MCP for Unity integrates AI assistants like Claude and VS Code Copilot with the Unity Editor using the Model Context Protocol. This allows developers to use Large Language Models to manage assets, control scenes, edit scripts, and automate various tasks within Unity, streamlining game development workflows.

unity-mcp

Active·★ 14.8k·MIT·Updated 2026-10-08

★ Trending★ Essential

MCP for Unity bridges AI assistants and the Unity Editor through the Model Context Protocol. From Claude Desktop or Claude Code, Codex, Cursor, VS Code, Windsurf, Cline, Gemini or local LLMs, you can control the editor in natural language: create scenes and GameObjects, edit C# scripts, manage assets, run tests, profile and build.

It suits game developers and technical artists who want an AI assistant to take on repetitive editor work or prototype quickly, such as setting up scenes, wiring components, generating scripts or running test passes. It exposes around 50 focused MCP tool entry points, works with Unity 2021.3 LTS through Unity 6, and is free and open source. It is sponsored and maintained by Aura, an AI assistant for Unreal and Unity, and the same makers have released a similar open-source project for Godot.

Getting started: requires Python 3.10+ via uv. In Unity, open Package Manager, choose "Add from git URL" and enter `https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main` (or use OpenUPM), then use Window → MCP for Unity → Configure All Detected Clients.

#Unity#LLM#AI Assistant#Game Development#Model Context Protocol#Coding

Features

01Natural Language Control over Unity

02Comprehensive Unity Toolset (assets, scenes, scripts, etc.)

03Automation of Repetitive Workflows

04Extensible with Various MCP Clients

05Seamless AI Assistant Integration

Why choose it

+Broad editor control: scenes, GameObjects, scripts, assets, tests, profiling and builds.

+Works with almost any MCP client, including local models.

+Easy setup through Unity's Package Manager with automatic client configuration.

+Free, MIT licensed and frequently released.

Trade-offs

!The assistant can modify scenes, scripts and assets; use version control so you can review and revert changes.

!Requires a Python environment managed by uv in addition to Unity.

!Results depend on the model's understanding of Unity APIs; complex gameplay code still needs developer review.

Compatibility

Claude Desktop

Supported

Verified via docs

Cursor

Supported

Verified via docs

VS Code Copilot

Supported

Verified via docs

Windsurf

Supported

Verified via docs

Antigravity

Supported

Verified via docs

Claude Code

Supported

Verified via docs

Quick start

$ Unity Package Manager → Add from git URL: https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main

Use cases

↳Rapidly creating and prototyping Unity applications using natural language.

↳AI-driven management of Unity assets, scenes, and scripts.

↳Automating complex or repetitive Unity development workflows.

How it compares

≈vs Unity MCP (IvanMurzak): another open-source bridge between LLMs and the Unity Editor; compare tool coverage and client support for your workflow.

≈vs MCP Unity (CoderGamester): a further Unity MCP plugin aimed at IDE-based agents such as Cursor and Claude Code.

≈vs Godot AI: the same makers' project for the Godot engine.

Alternatives

CopilotKit★ 37.8k

React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.

1Panel★ 37.1k

🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.

ragflow★ 91.9k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Context7★ 62.8k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

GitHub MCP Server★ 33.5k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

n8n★ 206.7k

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Brave Search MCP★ 1.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

Microsoft AutoGen★ 61.3k

A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

See all alternatives →

Comments

No comments yet. Be the first!

unity-mcp

Active·★ 14.8k·MIT·Updated 2026-10-08

★ Trending★ Essential

#Unity#LLM#AI Assistant#Game Development#Model Context Protocol#Coding

Features

01Natural Language Control over Unity

02Comprehensive Unity Toolset (assets, scenes, scripts, etc.)

03Automation of Repetitive Workflows

04Extensible with Various MCP Clients

05Seamless AI Assistant Integration

Why choose it

+Broad editor control: scenes, GameObjects, scripts, assets, tests, profiling and builds.

+Works with almost any MCP client, including local models.

+Easy setup through Unity's Package Manager with automatic client configuration.

+Free, MIT licensed and frequently released.

Trade-offs

!The assistant can modify scenes, scripts and assets; use version control so you can review and revert changes.

!Requires a Python environment managed by uv in addition to Unity.

!Results depend on the model's understanding of Unity APIs; complex gameplay code still needs developer review.

Compatibility

Claude Desktop

Supported

Verified via docs

Cursor

Supported

Verified via docs

VS Code Copilot

Supported

Verified via docs

Windsurf

Supported

Verified via docs

Antigravity

Supported

Verified via docs

Claude Code

Supported

Verified via docs

Quick start

$ Unity Package Manager → Add from git URL: https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main

Use cases

↳Rapidly creating and prototyping Unity applications using natural language.

↳AI-driven management of Unity assets, scenes, and scripts.

↳Automating complex or repetitive Unity development workflows.

How it compares

≈vs Unity MCP (IvanMurzak): another open-source bridge between LLMs and the Unity Editor; compare tool coverage and client support for your workflow.

≈vs MCP Unity (CoderGamester): a further Unity MCP plugin aimed at IDE-based agents such as Cursor and Claude Code.

≈vs Godot AI: the same makers' project for the Godot engine.

Alternatives

CopilotKit★ 37.8k

React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.

1Panel★ 37.1k

🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.

ragflow★ 91.9k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Context7★ 62.8k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

GitHub MCP Server★ 33.5k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

n8n★ 206.7k

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Brave Search MCP★ 1.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

Microsoft AutoGen★ 61.3k

A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

See all alternatives →

Comments

No comments yet. Be the first!