← Back to directory
U

Unity MCP Server

Community
330+ tools to turn Claude into a full Unity Editor & Hub copilot
GitHub source repository ↗
★ 390 Stars Category · Dev Tools Very popular Source revision 826af5ce61db
50FMRS · D
Reliability
4/20
Security and permissions
6/20
Maintenance
12/20
Documentation
15/20
Setup experience
13/20

This is a feature-rich open-source Unity MCP server providing 330+ tools, the most comprehensive among competitors (compared to Bezi and Coplay MCP), and it's free. It's especially well-suited for developers using Claude Cowork, thanks to its two-tier tool system that optimizes tool list size. However, it requires environment configuration awareness and carries data manipulation risks, so backups are recommended.

Read the FMRS scoring method →

The AnkleBreaker Unity MCP server is the most comprehensive Model Context Protocol (MCP) server for Unity game development. It connects MCP-compatible AI assistants like Claude, Cursor, and Windsurf to Unity Editor and Unity Hub via an HTTP bridge. It provides 330+ tools across 30+ categories, including scene management, GameObjects, components, rendering, builds, profiling, Shader Graph, Amplify Shader Editor, terrain, physics, NavMesh, animation, multiplayer, assets, scripts, and testing. It uses a two-tier tool system: about 70 core tools are always exposed directly, while the remaining 254 are accessed via a unity_advanced_tool proxy with lazy loading to avoid overwhelming MCP clients. It supports multi-instance, multi-agent, port resilience, and crash detection. Fully free and open source under the AnkleBreaker Open License, but reselling is forbidden.

Tools

The tool list has not been reviewed yet.

Setup

  1. Install the Unity plugin: Window > Package Manager > + > Add package from git URL: https://github.com/AnkleBreaker-Studio/unity-mcp-plugin.git 2. Clone and install the server: git clone https://github.com/AnkleBreaker-Studio/unity-mcp-server.git && cd unity-mcp-server && npm install 3. Add the following JSON config to Claude Desktop (Settings > Developer > Edit Config): {"mcpServers":{"unity":{"command":"node","args":["C:/path/to/unity-mcp-server/src/index.js"],"env":{"UNITY_HUB_PATH":"C:\\Program Files\\Unity Hub\\Unity Hub.exe","UNITY_BRIDGE_PORT":"7890"}}}} 4. Restart Claude Desktop

Fit and risk

Best for

  • Independent developers and small studios looking for a free, open-source solution to control Unity with AI
  • Developers who want to automate game development workflows using MCP-compatible clients like Claude or Cursor
  • Teams needing an extensive toolset covering a broad range of Unity features

Not for

  • Professional game companies requiring commercial support or enterprise guarantees
  • Beginners who are not comfortable with environment configuration or command-line tools (requires Node.js 18+ and Unity Hub)
  • Users who want to use Unity's native AI features within Unity 6.2+ without external MCP clients

Required permissions

  • Read/modify Unity project files, create/delete assets and scripts
  • Execute Unity Editor commands, read console and compilation logs
  • Control Unity Hub (list/install editors) requiring UNITY_HUB_PATH environment variable
  • Communicate with the Unity Editor over HTTP bridge, default port 7890

Risks and side effects

  • Data loss risk due to automatic creation/deletion of assets and scripts; recommend regular project backups
  • AI-generated code may introduce errors or corrupt the project
  • Misconfiguration of environment variables (e.g., UNITY_HUB_PATH) can cause connection failures
  • Using a non-standard license (AnkleBreaker Open License) might restrict commercial redistribution

Troubleshooting

  1. Connection failed: Ensure Unity Editor is open and plugin installed; check console for '[MCP Bridge] Server started on port 7890'
  2. Unity Hub not found: Update UNITY_HUB_PATH in config to point to correct Unity Hub executable
  3. Port conflict: Change UNITY_BRIDGE_PORT and update the port in Unity's MCP Dashboard settings
  4. Category disabled: Check category settings in Unity's MCP Dashboard and enable the required category

Use cases

AI-assisted game development: create scenes, place objects, write scripts, run builds
Get scene hierarchy, view compilation errors, profile performance
Edit Shader Graphs, sculpt terrain, bake NavMesh, manage animations, run multiplayer tests

Supported clients

Claude DesktopFull support