原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

AI Game Developer: MCP for Unity, Unreal and Godot

作者:IvanMurzak版本 9.3.2i★ –i电脑或云端
注册名称io.github.IvanMurzak/Unity-MCP

安装

概览

作者提供的说明(英文原文)

Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:3 项中通过 3 项
  • 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
  • 需要你自己填写: MCP_PLUGIN_PORT, MCP_PLUGIN_CLIENT_TIMEOUT, MCP_PLUGIN_TOOL_TIMEOUT, MCP_PLUGIN_CLIENT_TRANSPORT, MCP_AUTH, MCP_AUTH_ISSUER, MCP_PUBLIC_URL, MCP_BIND, MCP_ALLOWED_ORIGINS

你需要

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://ai-game.dev/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "unity": {
      "command": "dnx",
      "args": [
        "com.IvanMurzak.GameDev.MCP.Server",
        "--yes"
      ],
      "env": {
        "MCP_PLUGIN_PORT": "your-value",
        "MCP_PLUGIN_CLIENT_TIMEOUT": "your-value",
        "MCP_PLUGIN_TOOL_TIMEOUT": "your-value",
        "MCP_PLUGIN_CLIENT_TRANSPORT": "your-value",
        "MCP_AUTH": "your-value",
        "MCP_AUTH_ISSUER": "your-value",
        "MCP_PUBLIC_URL": "your-value",
        "MCP_BIND": "your-value",
        "MCP_ALLOWED_ORIGINS": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http unity https://ai-game.dev/mcp

或者在你的电脑上运行

claude mcp add unity --env MCP_PLUGIN_PORT=your-value --env MCP_PLUGIN_CLIENT_TIMEOUT=your-value --env MCP_PLUGIN_TOOL_TIMEOUT=your-value --env MCP_PLUGIN_CLIENT_TRANSPORT=your-value --env MCP_AUTH=your-value --env MCP_AUTH_ISSUER=your-value --env MCP_PUBLIC_URL=your-value --env MCP_BIND=your-value --env MCP_ALLOWED_ORIGINS=your-value -- dnx com.IvanMurzak.GameDev.MCP.Server --yes

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "unity": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "unity": {
      "command": "dnx",
      "args": [
        "com.IvanMurzak.GameDev.MCP.Server",
        "--yes"
      ],
      "env": {
        "MCP_PLUGIN_PORT": "your-value",
        "MCP_PLUGIN_CLIENT_TIMEOUT": "your-value",
        "MCP_PLUGIN_TOOL_TIMEOUT": "your-value",
        "MCP_PLUGIN_CLIENT_TRANSPORT": "your-value",
        "MCP_AUTH": "your-value",
        "MCP_AUTH_ISSUER": "your-value",
        "MCP_PUBLIC_URL": "your-value",
        "MCP_BIND": "your-value",
        "MCP_ALLOWED_ORIGINS": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "unity": {
      "type": "http",
      "url": "https://ai-game.dev/mcp"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "unity": {
      "type": "stdio",
      "command": "dnx",
      "args": [
        "com.IvanMurzak.GameDev.MCP.Server",
        "--yes"
      ],
      "env": {
        "MCP_PLUGIN_PORT": "your-value",
        "MCP_PLUGIN_CLIENT_TIMEOUT": "your-value",
        "MCP_PLUGIN_TOOL_TIMEOUT": "your-value",
        "MCP_PLUGIN_CLIENT_TRANSPORT": "your-value",
        "MCP_AUTH": "your-value",
        "MCP_AUTH_ISSUER": "your-value",
        "MCP_PUBLIC_URL": "your-value",
        "MCP_BIND": "your-value",
        "MCP_ALLOWED_ORIGINS": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://ai-game.dev/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • MCP_PLUGIN_PORT env
    Client -> Server <- Plugin connection port (default: 8080)
  • MCP_PLUGIN_CLIENT_TIMEOUT env
    Plugin -> Server connection timeout (ms) (default: 10000). Tool calls use MCP_PLUGIN_TOOL_TIMEOUT instead.
  • MCP_PLUGIN_TOOL_TIMEOUT env
    How long one tool call may run in the plugin (ms). A tool call is sent once and never re-sent (default: 300000, or MCP_PLUGIN_CLIENT_TIMEOUT if larger)
  • MCP_PLUGIN_CLIENT_TRANSPORT env
    Client -> Server transport type: stdio or streamableHttp (default: stdio)
  • MCP_AUTH env
    Authentication mode: none or oauth. Default depends on transport: stdio -> none (offline/local/CI), streamableHttp -> oauth when MCP_AUTH_ISSUER + MCP_PUBLIC_URL are set, otherwise none. oauth valida…
  • MCP_AUTH_ISSUER env
    OAuth authorization-server URL (e.g. https://ai-game.dev). Required when MCP_AUTH=oauth.
  • MCP_PUBLIC_URL env
    This server's canonical public resource URL (its token audience, e.g. https://ai-game.dev/mcp). Required when MCP_AUTH=oauth; also seeds the Origin allow-list.
  • MCP_BIND env
    Network bind address: loopback (default), any (0.0.0.0), or a specific IP. Hosted deploys reachable by a reverse proxy set MCP_BIND=0.0.0.0.
  • MCP_ALLOWED_ORIGINS env
    Comma/semicolon-separated additional allowed Origins for browser clients (in addition to loopback + the MCP_PUBLIC_URL origin). Avoids a blanket wildcard on credentialed paths.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

服务器要求先登录,才会列出它的工具。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 IvanMurzak 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • ✓ 通过

    端点有响应

    在 582 毫秒内响应(HTTP 401)

  • ✓ 通过

    使用 OAuth 登录

    声明支持 OAuth 登录,你的 AI 应用可以带你去登录

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32620 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32620 个服务器的 89% 更新
  • 基础检查结果等于或优于此分类中其他 32620 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

AI Game Developer: MCP for Unity, Unreal and Godot 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(9.3.2)于4天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, Intervals MCP

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211前天更新
安装

Intervals MCP

作者:ljcl

Remote MCP server for intervals.icu run data and analysis

在你的电脑上运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

✨ AI Game Developer — Unity SKILLS, MCP

中文 | 日本語 | Español

Unity MCP is an AI-powered game development assistant for Editor & Runtime. Connect Claude, Cursor, & Windsurf to Unity via MCP. Automate workflows, generate code, and enable AI within your games.

Unlike other tools, this plugin works inside your compiled game, allowing for real-time AI debugging and player-AI interaction.

[💬 Join our Discord Server](https://discord.gg/cfbdMZX99G) - Ask questions, showcase your work, and connect with other developers!

##

  • ✔️ AI agents - Use the best agents from Anthropic, OpenAI, Microsoft, or any other provider with no vendor lock-in
  • ✔️ Tools - A wide range of default MCP Tools for operating in Unity Editor
  • ✔️ Skills - Generate skills for AI based on operating system, Unity version, plugins in the project
  • ✔️ Code and Tests - Develop game mechanics and test them with AI agents
  • ✔️ Runtime (in-game) - Use LLMs directly inside your compiled game for dynamic NPC behavior or debugging
  • ✔️ Debug support - Let AI debug and fix the problems in a project
  • ✔️ Natural conversation - Chat with AI like you would with a human
  • ✔️ Flexible deployment - Works locally (stdio) and remotely (http) via configuration
  • ✔️ Extensible - Create custom Tools in your project code

https://github.com/user-attachments/assets/228baf4d-4f00-4dce-939d-fb985ebdd8dd

OR use cli
# 1. Install unity-mcp-cli

npm install -g unity-mcp-cli

2. Install "AI Game Developer" in Unity project

unity-mcp-cli install-plugin ./MyUnityProject

3. Sign in to ai-game.dev (opens your browser — OAuth device flow)

unity-mcp-cli login

4. Open Unity project (auto-connects and generates skills)

unity-mcp-cli open ./MyUnityProject

Quick Start

Get up and running in three steps:

  1. [Install plugin](#step-1-install-unity-mcp-plugin) — download the .unitypackage installer or run openupm add com.ivanmurzak.unity.mcp

Alternative: npx unity-mcp-cli install-plugin ./MyUnityProject — see CLI documentation

  1. [Pick an AI agent](#step-2-install-ai-agent) — Claude Code, Claude Desktop, GitHub Copilot, Cursor, or any other
  2. [Setup AI agent](#step-3-configure-ai-agent) — open Window/AI Game Dev in Unity and click Auto-generate skills (recommended) or Configure MCP

Alternative: npx unity-mcp-cli setup-skills claude-code ./MyUnityProject — see CLI documentation

That's it. Ask your AI *"Create 3 cubes in a circle with radius 2"* and watch it happen. ✨


Skills and Tools Reference

Since 1.0.0 the plugin exposes a small set of tools, and most Editor work goes through RQL, a query language over the Editor's data: rql-query reads, rql-mutate changes, and rql-schema describes the sources, types and calls (start there when unsure). The one-tool-per-action tools of earlier versions (gameobject-create, scene-save, console-get-logs and others) were replaced by RQL in #1017. See docs/default-mcp-tools.md for the full reference.

🧰 Browse the full MCP tools registry online: ai-game.dev/docs/tools

Shown to the AI agent by default: rql-query, rql-mutate, rql-schema, screenshot-isolated, script-execute, tests-run, unity-tool-list. The other tools are installed but hidden from the agent's tool list (a hidden tool still runs when called by name). Show them with tool-set-visibility, in the AI Game Developer window, or with unity-mcp-cli configure --enable-tools .

RQL (scenes, GameObjects, components, assets, console, editor)

  • rql-query - Read Editor data with an RQL query, e.g. roots | recurse children | select name active
  • rql-mutate - Change Editor data or call Editor operations, e.g. editor | call CreateGameObject({name: "Ground", primitive: "Plane"})
  • rql-schema - Describe the sources, types, members and calls RQL can use, and print the topic guides
  • Sources: scenes, roots, objects (every GameObject in the loaded scenes), selection, prefab (the prefab open in prefab mode), editor (create GameObjects, materials, folders and scenes; open and save scenes and prefabs; copy, move and delete assets; execute menu items; …), settings, console (captured Editor log entries), shaders, componentTypes, tests, testResults, profiler, lighting; assets by path with unity.asset("Assets/…")

Screenshots

  • screenshot-isolated - Render a GameObject in isolation from a chosen angle (optional composite 2x2 view)
  • screenshot-scene-view - Captures a screenshot from the Unity Editor Scene View (hidden by default)
  • screenshot-game-view - Captures a screenshot from the Unity Editor Game View (hidden by default)
  • screenshot-camera - Captures a screenshot from a camera and returns it as an image (hidden by default)

Scripting, tests and packages

  • script-execute - Compiles and executes C# code dynamically using Roslyn
  • script-read - Reads the content of a script file (hidden by default)
  • script-update-or-create - Updates or creates script file with the provided C# code (hidden by default)
  • script-delete - Delete the script file(s) (hidden by default)
  • tests-run - Execute Unity tests (EditMode/PlayMode): any RQL selection over the tests source as one run, results filtered with RQL
  • package-list, package-search, package-add, package-remove - Unity Package Manager packages (hidden by default)

Tool management

  • unity-tool-list - List every tool and whether the agent sees it
  • tool-set-visibility - Show or hide tools in the agent's tool list (hidden by default)
  • tool-set-enabled-state - Deprecated alias of tool-set-visibility (hidden by default)

Profiling & Diagnostics

  • RQL source profiler (via rql-query / rql-mutate) - memory, rendering, script and frame snapshots, module f

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx