MCP Unity integrates the Model Context Protocol into the Unity Editor, enabling various AI assistants to directly interact with and manipulate Unity projects. It provides a comprehensive set of tools and resources for AI agents to manage scenes, GameObjects, packages, and scripts within Unity.

mcp-unity: MCP Unity integrates the Model Context Protocol into the Unity Editor,… (★ 1.8k, MIT)

Features

01AI Assistant interaction with Unity projects

02IDE integration with package cache access for improved code intelligence

03Comprehensive tools for manipulating Unity scenes and GameObjects programmatically

04Ability to manage Unity packages, assets, and run tests via AI commands

05Access to Unity Editor resources like menu items, scene hierarchy, and console logs

Why choose it

+AI Assistant interaction with Unity projects

+Automated game development tasks and asset generation via AI agents

+Covers 6 supported environments or platforms, which is helpful for broader deployment needs.

+Ships with a public repository and a MIT license, which makes adoption and review easier.

Trade-offs

!There are at least 8 related tools in the same category, so the best choice is easier to make after side-by-side comparison.

Compatibility

Cursor

Supported

Verified via docs

Windsurf

Supported

Verified via docs

Claude Code

Supported

Verified via docs

Codex CLI

Supported

Verified via docs

GitHub Copilot

Supported

Verified via docs

Google Antigravity

Supported

Verified via docs

Quick start

$ https://github.com/CoderGamester/mcp-unity.git

Use cases

↳Automated game development tasks and asset generation via AI agents

↳AI-driven project refactoring and code intelligence within the Unity Editor

↳Automated testing and debugging of Unity projects with AI assistants

How it compares

≈mcp-unity sits in the Workflow Automation category, so it makes more sense to evaluate it alongside tools like Gemini CLI instead of in isolation.

≈If your main need is closer to "Automated game development tasks and asset generation via AI agents", that use case is a better lens for comparison than broad feature checklists alone.

≈mcp-unity uses a MIT license, and community traction are both easier to judge in category context.