Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Godot MCP run my Godot project and capture the debug output"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
((((((( (((((((
((((((((((( (((((((((((
((((((((((((( (((((((((((((
(((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((
((((( ((((((((((((((((((((((((((((((((((((((((( (((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((@@@@@@@(((((((((((((((((((((((((((@@@@@@@(((((((((((
(((((((((@@@@,,,,,@@@(((((((((((((((((((((@@@,,,,,@@@@(((((((((
((((((((@@@,,,,,,,,,@@(((((((@@@@@(((((((@@,,,,,,,,,@@@((((((((
((((((((@@@,,,,,,,,,@@(((((((@@@@@(((((((@@,,,,,,,,,@@@((((((((
(((((((((@@@,,,,,,,@@((((((((@@@@@((((((((@@,,,,,,,@@@(((((((((
((((((((((((@@@@@@(((((((((((@@@@@(((((((((((@@@@@@((((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
@@@@@@@@@@@@@((((((((((((@@@@@@@@@@@@@((((((((((((@@@@@@@@@@@@@
((((((((( @@@(((((((((((@@(((((((((((@@(((((((((((@@@ (((((((((
(((((((((( @@((((((((((@@@(((((((((((@@@((((((((((@@ ((((((((((
(((((((((((@@@@@@@@@@@@@@(((((((((((@@@@@@@@@@@@@@(((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((((((((((((((((
(((((((((((((((((((((((((((((((((
/$$ /$$ /$$$$$$ /$$$$$$$
| $$$ /$$$ /$$__ $$| $$__ $$
| $$$$ /$$$$| $$ \__/| $$ \ $$
| $$ $$/$$ $$| $$ | $$$$$$$/
| $$ $$$| $$| $$ | $$____/
| $$\ $ | $$| $$ $$| $$
| $$ \/ | $$| $$$$$$/| $$
|__/ |__/ \______/ |__/ A Model Context Protocol (MCP) server for interacting with the Godot game engine.
Godot MCP enables AI assistants to launch the Godot editor, run projects, capture debug output, and control project execution - all through a standardized interface.
This direct feedback loop helps AI assistants like Claude understand what works and what doesn't in real Godot projects, leading to better code generation and debugging assistance.
Related MCP server: Godot MCP
Launch Godot Editor: Open the Godot editor for a specific project
Run Godot Projects: Execute Godot projects in debug mode
Capture Debug Output: Retrieve console output and error messages
Control Execution: Start and stop Godot projects programmatically
Get Godot Version: Retrieve the installed Godot version
List Godot Projects: Find Godot projects in a specified directory
Project Analysis: Get detailed information about project structure
Scene Management:
Create new scenes with specified root node types
Add nodes to existing scenes with customizable properties
Load sprites and textures into Sprite2D nodes
Export 3D scenes as MeshLibrary resources for GridMap
Save scenes with options for creating variants
UID Management (for Godot 4.4+):
Get UID for specific files
Update UID references by resaving resources
Godot Engine installed on your system
Node.js and npm
An AI assistant that supports MCP (Cline, Cursor, etc.)
First, clone the repository and build the MCP server:
git clone https://github.com/Coding-Solo/godot-mcp.git
cd godot-mcp
npm install
npm run buildAdd to your Cline MCP settings file (~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json):
{
"mcpServers": {
"godot": {
"command": "node",
"args": ["/absolute/path/to/godot-mcp/build/index.js"],
"env": {
"DEBUG": "true" // Optional: Enable detailed logging
},
"disabled": false,
"autoApprove": [
"launch_editor",
"run_project",
"get_debug_output",
"stop_project",
"get_godot_version",
"list_projects",
"get_project_info",
"create_scene",
"add_node",
"load_sprite",
"export_mesh_library",
"save_scene",
"get_uid",
"update_project_uids"
]
}
}
}Using the Cursor UI:
Go to Cursor Settings > Features > MCP
Click on the + Add New MCP Server button
Fill out the form:
Name: godot (or any name you prefer)
Type: command
Command: node /absolute/path/to/godot-mcp/build/index.js
Click "Add"
You may need to press the refresh button in the top right corner of the MCP server card to populate the tool list
Using Project-Specific Configuration:
Create a file at .cursor/mcp.json in your project directory with the following content:
{
"mcpServers": {
"godot": {
"command": "node",
"args": ["/absolute/path/to/godot-mcp/build/index.js"],
"env": {
"DEBUG": "true" // Enable detailed logging
}
}
}
}You can customize the server behavior with these environment variables:
GODOT_PATH: Path to the Godot executable (overrides automatic detection)
DEBUG: Set to "true" to enable detailed server-side debug logging
Once configured, your AI assistant will automatically run the MCP server when needed. You can use prompts like:
"Launch the Godot editor for my project at /path/to/project"
"Run my Godot project and show me any errors"
"Get information about my Godot project structure"
"Analyze my Godot project structure and suggest improvements"
"Help me debug this error in my Godot project: [paste error]"
"Write a GDScript for a character controller with double jump and wall sliding"
"Create a new scene with a Player node in my Godot project"
"Add a Sprite2D node to my player scene and load the character texture"
"Export my 3D models as a MeshLibrary for use with GridMap"
"Create a UI scene with buttons and labels for my game's main menu"
"Get the UID for a specific script file in my Godot 4.4 project"
"Update UID references in my Godot project after upgrading to 4.4"The Godot MCP server uses a bundled GDScript approach for complex operations:
Direct Commands: Simple operations like launching the editor or getting project info use Godot's built-in CLI commands directly.
Bundled Operations Script: Complex operations like creating scenes or adding nodes use a single, comprehensive GDScript file (godot_operations.gd) that handles all operations.
This architecture provides several benefits:
No Temporary Files: Eliminates the need for temporary script files, keeping your system clean
Simplified Codebase: Centralizes all Godot operations in one (somewhat) organized file
Better Maintainability: Makes it easier to add new operations or modify existing ones
Improved Error Handling: Provides consistent error reporting across all operations
Reduced Overhead: Minimizes file I/O operations for better performance
The bundled script accepts operation type and parameters as JSON, allowing for flexible and dynamic operation execution without generating temporary files for each operation.
Godot Not Found: Set the GODOT_PATH environment variable to your Godot executable
Connection Issues: Ensure the server is running and restart your AI assistant
Invalid Project Path: Ensure the path points to a directory containing a project.godot file
Build Issues: Make sure all dependencies are installed by running npm install
For Cursor Specifically:
Ensure the MCP server shows up and is enabled in Cursor settings (Settings > MCP)
MCP tools can only be run using the Agent chat profile (Cursor Pro or Business subscription)
Use "Yolo Mode" to automatically run MCP tool requests
This project is licensed under the MIT License - see the LICENSE file for details.
Add a node to an existing scene
Inputs: nodeName (required), nodeType (required), scenePath (required), projectPath (required), +2 more.
Create a new Godot scene file
Inputs: scenePath (required), projectPath (required), rootNodeType.
Export a scene as a MeshLibrary resource
Inputs: scenePath (required), outputPath (required), projectPath (required), meshItemNames.
Get the current debug output and errors
Inputs: no named parameters.
Get the installed Godot version
Inputs: no named parameters.
Retrieve metadata about a Godot project
Inputs: projectPath (required).
Get the UID for a specific file in a Godot project (for Godot 4.4+)
Inputs: filePath (required), projectPath (required).
Launch Godot editor for a specific project
Inputs: projectPath (required).
List Godot projects in a directory
Inputs: directory (required), recursive.
Load a sprite into a Sprite2D node
Inputs: nodePath (required), scenePath (required), projectPath (required), texturePath (required).
Run the Godot project and capture output
Inputs: projectPath (required), scene.
Save changes to a scene file
Inputs: scenePath (required), projectPath (required), newPath.
Stop the currently running Godot project
Inputs: no named parameters.
Update UID references in a Godot project by resaving resources (for Godot 4.4+)
Inputs: projectPath (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 14 tools
Most tools target clearly distinct actions, such as launch vs run vs stop project, or get version vs project info. However, load_sprite overlaps with add_node as a specialized node-addition tool, and launch_editor vs run_project may be confused by agents unfamiliar with Godot workflows.
All 14 tools use snake_case with a consistent verb_noun pattern (launch_editor, create_scene, get_uid, update_project_uids). There are no deviations in convention, making the set highly predictable.
14 tools sits comfortably within the ideal 3–15 range. Each tool earns its place across project lifecycle, scene editing, and UID management without redundancy.
The surface covers launch/run/debug/stop, project discovery, scene creation, node addition, and UID management. However, it lacks scene lifecycle essentials like delete_scene or remove_node, and no node property update tool exists, which could block common editing workflows.
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
