Unity MCP 統合フレームワーク

Created By
isuzu-shiranuia year ago
Unity Editor integration with Model Context Protocol (MCP) enabling AI assistants like Claude to interact with Unity projects. Features a TypeScript MCP server and C# Unity plugin with extensible command handler architecture, TCP/IP communication, and dynamic plugin discovery.
Overview

What is Unity MCP?

Unity MCP is an integration framework that allows AI assistants, such as Claude, to interact with Unity projects through the Model Context Protocol (MCP). It features a TypeScript MCP server and a C# Unity plugin with an extensible command handler architecture.

How to use Unity MCP?

To use Unity MCP, install it via the Unity Package Manager, configure the connection settings, and start the server to enable communication between Unity and external AI services.

Key features of Unity MCP?

  • Extensible plugin architecture for custom command handlers
  • Seamless integration with AI models using MCP
  • Support for TypeScript and C# components
  • Editor tool functionality with customizable settings
  • Automatic discovery and registration of command handlers
  • TCP/IP communication between Unity and external AI services

Use cases of Unity MCP?

  1. Enabling AI-driven interactions within Unity projects.
  2. Creating custom command handlers for specific functionalities.
  3. Facilitating communication between Unity and AI models for enhanced game development.

FAQ from Unity MCP?

  • What are the system requirements for Unity MCP?

Unity 2023.2.19f1 or higher, .NET/C# 9.0, and Node.js 18.0.0 or higher are required.

  • Is Unity MCP free to use?

Yes! Unity MCP is open-source and available under the MIT license.

  • Can I create custom command handlers?

Yes! Unity MCP allows you to create and register custom command handlers easily.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
isuzu-shiranui
Star
49
Language
C#
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

4 hours ago