IvanMurzak/Unity-MCP

AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.

What it solves

Unity MCP provides a way to connect AI agents (like Claude, Cursor, or Windsurf) directly to the Unity game engine. It eliminates the manual process of copying code and instructions between an LLM and the editor, allowing AI to automate workflows, generate game mechanics, and perform real-time debugging both in the Editor and within compiled games.

How it works

The project implements the Model Context Protocol (MCP), acting as a bridge between AI agents and Unity. It provides a set of "Tools" (over 70 built-in) that the AI can call to interact with the Unity AssetDatabase, Hierarchy, Scene, and Profiler. It can be deployed locally via stdio or remotely via HTTP. The system can automatically generate "skills" based on the project's specific OS, Unity version, and installed plugins.

Who it’s for

Game developers using Unity who want to integrate LLM-driven automation into their development pipeline or implement AI-driven behaviors and debugging tools directly into their runtime games.

Highlights

  • Editor & Runtime Support: Works inside the Unity Editor and within compiled game builds for real-time interaction.
  • Extensive Toolset: Includes 70+ built-in tools for asset management, scene manipulation, scripting, and profiling.
  • Agent Agnostic: Compatible with various AI agents including Claude, Cursor, GitHub Copilot, and Gemini.
  • Dynamic Code Execution: Can compile and execute C# code dynamically using Roslyn.
  • Customizable: Supports the creation of custom tools and MCP prompts within the project code.