Godot MCP
Enables AI assistants to fully access and manipulate Godot editor projects, including scenes, scripts, nodes, and settings, with an interactive visualizer.
README
Godot MCP
Give your AI assistant full access to the Godot editor.
Build games faster with Claude, Cursor, or any MCP-compatible AI — no copy-pasting, no context switching. AI reads, writes, and manipulates your scenes, scripts, nodes, and project settings directly.
Godot 4.x · 42 tools · Interactive project visualizer · MIT license
Quick Start
0. Install Node.js (one-time setup)
Download and run the installer from nodejs.org (LTS version). It's a standard installer — no terminal needed.
1. Install the Godot plugin
Inside the Godot editor, click the AssetLib tab at the top → search "mcp" → find "Godot AI Assistant tools MCP" → Install.
Then go to Project → Project Settings → Plugins and enable the Godot MCP plugin.
2. Add the server config to your AI client
Claude Desktop — Settings → Developer → Edit Config → open the config file and paste:
Mac / Linux:
{
"mcpServers": {
"godot": {
"command": "npx",
"args": ["-y", "godot-mcp-server"]
}
}
}
Windows:
{
"mcpServers": {
"godot": {
"command": "cmd",
"args": ["/c", "npx", "-y", "godot-mcp-server"]
}
}
}
Cursor — Settings → MCP → Add Server:
Mac / Linux:
{
"mcpServers": {
"godot": {
"command": "npx",
"args": ["-y", "godot-mcp-server"]
}
}
}
Windows:
{
"mcpServers": {
"godot": {
"command": "cmd",
"args": ["/c", "npx", "-y", "godot-mcp-server"]
}
}
}
Claude Code — run in terminal:
claude mcp add godot -- npx -y godot-mcp-server
Works with any MCP-compatible client (Cline, Windsurf, etc.)
3. Restart your AI client
Close and reopen Claude Desktop / Cursor / your client so it picks up the new config.
4. Restart your Godot project
Hit Restart Project in the Godot editor. Check the top-right corner — you should see MCP Connected in green. You're ready to go.
What Can It Do?
42 Tools Across 6 Categories
| Category | Tools | Examples |
|---|---|---|
| File Operations | 4 | Browse directories, read files, search project, create scripts |
| Scene Operations | 11 | Create scenes, add/remove/move nodes, set properties, attach scripts, assign collision shapes and textures |
| Script Operations | 6 | Apply code edits, validate syntax, rename/move files with reference updates |
| Project Tools | 14 | Run/stop scenes, query ClassDB, read errors from Output + Debugger, project settings, input map, collision layers, scene tree dumps, rescan filesystem |
| Asset Generation | 1 | Generate 2D sprites from SVG |
| Visualization | 6 | Interactive browser-based project map, scene graph explorer |
Interactive Visualizer
Run map_project and get a browser-based explorer at localhost:6510:
- Force-directed graph of all scripts and their relationships
- Click any script to see variables, functions, signals, and connections
- Edit code directly in the visualizer — changes sync to Godot in real time
- Scene view with node property editing
- Find usages before refactoring <img width="1710" height="1107" alt="image" src="https://github.com/user-attachments/assets/a9faf163-8b8b-43da-93ec-c7a651e8ac60" />
Limitations
AI cannot create 100% of a game by itself — it struggles with complex UI layouts, compositing scenes, and some node property manipulation. It's still in active development, so feedback is very welcome!
Architecture
┌─────────────┐ MCP (stdio) ┌──────────────┐ WebSocket ┌──────────────┐
│ AI Client │◄────────────────►│ MCP Server │◄─────────────►│ Godot Editor │
│ (Claude, │ │ (Node.js) │ port 6505 │ (Plugin) │
│ Cursor) │ │ │ │ │
└─────────────┘ │ Visualizer │ │ 42 tool │
│ HTTP :6510 │ │ handlers │
└──────┬───────┘ └──────────────┘
│
┌──────▼───────┐
│ Browser │
│ Visualizer │
└──────────────┘
Current Limitations
- Local only — runs on localhost, no remote connections
- Single connection — one Godot instance at a time
- No undo — changes save directly (use version control)
- AI is still limited in Godot knowledge — it can't create 100% of the game alone, but it can help debug, write scripts, and tag along for the journey
Development
To build from source instead of using npm:
cd mcp-server
npm install
npm run build
Then point your AI client at mcp-server/dist/index.js instead of using npx.
Release notes
Narrative write-ups of each release live in release-notes/ (starting with v0.5.0). For the full change history, see CHANGELOG.md.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。