godot
GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools: scene management, GDScript LSP, DAP debugger, screenshot capture, input injection, ClassDB introspection, CC0 asset library. npx gopeak
claude mcp add --transport stdio had0yun-godot-mcp npx -y gopeak \ --env GODOT_PATH="/path/to/godot" \ --env GOPEAK_TOOL_PROFILE="compact"
How to use
GoPeak is an MCP server for Godot that lets AI assistants run, inspect, modify, and debug real Godot projects end-to-end. It provides a curated tool surface (compact profile) with 33 core tools plus dynamic groups, enabling in-context project manipulation, runtime inspection, and debugging within Godot projects. You can launch Godot projects, inspect live scenes and resources, create or modify scenes and scripts, manage signals and animations, and access runtime metrics and diagnostics. With the compact tool surface, you get a balance between capability and token efficiency, with additional tools activated on demand via dynamic tool groups.
To use the server, first install the GoPeak MCP client configuration in your client app or environment. The example configuration in the Quick Start shows how to connect using npx and pass environment variables to point GoPeak at your Godot project. Once connected, you can issue natural-language prompts like listing Godot projects, creating a scene, or running a project and inspecting debug output. The server exposes capabilities across scene/script/resource/runtime/LSP/DAP areas, so you can perform in-context edits, inspect class data, and debug live runtime state. Tools can be auto-activated via the catalog or manually via tool.groups for debugging sessions, and the client will receive notifications when the tool list changes.
Typical workflows include launching the editor, running the project to collect logs, inspecting the live scene graph, editing properties or scripts, and applying fixes based on AI-guided analysis. The setup also supports fine-grained control over tool exposure and token usage by leveraging the GOPEAK_TOOL_PROFILE and related environment variables.
How to install
Prerequisites
- Godot 4.x installed
- Node.js 18+ installed
- A MCP-compatible client (Claude Desktop, Cursor, Cline, OpenCode, etc.)
A. Quick start (recommended)
- Install and run via npx:
npx -y gopeak
- Connect to the GoPeak MCP server (Godot) by adding the following MCP client config:
{
"mcpServers": {
"godot": {
"command": "npx",
"args": ["-y", "gopeak"],
"env": {
"GODOT_PATH": "/path/to/godot",
"GOPEAK_TOOL_PROFILE": "compact"
}
}
}
}
B. Global install (alternative)
npm install -g gopeak
gopeak
C. From source (advanced)
git clone https://github.com/HaD0Yun/godot-mcp.git
cd godot-mcp
npm install
npm run build
node build/index.js
GoPeak also exposes two CLI bin names: gopeak and godot-mcp.
Additional notes
Notes and tips:
- Environment variables: GODOT_PATH should point to your Godot executable or project root as required by your setup. GOPEAK_TOOL_PROFILE selects the exposure mode (compact by default). You can override GOPEAK_TOOL_PROFILE using MCP_TOOL_PROFILE as a fallback alias.
- Tool surface and tokens: compact mode exposes 33 core tools with 22 dynamic groups (78 additional tools). Use tool.catalog to discover tools and tool.groups to activate a specific group, then deactivate groups when done to minimize token usage.
- Page size for tools: tools are paginated to avoid sending all 110+ tools at once. Adjust GOPEAK_TOOLS_PAGE_SIZE if your client needs smaller or larger pages.
- Debug workflow: use Run project, capture debug output, inspect logs, and use runtime inspection tools to modify properties or call methods in real time.
- Compatibility: ensure your Godot project is compatible with Godot 4.x APIs and the tools provided by GoPeak. Some features may require specific editor plugins installed via the Addons section in Godot.
Related MCP Servers
unity
Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Unity
AI-powered bridge connecting LLMs and advanced AI agents to the Unity Editor via the Model Context Protocol (MCP). Chat with AI to generate code, debug errors, and automate game development tasks directly within your project.
deep-code-reasoning
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI
coplay-unity-plugin
Unity plugin for Coplay
mcp-mail
📧 MCP Mail Tool - AI-powered email management tool | 基于 MCP 的智能邮件管理工具
cursor-history
MCP server for browsing, searching, and exporting Cursor AI chat history.