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 bridge between AI agents (like Claude, Cursor, and Windsurf) and the Unity game engine. It allows developers to automate tedious editor tasks, generate game mechanics, and debug projects using natural language. Uniquely, it also works within compiled games, enabling real-time AI debugging and dynamic NPC behaviors during runtime.
How it works
The project implements the Model Context Protocol (MCP), acting as an MCP server that connects AI agents to Unity. It provides a vast library of over 70 built-in tools that the AI can call to manipulate the Unity Editor, manage assets, modify the scene hierarchy, and execute C# code via Roslyn. It supports both local (stdio) and remote (http) deployment and can be extended with custom tools and prompts.
Who it’s for
Game developers using Unity who want to accelerate their workflow with AI agents, as well as developers looking to integrate LLM-driven logic into their final game builds.
Highlights
- Editor & Runtime Support: Works both in the Unity Editor and inside compiled game builds.
- Extensive Toolset: Includes 70+ default tools for asset management, scene manipulation, scripting, and profiling.
- AI Agent Agnostic: Compatible with various providers including Anthropic, OpenAI, and Microsoft.
- Dynamic Code Execution: Can compile and execute C# code on the fly using Roslyn.
- Extensible Architecture: Allows developers to create their own custom MCP tools and prompts within their project code.
Related
- Project
- Project
- Project
- Project
- Project