Back to MCP Catalog

Godot MCP Server

GamingTypeScript
Interface with the Godot game engine to launch, run, and debug projects
Available Tools

launch_editor

Opens the Godot editor for a specific project

run_project

Executes Godot projects in debug mode

get_debug_output

Retrieves console output and error messages from running Godot projects

stop_project

Stops a running Godot project

get_godot_version

Retrieves the installed Godot version

list_projects

Finds Godot projects in a specified directory

get_project_info

Gets detailed information about project structure

create_scene

Creates new scenes with specified root node types

add_node

Adds nodes to existing scenes with customizable properties

load_sprite

Loads sprites and textures into Sprite2D nodes

export_mesh_library

Exports 3D scenes as MeshLibrary resources for GridMap

save_scene

Saves scenes with options for creating variants

get_uid

Gets UID for specific files (for Godot 4.4+)

update_project_uids

Updates UID references by resaving resources (for Godot 4.4+)

Godot MCP provides a seamless interface between AI assistants and the Godot game engine. It enables launching the editor, running projects, capturing debug output, and controlling project execution through a standardized protocol. This direct feedback loop helps AI assistants understand what works in real Godot projects, leading to better code generation and debugging assistance.

Overview

Godot MCP creates a bridge between AI assistants and the Godot game engine, allowing for direct interaction with Godot projects. This enables AI assistants to provide more accurate and contextual help when working with Godot game development.

Requirements

Before installing Godot MCP, ensure you have:

  • Godot Engine installed on your system
  • Node.js and npm
  • An AI assistant that supports MCP (Claude, Cursor, etc.)

Installation

Step 1: Clone and Build the Repository

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 build

Step 2: Configure with Your AI Assistant

For Claude (using Cline)

Add the following to your Cline MCP settings file (typically located at ~/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"
      ]
    }
  }
}

For Cursor

  1. Go to Cursor Settings > Features > MCP
  2. Click on the + Add New MCP Server button
  3. Fill out the form:
    • Name: godot (or any name you prefer)
    • Type: command
    • Command: node /absolute/path/to/godot-mcp/build/index.js
  4. Click "Add"

Usage

Once configured, your AI assistant can interact with Godot through various commands. Here are some examples of what you can do:

  • Launch the Godot editor for a specific project
  • Run Godot projects and capture their output
  • Create and modify scenes programmatically
  • Add nodes to existing scenes with custom properties
  • Load sprites and textures into Sprite2D nodes
  • Export 3D scenes as MeshLibrary resources
  • Manage UIDs for Godot 4.4+ projects

Troubleshooting

If you encounter issues:

  1. Ensure Godot is properly installed and accessible from your PATH
  2. Check that the path to the MCP server is correct in your configuration
  3. Enable DEBUG mode by setting the environment variable in your configuration
  4. Verify that your AI assistant supports MCP and is properly configured

Additional Resources

Related MCPs

VRChat API
GamingTypeScript

Access and interact with the VRChat API

Unity Editor Integration
GamingC#

Connect Unity Editor with AI models for game development assistance

OpenDota
GamingPython

Access real-time Dota 2 statistics, match data, and player information

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.