AI-godot-mcp
Enables AI-driven game development by providing MCP tools to interact with the Godot editor, including scene editing, node manipulation, script attachment, and scene execution.
README
AI-godot-mcp
Production-grade Godot MCP service for AI-driven game development.
Inspired by dpeachpeach/godot-mcp
Features
π Project Inspection
get_project_context- Retrieve Godot version, project name, and plugin statusget_scene_tree- Get current scene node tree (supports depth limit and type filtering)get_editor_logs- Fetch editor output panel logs (supports timestamp and level filtering)
π¨ Scene Editing
create_scene- Create new scene filesadd_node- Add nodes to scene tree with automatic parent resolutionset_node_property- Modify node properties with type validationdelete_node- Delete nodes with full undo supportload_resource- Load and reference external resourcessave_current_scene- Save current scene to disk
β‘ Transaction Management
begin_ai_action/end_ai_action- Atomic batch operations with native UndoRedo integration
π Script Management
attach_script- Attach GDScript to nodes with automatic template generationget_resource_uid- Get resource UID for cross-reference validation
βΆοΈ Scene Execution
play_current_scene- Run current scene in editor (F6)stop_running_scene- Stop running scene (F8)
π οΈ CLI Tools
install- Deploy plugin to Godot projects with version validationuninstall- Clean removal of plugin from projectsversion- Display version and compatibility information
Requirements
- Godot: 4.6.x only
- Node.js: β₯20.0.0
Quick Start
Installation
npx ai-godot-mcp install <godot-project-path>
Enable Plugin
In Godot Editor:
- Open your project
- Navigate to Project β Project Settings β Plugins
- Enable "AI Godot MCP"
Configure MCP Client
Claude Code
claude mcp add ai-godot-mcp -- npx ai-godot-mcp
Restart Claude Code and the tools will be available.
<details> <summary><strong>Other MCP Clients</strong></summary>
For any MCP-compatible client, use this configuration:
{
"mcpServers": {
"ai-godot-mcp": {
"command": "npx",
"args": ["ai-godot-mcp"]
}
}
}
</details>
Architecture
AI-godot-mcp uses a WebSocket communication architecture:
- Node MCP Server (WebSocket client) β Godot Editor Plugin (WebSocket server on port 6550)
- All write operations integrate with Godot's native UndoRedo system, supporting atomic transactions
- Unified response format:
{ok: true, data}or{ok: false, error: {code, message, suggestions}}
CLI Commands
install
npx ai-godot-mcp install <project-path>
Deploy plugin to Godot project with version compatibility validation (Godot 4.6.x only).
uninstall
npx ai-godot-mcp uninstall <project-path>
Remove addons/ai_godot_mcp/ directory from project.
version
npx ai-godot-mcp version
Display version information and supported Godot versions.
Building from Source
<details> <summary>Expand to view</summary>
git clone https://github.com/DC925928496/AI-godot-mcp.git
cd AI-godot-mcp
npm install
npm run build
Then point your MCP client configuration to build/index.js instead of using npx.
</details>
Troubleshooting
- Godot version mismatch β Ensure you're using Godot 4.6.x (verify with
godot --version) - Plugin not enabled β Check Project β Project Settings β Plugins in editor, ensure "AI Godot MCP" is checked
- WebSocket connection failed β Confirm plugin is started and port 6550 is not occupied
- Tool call timeout β Ensure Godot editor is running and plugin is loaded
License
MIT
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.