Godot MCP Server for Openclaw

An advanced Model Context Protocol integration that enables AI agents to control the Godot Editor for automated scene building and script management.

thb32133451
v1.0.0
Mar 4, 2026
0
1.4k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install godot-mcp

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install godot-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Godot MCP Server?

The Godot MCP Server is a specialized plugin designed to bridge the gap between AI assistants and the Godot Engine. By utilizing the Model Context Protocol, it allows developers to leverage Openclaw Skills to programmatically manipulate their game projects. This integration enables AI agents to handle complex tasks like scene tree construction, node property adjustments, and resource management directly within the editor environment.

This tool is essential for developers looking to incorporate AI-driven workflows into their game development process. It supports a wide range of AI clients including Claude CLI, Cursor, and Windsurf, making it a versatile addition to any modern developer's toolkit.

Godot MCP Server Use Cases

  • Rapid prototyping of game levels by describing scene hierarchies to an AI agent.
  • Automated generation and attachment of GDScript files to specific scene nodes.
  • Batch processing of project resources, such as updating texture filter modes or material properties.
  • AI-assisted debugging through real-time log analysis and state inspection within the Godot Editor.
  • Procedural placement and configuration of physics bodies and collision shapes using natural language commands.

How Godot MCP Server Works

  1. The plugin is installed as an addon within a Godot project and activated via the Project Settings.
  2. Once enabled, the plugin starts a local server (defaulting to port 3000) that listens for MCP-compliant requests.
  3. The user configures an AI client (like Cursor or Claude) to connect to the Godot MCP endpoint.
  4. When the user provides a prompt, the AI selects the appropriate tool from the Openclaw Skills set, such as node_add or script_write.
  5. The server executes the corresponding command via Godot's internal APIs and returns the execution status or data back to the AI.

Godot MCP Server Setup

To get started, clone the repository and move the addon to your project's directory:

git clone https://github.com/DaxianLee/godot-mcp.git
cp -r godot-mcp/addons/godot_mcp /path/to/your/project/addons/

After copying the files, open your project in the Godot Editor, navigate to Project -> Project Settings -> Plugins, and enable the Godot MCP Server. To connect a CLI client, use the following command:

claude mcp add --transport http godot-mcp http://127.0.0.1:3000/mcp

Godot MCP Server Data Schema & Taxonomy

The skill interacts with the Godot project structure using the following schema:

Data Category Management Type Details
Scenes .tscn files Controls scene creation, tree structures, and saving.
Nodes Object Properties Manipulates node types, positions, and inspector variables.
Scripts .gd files Handles GDScript generation, reading, and node attachment.
Resources .tres / .res Manages materials, shaders, and audio assets.
Filesystem res:// path Direct access to project directory for file operations.

Godot MCP Server Advanced Features

  • Multi-agent support allowing different AI clients to collaborate on the same project.
  • Automated physics body configuration with support for custom shapes and collision layers.
  • Advanced UI and TileMap editing tools for rapid interface and level layout generation.
  • Built-in multi-language support covering 9 languages for global development teams.
  • High-level undo/redo integration to safely test AI-generated changes within the editor.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*