AgentHubAgentHub

AI Game Developer: MCP for Unity, Un… MCP Setup & Guide

MCP ServerMCP RegistryOfficial

io.github.IvanMurzak/Unity-MCP · v9.3.2

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

Copy the install config on this page first, then verify docs and permissions upstream.

Overview

Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors. AI Game Developer: MCP for Unity, Unreal and Godot is a MCP Server listed from MCP Registry. Transports: streamable-http, stdio. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.

Use cases

AgentHub Verified AvailabilityTested & Ready

Automated pipeline validated install commands, protocol & client compatibility

Verified At2026-11-22
Install Snippets TestedCLI & JSON config syntax verified
Protocol Handshake ReadyComplies with JSON-RPC 2.0 specifications
Origin Registry ActiveSourced from official-mcp-registry
Verified ClientsClaude Code、Claude Desktop、Cursor 等
Security Tier: A+ 级 · 官方认证推荐 (A+)·Maintained by official/verified teams, audited for standard MCP protocol compliance.

Copy by platform

Choose your platform

  1. Open or create .cursor/mcp.json in your project root
  2. Click Copy config and paste; if you already have MCPs, merge only this entry under mcpServers
  3. Save, then Cmd+Shift+P (Ctrl+Shift+P on Windows) → Reload Window

Pre-fill Environment Variables (Optional)

Privacy Guarantee: Keys are replaced 100% locally in your browser memory and are NEVER uploaded or stored on any server.
Click to copy snippet
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Setup tutorial

  1. Open the AI Game Developer: MCP for Unity, Unreal and Godot page and confirm this MCP Server (source: MCP Registry).
  2. Copy the Cursor, Claude Code, or VS Code snippet.
  3. Merge it into mcpServers and replace env placeholders with real secrets.
  4. Reload the window, then call the MCP tools from your agent chat.

Install commands

Install commands and setup steps are in the HTML so search engines and no-JS browsers can read them without running client JavaScript.

Claude Code (remote)

  1. Install Claude Code CLI (claude must work in your terminal)
  2. Click Copy config below, paste into terminal, and run
  3. Restart Claude Code after it succeeds
claude mcp add --transport http Unity-MCP https://ai-game.dev/mcp

Cursor — .cursor/mcp.json (remote)

  1. Open or create .cursor/mcp.json in your project root
  2. Click Copy config and paste; if you already have MCPs, merge only this entry under mcpServers
  3. Save, then Cmd+Shift+P (Ctrl+Shift+P on Windows) → Reload Window
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

VS Code — .vscode/mcp.json (remote)

  1. Install GitHub Copilot in VS Code with MCP support
  2. Open or create .vscode/mcp.json in your project root
  3. Click Copy config and paste; merge only this mcpServers entry if others exist
  4. Save and Developer: Reload Window
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Claude Desktop — claude_desktop_config.json (remote)

  1. Open Claude Desktop config: macOS ~/Library/Application Support/Claude/claude_desktop_config.json; Windows %APPDATA%\Claude\claude_desktop_config.json
  2. Click Copy config and merge under mcpServers
  3. Fully quit and restart Claude Desktop
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Trae — .trae/mcp.json (remote)

  1. Trae → Settings → MCP, or edit .trae/mcp.json (project) / global mcp.json
  2. Use Manual add / Raw JSON, click Copy config and paste; merge only this mcpServers entry
  3. Save, pick an MCP-capable agent (e.g. Builder with MCP), reload window if needed
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Cherry Studio — MCP settings (remote)

  1. Cherry Studio → Settings → MCP Servers
  2. Add via JSON import or SSE/HTTP with the URL
  3. Click Copy config, paste the mcpServers entry, then enable the server
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Tongyi Lingma — MCP config (remote)

  1. Tongyi Lingma: avatar → Settings → MCP (agent mode; plugin ~v2.5+)
  2. Click + → config file or manual SSE/HTTP with the service URL
  3. Click Copy config and merge JSON; a healthy icon means connected
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Cline — MCP Servers (remote)

  1. VS Code Cline panel → settings gear → MCP Servers
  2. Click Copy config and paste the mcpServers entry into Cline
  3. Save; Cline reconnects and shows tools
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

WorkBuddy — .workbuddy/mcp.json (remote)

  1. WorkBuddy: sidebar Plugins → MCP Servers → Configure MCP; or edit ~/.workbuddy/mcp.json (user) / .workbuddy/mcp.json (project)
  2. Click Copy config and merge under mcpServers (Tencent WorkBuddy / CodeBuddy)
  3. Save; status should turn green — fully restart the client if needed
{
  "mcpServers": {
    "Unity-MCP": {
      "url": "https://ai-game.dev/mcp"
    }
  }
}

Windsurf — mcp_config.json (remote)

  1. Edit ~/.codeium/windsurf/mcp_config.json (Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json)
  2. Click Copy config and merge; remote MCP must use serverUrl (not url)
  3. Save and refresh MCP in Windsurf Cascade
{
  "mcpServers": {
    "Unity-MCP": {
      "serverUrl": "https://ai-game.dev/mcp"
    }
  }
}

Troubleshooting & Common ErrorsFAQ

Common connection errors and verified fixes for AI Game Developer: MCP for Unity, Unreal and Godot

Getting 'connection closed' or exit code 1 in Cursor / Claude Code for AI Game Developer: MCP for Unity, Unreal and Godot?

Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.

Fix Snippet
# Check binary path in terminal:
which npx
node -v
Getting 'spawn npx ENOENT' or 'command not found'?

The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).

Missing required environment variable or authentication failure?

AI Game Developer: MCP for Unity, Unreal and Godot requires environment variables (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). Ensure you have added valid keys under the 'env' object in your config file without trailing whitespace.

Fix Snippet
// .cursor/mcp.json 或 claude_desktop_config.json
{
  "env": {
    "API_KEY": "your_actual_key_here"
  }
}

Tool Mock Playground

Sandbox

AI Game Developer: MCP for Unity, Unreal and Godot Tool Interface Simulation · Preview tool schema & outputs without local runtime

Sandbox Ready
fn: unity_mcpExecute the core tool interface of AI Game Developer: MCP for Unity, Unreal and Godot
Request ArgumentsJSON Schema
{
  "target": "AI Game Developer: MCP for Unity, Unreal and Godot",
  "action": "execute",
  "options": {
    "mode": "standard",
    "timeoutMs": 5000
  }
}
💡Parameters generated dynamically by Agent runtime
Agent Tool Output

Click 'Run Mock' above

to preview the raw response returned to the LLM

Env: AgentHub Virtual SandboxJSON-RPC 2.0

Decision Guide: Why & When to Use

Assess suitability before installing to save trial-and-error time

Best Suited For
  • PR review
  • Changelog generation
  • Cross-repo issue search
When NOT to Use
  • Replacing human security audit
  • Unauthorized repo access
Recommended Workflow Pairing:View Scenario →

AI Game Developer: MCP for Unity, Unreal and Godot + Scenario Prompt → Complete Agent Automation

MCP hands-on: install to visible results

Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.

Open tutorial →

Related resources

Often paired with

insurance-advisor-china

v2.4.21

SkillClawHub7410.3k

io.clawhub.mnetfairy/insurance-advisor-china

中国大陆AI保险顾问。为个人和家庭提供全方位的保险咨询、产品对比、方案设计、投保指导。当用户询问保险配置、保险方案、产品对比、重疾险/医疗险/寿险/意外险/储蓄险推荐、保费计算、保障缺口分析、需求分析、核保合规、理赔等问题时使用。发布产物仅含 SKILL.md + 3 个只读参考文件(references/products.json、insurance-knowledge.md、compliance.md)+ 3 个运行时脚本(needs_analyzer / premium_calculator / plan_designer);数据清洗脚本与回归测试脚本是本地维护工具,不随发布产物分发。

source

ai-insurance-advisor

v2.4.21

SkillClawHub8110.4k

io.clawhub.mnetfairy/ai-insurance-advisor

中国大陆保险顾问。本 skill 覆盖 8 项能力:保险需求分析(needs_analyzer.py)、产品对比(premium_calculator.py + 本地 products.json)、保费计算(premium_calculator.py)、方案设计(plan_designer.py)、保险知识问答(insurance-knowledge.md)、合规要点提示(compliance.md)、朋友圈/社交营销文案生成(agent LLM 生成,无专属脚本)、培训话术支持(agent LLM 生成,无专属脚本)。不提供核保预审、理赔代办、代理人展业工具等能力——这些场景请转人工或调用专业服务。发布产物仅含 SKILL.md + 3 个只读参考文件 + 3 个运行时脚本(needs_analyzer / premium_calculator / plan_designer);数据清洗与回归测试脚本为本地维护工具,不随发布产物分发。

source

中文公文写作

v2.0.63

SkillClawHub7412k

io.clawhub.gongyu0918-debug/chinese-official-writing

用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。

source

Keep exploring AgentHub

Most people compare similar tools or check scenario guides before installing—start here.

Listing badge: put AgentHub on your site

Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.

PreviewListed on AgentHub: AI Game Developer: MCP for Unity, Unreal and Godot
HTML
<a href="https://myagenthub.cn/p/io.github.IvanMurzak/Unity-MCP" title="Listed on AgentHub: AI Game Developer: MCP for Unity, Unreal and Godot" target="_blank" rel="noopener">
  <img src="https://myagenthub.cn/badge/io.github.IvanMurzak/Unity-MCP?lang=en" alt="Listed on AgentHub: AI Game Developer: MCP for Unity, Unreal and Godot" height="20" style="border:0"/>
</a>
Markdown (GitHub README)
[![Listed on AgentHub: AI Game Developer: MCP for Unity, Unreal and Godot](https://myagenthub.cn/badge/io.github.IvanMurzak/Unity-MCP?lang=en)](https://myagenthub.cn/p/io.github.IvanMurzak/Unity-MCP)

Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.

Unified Manifest

{
  "id": "io.github.IvanMurzak/Unity-MCP",
  "type": "mcp-server",
  "version": "9.3.2",
  "displayName": "AI Game Developer: MCP for Unity, Unreal and Godot",
  "description": "Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.",
  "repository": {
    "url": "https://github.com/IvanMurzak/Unity-MCP",
    "source": "github"
  },
  "homepage": "https://ai-game.dev",
  "distribution": {
    "packages": [
      {
        "registryType": "nuget",
        "identifier": "com.IvanMurzak.GameDev.MCP.Server",
        "version": "9.3.2",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "MCP_PLUGIN_PORT",
            "description": "Client -> Server <- Plugin connection port (default: 8080)"
          },
          {
            "name": "MCP_PLUGIN_CLIENT_TIMEOUT",
            "description": "Plugin -> Server connection timeout (ms) (default: 10000). Tool calls use MCP_PLUGIN_TOOL_TIMEOUT instead."
          },
          {
            "name": "MCP_PLUGIN_TOOL_TIMEOUT",
            "description": "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)"
          },
          {
            "name": "MCP_PLUGIN_CLIENT_TRANSPORT",
            "description": "Client -> Server transport type: stdio or streamableHttp (default: stdio)"
          },
          {
            "name": "MCP_AUTH",
            "description": "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 validates ES256 JWTs (via cached JWKS) issued by MCP_AUTH_ISSUER, audienced to MCP_PUBLIC_URL."
          },
          {
            "name": "MCP_AUTH_ISSUER",
            "description": "OAuth authorization-server URL (e.g. https://ai-game.dev). Required when MCP_AUTH=oauth."
          },
          {
            "name": "MCP_PUBLIC_URL",
            "description": "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."
          },
          {
            "name": "MCP_BIND",
            "description": "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."
          },
          {
            "name": "MCP_ALLOWED_ORIGINS",
            "description": "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."
          }
        ]
      }
    ],
    "remotes": [
      {
        "transport": "streamable-http",
        "url": "https://ai-game.dev/mcp"
      }
    ]
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode",
    "trae",
    "cherry-studio",
    "lingma",
    "windsurf",
    "cline",
    "workbuddy"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.IvanMurzak/Unity-MCP",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.IvanMurzak%2FUnity-MCP/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}
AI Game Developer: MCP for Unity, Un… MCP Setup - AgentHub