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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.