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.

Unity‑MCP – AI‑powered Game Development Assistant

What it is – A Unity package that lets you connect large‑language‑model (LLM) agents such as Claude, OpenAI Codex, Cursor, GitHub Copilot, Gemini, etc., to the Unity Editor and to a built‑game at runtime. The plugin exposes a set of “MCP Tools” (70+ built‑in commands) that AI agents can invoke to manipulate assets, scenes, GameObjects, scripts, packages, the editor state, and even run profiling queries.

Key capabilities

  • Editor‑side AI – Ask an LLM to create objects, write scripts, run tests, or debug issues directly from a Unity window.
  • Runtime AI – The same LLM calls can be made from inside a compiled game, enabling dynamic NPC behaviour or in‑game debugging.
  • Vendor‑agnostic agents – Works with Anthropic, OpenAI, Microsoft, and any other provider that speaks the MCP protocol; no lock‑in.
  • Extensible tool system – Developers can add custom tools or prompts in C# and expose them to the AI.
  • Automatic skill generation – The plugin scans the project (Unity version, installed packages, OS) and builds a “skill set” that the AI can use without manual configuration.
  • Multiple deployment modes – The MCP server can run locally via stdio, over HTTP, or in a Docker container.

How to get started

  1. Install the plugin – either download the AI-Game-Dev-Installer.unitypackage from the Releases page or run the CLI:
    npm install -g unity-mcp-cli
unity-mcp-cli install-plugin ./MyUnityProject
  2. Choose an AI agent – Claude, Codex, Cursor, Copilot, Gemini, etc. (the UI lists the supported agents).
  3. Configure the agent – Open Window → AI Game Developer in Unity and click Auto‑generate skills, or run the CLI command unity-mcp-cli setup-skills claude-code ./MyUnityProject.
  4. Talk to the AI – Type natural language commands like “Create three cubes in a circle with radius 2” and watch the editor execute the corresponding MCP tools.

Typical workflow examples

  • Generate and place prefabs, modify component fields, or create new scripts on the fly.
  • Run Unity Play‑Mode or Edit‑Mode tests automatically and get a summary of failures.
  • Capture screenshots of the scene or camera for visual debugging.
  • Use reflection‑based calls to invoke any C# method (even private ones) from the AI.
  • Deploy a Dockerised MCP server and let a remote LLM drive NPC dialogue in a shipped game.

Ecosystem & extensions The core package can be expanded with optional skill packs that add tools for specific Unity subsystems:

  • AI Animation, AI Cinemachine, AI InputSystem, AI Navigation, AI ParticleSystem, AI ProBuilder, AI Splines, AI Terrain, AI Tilemap, AI Timeline. Each pack lives in its own repository (e.g., Unity-AI-Animation) and can be installed via the Unity Package Manager.

Installation options

  • Unity Package Manager – openupm add com.ivanmurzak.unity.mcp
  • CLI – unity-mcp-cli install-plugin …
  • Docker image – aigamedeveloper/mcp-server for headless server deployments.

License – The repository is released under the MIT License.

Who might use it

  • Indie developers who want rapid prototyping without writing boiler‑plate code.
  • Teams looking to embed LLM‑driven NPCs or debugging tools directly in a shipped game.
  • Educators demonstrating AI‑assisted game development inside Unity.

All details are taken from the project's README; no additional features have been inferred.

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
    CoplayDev/unity-mcp

    MCP for Unity is an MIT‑licensed Unity package that connects LLMs (Claude, Codex, Gemini, local models, etc.) to the Unity Editor via the Model Context Protocol. It lets you create scenes, edit C# scripts, manage assets, run tests, and build games using natural‑language prompts from any MCP client. Install via Unity’s Package Manager, configure detected AI clients, and start issuing commands like “add a cube with a Rigidbody.” The project includes 50 ready‑made tool actions, multi‑instance routing, remote server support, and extensive documentation, with community channels on Discord and GitHub.

  • 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
    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
    miscusi-peek/cheatengine-mcp-bridge

    A bridge that connects AI agents to Cheat Engine via the Model Context Protocol, enabling natural language interaction with program memory for reverse engineering and modding.