CoplayDev/unity-mcp
Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Overview
CoplayDev/unity-mcp is a C# MCP server licensed under MIT. Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity. Topics: ai, ai-integration, mcp, unity, anthropic, claude, copilot, cursor, game-development, gemini, llm, model-context-protocol, openai, unity3d, gamedev, videogames.
Ranked #20 out of 25632 indexed tools.
In the top 1% of all indexed tools.
Has 7,003 GitHub stars.
Has 43 contributors.
Actively maintained with commits in the last week.
Ecosystem
Signal Breakdown
How to Improve
Matched Queries
From the README
| [English](README.md) | [简体中文](docs/i18n/README-zh.md) | |----------------------|---------------------------------| #### Proudly sponsored and maintained by [Coplay](https://www.coplay.dev/?ref=unity-mcp) -- the best AI assistant for Unity. **Create your Unity apps with LLMs!** MCP for Unity bridges AI assistants (Claude, Claude Code, Cursor, VS Code, etc.) with your Unity Editor via the [Model Context Protocol](https://modelcontextprotocol.io/introduction). Give your LLM the tools to manage assets, control scenes, edit scripts, and automate tasks. <details> <summary><strong>Recent Updates</strong></summary> * **v9.5.4 (beta)** — New `manage_packages` tool: install, remove, search, and manage Unity packages and scoped registries. Includes input validation, dependency checks on removal, and git URL warnings. * **v9.5.3** — New `manage_graphics` tool (33 actions): volume/post-processing, light baking, rendering stats, pipeline settings, URP renderer features. 3 new resources: `volumRead full README on GitHub →