- Home
- MCP servers
- Godot
Godot
- python
23
GitHub Stars
python
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"dokujaa-godot-mcp": {
"command": "/path/to/your/godot-mcp/python/venv/bin/python",
"args": [
"/path/to/your/godot-mcp/python/server.py"
],
"env": {
"ENV": "{}",
"MESHY_API_KEY": "msy-abc123"
}
}
}
}You can use this MCP server to let Claude Desktop control and interact with the Godot Editor. It provides a bridge between Claude’s prompts and the Godot Engine, enabling you to automate tasks, generate scenes, and drive editor actions from your prompts.
How to use
Connect with Claude Desktop and enable the Godot MCP server to start issuing commands to the Godot Editor. You will typically start the local server, then configure Claude Desktop to reference that server so you can prompt for editor actions, scene generation, and dynamic interactions.
How to install
Prerequisites: you need Godot Engine (4.x or later), Python 3.8+, Claude Desktop, and an optional Meshy API account for AI-generated meshes.
STEP 0: Clone the repository and navigate to the directory.
git clone https://github.com/Dokujaa/Godot-MCP.git
STEP 1: Install the Godot Plugin.
-
Copy the addons/godot_mcp/ folder to your Godot project's addons/ directory.
-
Open your Godot project.
-
Go to Project → Project Settings → Plugins.
-
Enable the "Godot MCP" plugin.
-
You should see an MCP panel appear at the bottom of the editor.
-
The plugin automatically starts listening on a port.
STEP 2: Set up Python Environment.
- Navigate to the python/ directory.
cd python
- Create and activate a virtual environment.
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies.
pip install -r ../requirements.txt
Config Claude Desktop
Configure Claude Desktop to connect to the Godot MCP server by adding the MCP entry for Godot.
{
"mcpServers": {
"godot": {
"command": "/path/to/your/godot-mcp/python/venv/bin/python",
"args": ["/path/to/your/godot-mcp/python/server.py"],
"env": {}
}
}
}
Optional: Set up Meshy API
If you want AI-generated meshes, you can sign up for a Meshy API account and obtain an API key to enable mesh generation within Godot.
-
Sign up for a Meshy API account at the Meshy API site.
-
Get your API key from the dashboard. It starts with msy- and followed by random characters.
-
Set up the API key using one of these methods.
Option A: Using a .env file (Recommended)
# Copy the example file
cp python/.env.example python/.env
# Edit the .env file and add your API key
nano python/.env # or your preferred editor
Notes on prerequisites and startup
- The Godot MCP plugin begins listening on a port automatically when enabled in the Godot editor. You will use the configured Python server to handle requests from Claude Desktop.
Available tools
Meshy API integration
Integrates the Meshy API to generate dynamic meshes and scenes within Godot based on prompts or procedural instructions.
Godot MCP plugin listener
Provider component that runs inside Godot to expose MCP endpoints and keep a port open for Claude Desktop interactions.