What are the prerequisites for using Unity MCP Integration?
You need Unity 2021.3 or later and Node.js 18+ to run the MCP server. The server is written in TypeScript 5.0.
@quazaai
基本情報
Access real-time information about your Unity project
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"unity-mcp-server": {
"command": "node",
"args": [
"<path-to-project>/mcpServer/build/index.js"
]
}
}
}Get comprehensive information about the Unity project and editor state
Get detailed information about the current scene
Get information about specific GameObjects in the scene
Execute C# code directly in the Unity Editor
Retrieve and filter Unity console logs
Unity MCP Integration is a package that connects the Model Context Protocol (MCP) to the Unity Editor, enabling AI assistants to access real-time information about project scenes, execute C# code directly in the Editor, monitor logs, and control play mode. It is built for Unity developers who want to leverage AI within their Unity workflow.
Install the Unity package via the Package Manager using the Git URL or import the custom package. Then, navigate to the mcpServer directory, run npm install and node build/index.js to start the MCP server, or add the server configuration to your MCP Host. Use the MCP Debug window (Window > MCP Debug) to monitor the connection and test features.
You need Unity 2021.3 or later and Node.js 18+ to run the MCP server. The server is written in TypeScript 5.0.
The Unity plugin (C#) and the MCP server (TypeScript/Node.js) communicate via WebSocket, exchanging JSON messages for commands and data.
Available tools include `get_editor_state`, `get_current_scene_info`, `get_game_objects_info`, `execute_editor_command`, and `get_logs`.
Yes. Fork the repository, create a feature branch, make changes, and open a pull request. Development setup instructions for both Unity and server sides are provided in the README.
Add the server to your MCP Host configuration with the command `node` and arguments pointing to the built `index.js` file, as shown in the README’s configuration example.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
A search tool helps dev to solve the naming things problem.
MCP Toolbox for Databases is an open source MCP server for databases.
コメント