; set them in your runtime environment as needed.
  • The MCP config example uses a docker-based command as a generic deployment method. If you deploy differently (e.g., npx, uvx, or node), adapt the command and arguments to your environment while preserving the same endpoint name (unity-ai-probuilder).
  • Review Unity editor compatibility notes and any platform-specific constraints in the Unity AI ProBuilder documentation to ensure best results.

Related MCP Servers

Sponsor this space

Reach thousands of developers