# 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.

Repository: https://github.com/CoplayDev/unity-mcp
Canonical: https://ross.abutalabs.com/products/unity-mcp
Homepage: https://coplaydev.github.io/unity-mcp/
Language: C#
License: MIT
License Family: permissive
Topics: ai, ai-integration, mcp, unity, anthropic, claude, copilot, cursor, game-development, gemini, llm, model-context-protocol, openai, unity3d, gamedev, videogames
Last push: 2026-08-07T18:50:00+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 96, release rhythm 84, longevity 38
- inputs: {"age_days": 533, "days_push": 26, "days_rel": 31, "gap_med": 2, "n_releases_24m": 66}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13675, forks 1452 (observed 2026-08-28T04:11:04.503302+00:00)

## What it is
MCP for Unity is a bridge that connects AI assistants (Claude, Cursor, VS Code, local LLMs) to the Unity Editor via the Model Context Protocol. It exposes ~48 MCP tools backed by a Python server and a C# Unity package, letting LLMs manage assets, control scenes, edit scripts, run tests, and automate game dev workflows.

## Use cases
- control the Unity Editor with natural language from Claude or Cursor
- create scenes and GameObjects via an LLM prompt
- have an AI assistant edit C# scripts in my Unity project
- automate Unity asset and prefab management with an LLM
- run Unity tests and builds through an MCP client
- connect multiple Unity Editor instances to one AI session

## When to choose
- you use Unity 2021.3 LTS through Unity 6 and want AI-assisted editor automation
- you want an MCP-compatible bridge supporting many clients like Claude Desktop, Cursor, VS Code, and Gemini CLI
- you need to drive scenes, scripts, assets, and builds from natural language

## When to avoid
- you use a game engine other than Unity (e.g., Unreal or Godot)
- you don't use MCP-capable AI assistants or local LLMs
- you need a fully autonomous agent rather than editor tooling

## Facets
- artifact type: plugin
- maturity: active
- function: mcp, agent-framework, developer-tools, workflow-automation, testing
- domain: developer-tools
- platform: game-engine, python, cross-platform
- tags: unity-editor, model-context-protocol, llm-tools, gamedev, ai-assistant-integration, editor-plugin, game-development, ai-agents, automation, c#, desktop

## Member repositories
- CoplayDev/unity-mcp (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:04.503302+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:07.741053+00:00, confidence not recorded.
  - readme: https://github.com/CoplayDev/unity-mcp (fetched 2026-08-28T04:11:04.503302+00:00, sha b8e3f6077082)
  - homepage: https://coplaydev.github.io/unity-mcp/ (fetched 2026-08-29T08:07:33.739572+00:00, sha 62b8f423e26d)
- Data as of 2026-08-30T08:39:29.467469+00:00.