Godot MCP Toolkit
Enables AI assistants to automate Godot 4 projects via headless tooling, live editor control, and runtime remote control, including scene building, testing, and observation.
README
Godot MCP Toolkit
Godot MCP Toolkit is a practical MCP server for Godot 4 automation.
Project home: https://github.com/woyucbugongdaitian/godot-mcp-toolkit It combines safe headless project tools with an optional live Editor Bridge and Runtime Agent, so AI assistants can inspect, build, run, test, and iterate on Godot projects.
Highlights
- Headless project automation — create projects and scenes, edit nodes and resources, write GDScript, run checks, capture screenshots, and execute automation tests.
- Live editor control — bind one MCP conversation to one Godot editor for undoable scene edits, Inspector changes, selections, scripts, UI, 2D/3D authoring, animation, navigation, physics, audio, themes, plugins, and workspace controls.
- Runtime remote control — inspect scene trees and properties, call methods, pause/resume/step, inject keyboard and pointer input, capture game views, query physics, and control AudioServer.
- Runtime observability — poll watched property changes, Runtime Agent events, log cursors, and rolling frame metrics without opening another network service.
- Stylized rendering helpers — configure 2D palette tinting or 3D filmic environments with ambient color, glow, fog, saturation, contrast, and brightness.
Quick Start
Requirements
- Node.js 18 or later.
- A Godot 4 executable. Set its path through
GODOT_BINorGODOT_PATH.
Install and build
npm.cmd install
npm.cmd run build
MCP configuration
{
"mcpServers": {
"godot-mcp-toolkit": {
"command": "node",
"args": ["E:/Tools/godot-mcp-toolkit/build/index.mjs"],
"env": {
"GODOT_PATH": "E:/Tools/Godot/Godot_v4.7-stable_win64.exe"
}
}
}
}
Use projectPath with each tool call, or set GODOT_MCP_PROJECT for a default project.
Optional Live Editor and Runtime Control
- Copy
godot/addons/godot_mcp_proto the target project'saddons/godot_mcp_prodirectory. - Enable Godot MCP Toolkit in Project Settings → Plugins.
- Set
GODOT_MCP_ENABLE_EDITOR_BRIDGE=1and, when needed,GODOT_MCP_TOOL_GROUPS=allin the MCP server environment. - Reload Godot and the MCP client.
The plugin automatically registers the Runtime Agent as an autoload. Both the editor and runtime enforce a 90-second one-to-one conversation binding; release it with release_editor_binding or release_runtime_binding when finished.
Tool Groups
| Group | Focus |
|---|---|
| Project, scenes, nodes, scripts | Safe headless project automation and CI workflows |
| Editor and advanced editor | Live Inspector, scene graph, Script Editor, 2D/3D, animation, navigation, physics, audio, themes, and workspace |
| UI and effects | UI screens/components, particles, shaders, post-process, and stylized rendering |
| Runtime | Remote game control, input, screenshots, metrics, property watches, physics, and audio |
| Resources, performance, AI | Resource inspection, profiling, automated tests, and project context |
See Capabilities, Editor Bridge setup, Multi-project usage, Compatibility, and the Roadmap.
Development
npm.cmd run check
npm.cmd test
npm.cmd run build
The test suite validates the MCP contract plus editor and runtime one-to-one binding behavior.
License
MIT. See LICENSE. This project is an independent community implementation; see NOTICE.md for attribution.
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。