better-godot-mcp
18 composite tools for structured Godot 4.x interaction: scenes, nodes, GDScript, shaders, animation, tilemap, physics, and more.
README
Better Godot MCP
Composite MCP Server for Godot Engine - Optimized for AI Agents
Why "Better"?
18 composite tools that consolidate Godot Engine operations into action-based mega-tools optimized for AI agents.
Key Features
| Feature | Description |
|---|---|
| Composite Actions | 1 tool call instead of multiple steps |
| Full Scene Control | Create, parse, modify .tscn files directly |
| GDScript CRUD | Create, read, write, attach scripts |
| Shader Support | Create, edit shaders with Godot 4 syntax |
| Input Mapping | Manage input actions and events |
| Physics/Audio/Nav | Configure collision layers, audio buses, navigation |
| Token Efficient | Tiered descriptions with on-demand help tool |
Quick Start
Option 1: Package Manager (Recommended)
{
"mcpServers": {
"better-godot": {
"command": "bun",
"args": ["x", "@n24q02m/better-godot-mcp@latest"]
}
}
}
Alternatively, you can use npx, pnpm dlx, or yarn dlx:
| Runner | command |
args |
|---|---|---|
| npx | npx |
["-y", "@n24q02m/better-godot-mcp@latest"] |
| pnpm | pnpm |
["dlx", "@n24q02m/better-godot-mcp@latest"] |
| yarn | yarn |
["dlx", "@n24q02m/better-godot-mcp@latest"] |
Option 2: Docker
{
"mcpServers": {
"better-godot": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"--name", "mcp-godot",
"n24q02m/better-godot-mcp:latest"
]
}
}
}
Note: Project path is passed via tool parameters (
project_path), not environment variables.
Tools
| Tool | Actions |
|---|---|
project |
info, version, run, stop, settings_get, settings_set, export |
scenes |
create, list, info, delete, duplicate, set_main |
nodes |
add, remove, rename, list, set_property, get_property |
scripts |
create, read, write, attach, list, delete |
editor |
launch, status |
setup |
detect_godot, check |
config |
status, set |
help |
Get full documentation for any tool |
resources |
list, info, delete, import_config |
input_map |
list, add_action, remove_action, add_event |
signals |
list, connect, disconnect |
animation |
create_player, add_animation, add_track, add_keyframe, list |
tilemap |
create_tileset, add_source, set_tile, paint, list |
shader |
create, read, write, get_params, list |
physics |
layers, collision_setup, body_config, set_layer_name |
audio |
list_buses, add_bus, add_effect, create_stream |
navigation |
create_region, add_agent, add_obstacle |
ui |
create_control, set_theme, layout, list_controls |
Token Optimization
Tiered descriptions for efficient token usage:
| Tier | Purpose | When |
|---|---|---|
| Tier 1 | Compressed descriptions | Always loaded |
| Tier 2 | Full docs via help tool |
On-demand |
{"name": "help", "tool_name": "scenes"}
Environment Variables
| Variable | Required | Description |
|---|---|---|
GODOT_PROJECT_PATH |
No | Default project path (most tools accept project_path param) |
GODOT_PATH |
No | Path to Godot binary (auto-detected if not set) |
Limitations
- Requires Godot 4.x project structure
- Scene files (
.tscn) are parsed/modified via text manipulation, not Godot's internal API run/stop/exportactions require Godot binary to be installed- Docker mode has limited filesystem access (mount your project directory)
Build from Source
git clone https://github.com/n24q02m/better-godot-mcp
cd better-godot-mcp
mise run setup
bun run build
Requirements: Node.js 24+, bun latest
Compatible With
Also by n24q02m
| Server | Description | Install |
|---|---|---|
| better-notion-mcp | Notion API for AI agents | npx -y @n24q02m/better-notion-mcp@latest |
| wet-mcp | Web search, content extraction, library docs | uvx --python 3.13 wet-mcp@latest |
| mnemo-mcp | Persistent AI memory with hybrid search | uvx mnemo-mcp@latest |
| better-email-mcp | Email (IMAP/SMTP) for AI agents | npx -y @n24q02m/better-email-mcp@latest |
Contributing
See CONTRIBUTING.md
License
MIT - See LICENSE
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.