Unity CLI Loop
Let AI Drive Unity, from Editor to Play Mode.
What is Unity CLI Loop?
Unity CLI Loop is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to let ai drive unity, from editor to play mode.
Let AI Drive Unity, from Editor to Play Mode.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Let AI Drive Unity, from Editor to Play Mode.
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx unity-cli-loopConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Unity CLI Loop
Unity CLI Loop (uloop) is an MCP server and CLI that lets AI coding assistants drive the Unity Editor directly — compiling scripts, running tests, taking screenshots, simulating input, and executing C# code at runtime — closing the feedback loop that normally requires a human to click 'Play' and check the console. It installs as a Unity Package Manager package on the Unity side and an npm CLI on the Node.js side, then bridges the two so Claude or other MCP clients can iterate on Unity game code autonomously.
Prerequisites
- Unity 2022.3 LTS or later
- Node.js 22.0 or later
- An MCP-compatible client such as Claude Desktop or Claude Code
- Optional: com.unity.inputsystem package for input simulation and recording
- Optional: com.unity.test-framework package for automated test execution
Install the uloop-cli Node.js package
Install the CLI globally via npm. This provides the uloop command used to manage the MCP server and install skills for AI clients.
npm install -g uloop-cliAdd the Unity package via Package Manager
In Unity, open Window > Package Manager, click the + button, choose 'Add package from git URL', and paste the repository URL. This installs the Editor-side bridge that communicates with the CLI.
# Git URL to paste in Unity Package Manager:
https://github.com/hatayama/unity-cli-loop.git?path=/Packages/src
# Or add via OpenUPM (scoped registry):
# Name: OpenUPM
# URL: https://package.openupm.com
# Scope: io.github.hatayama.uloopmcpInstall skills for your AI client
Run uloop skills install to register the MCP server and its skills with your AI client. Use --claude for Claude Code or --codex for OpenAI Codex. Add --global to install across all projects.
uloop skills install --claude
# Or globally:
uloop skills install --claude --globalOpen your Unity project and start the bridge
Open your Unity project. The uloop package adds a background service that the CLI connects to automatically when the Unity Editor is running.
Configure your MCP client
Add the uloop MCP server to your claude_desktop_config.json or Claude Code settings so your AI assistant can invoke Unity tools.
{
"mcpServers": {
"unity-cli-loop": {
"command": "npx",
"args": ["unity-cli-loop"]
}
}
}Verify the connection
Ask Claude to compile the Unity project and show you any errors. The AI should trigger a compile, receive the compiler output, and report back within seconds.
Unity CLI Loop Examples
Client configuration
Claude Desktop config block for Unity CLI Loop. The skills install command may add this automatically — check claude_desktop_config.json after running it.
{
"mcpServers": {
"unity-cli-loop": {
"command": "npx",
"args": ["unity-cli-loop"]
}
}
}Prompts to try
Example prompts that use the 15 built-in uloop tools to drive Unity development autonomously.
- "Compile the Unity project and fix any errors you find"
- "Run all EditMode tests and explain any failures"
- "Take a screenshot of the current Game view and describe the scene layout"
- "Find all GameObjects with the 'Enemy' tag and list their positions"
- "Start Play Mode, simulate clicking the Start button in the UI, then take a screenshot after 2 seconds"
- "Execute this C# snippet in the Editor: Debug.Log(Camera.main.transform.position)"Troubleshooting Unity CLI Loop
uloop cannot connect to Unity — 'Editor not found' error
The Unity Editor must be open with the project loaded before uloop can connect. Ensure the uloop Unity package is installed in the project (visible in Package Manager) and that Unity has finished its initial compilation.
Node.js version error on install
Unity CLI Loop requires Node.js 22.0 or later. Check your version with `node -v` and upgrade via nvm (`nvm install 22 && nvm use 22`) or the official installer at nodejs.org.
Input simulation tools fail with missing package error
Input simulation and recording require the com.unity.inputsystem package. Add it via Unity Package Manager (Window > Package Manager > Unity Registry > Input System) and enable the new Input System in Player Settings.
Frequently Asked Questions about Unity CLI Loop
What is Unity CLI Loop?
Unity CLI Loop is a Model Context Protocol (MCP) server that let ai drive unity, from editor to play mode. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Unity CLI Loop?
Follow the installation instructions on the Unity CLI Loop GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Unity CLI Loop?
Unity CLI Loop works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Unity CLI Loop free to use?
Yes, Unity CLI Loop is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Unity CLI Loop Alternatives — Similar Browser Automation Servers
Looking for alternatives to Unity CLI Loop? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Unity CLI Loop in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Unity CLI Loop?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.