CoplayDev/unity-mcp

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

MCP for Unity – AI‑powered Unity Editor control

What it is

  • An open‑source Unity package that lets you talk to large language models (Claude, Codex, Gemini, local LLMs, etc.) and have them manipulate the Unity Editor for you. It implements the Model Context Protocol (MCP) so any MCP‑compatible client can issue natural‑language commands.

Key capabilities

  • Scene & GameObject creation – ask the model to add cubes, lights, prefabs, etc.
  • C# script editing – generate or modify scripts, with Roslyn validation to catch syntax errors before they reach the editor.
  • Asset management – import, move, rename, or delete assets via chat.
  • Testing & profiling – run unit tests, start profiling sessions, and retrieve results.
  • Build automation – trigger builds for any target platform.
  • Tool catalog – 50 pre‑defined “tool entrypoints” covering UI, VFX, animation, testing, and more.
  • Multi‑instance routing – control several Unity editor instances from a single client.
  • Remote server mode – host the MCP bridge on another machine with authentication.

How to get started

  1. Add the package in Unity’s Package Manager using the git URL:
    https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main
    (pin a tag such as #v10.0.0 for a stable release or use OpenUPM: openupm add com.coplaydev.unity-mcp).
  2. Open Window → MCP for Unity → Configure All Detected Clients – the UI scans for installed MCP clients (Claude Desktop, Cursor, VS Code, etc.) and sets up the communication bridge.
  3. In any MCP client, type a natural‑language prompt, e.g. “Create a cube at the origin and add a Rigidbody.” – the cube appears in the scene within seconds.

Who it’s for

  • Game developers who want to prototype or iterate faster by describing changes in plain language.
  • Studios experimenting with AI‑assisted content creation pipelines.
  • Researchers studying human‑AI interaction in 3D authoring environments.

Community & support

  • Discord for real‑time help and feature discussion.
  • GitHub Issues & Discussions for bug reports, feature requests, and design ideas.
  • Detailed docs, migration guides, and a full tool reference hosted at https://coplaydev.github.io/unity-mcp/.

License

  • MIT – free for commercial and non‑commercial use.

Related projects

  • Aura (the sponsor) offers a premium AI assistant for Unity/Unreal.
  • The same team maintains Godot AI, an analogous tool for the Godot engine.

If you use MCP for Unity in research, cite the accompanying ACM paper (Wu & Barnett, 2025).

Related

  • Project
    CoderGamester/mcp-unity

    An implementation of the Model Context Protocol for the Unity Editor, allowing AI assistants to directly manipulate scenes, assets, and editor settings.

  • Project
    isuzu-shiranui/UnityMCP

    A framework that exposes the Unity Editor as an MCP server, enabling AI agents to automate editor tasks, diagnose projects, and manipulate assets.

  • Project
    AnkleBreaker-Studio/unity-mcp-server

    AnkleBreaker Unity MCP is a Model Context Protocol server that lets AI assistants control multiple Unity editors simultaneously — building scenes, running tests, managing multiplayer Play Mode, and inspecting performance — with per-editor queues, action history, and undo support. It's built for teams coordinating several agents across projects and demanding Unity workflows.

  • Project
    github/github-mcp-server

    A Model Context Protocol (MCP) server that enables AI agents to interact with GitHub repositories, issues, pull requests, and CI/CD workflows.

  • Project
    cl0nazepamm/3dsmax-mcp

    A bridge that connects AI agents to Autodesk 3ds Max via the Model Context Protocol, enabling automated 3D modeling, material workflows, and scene management.