Engines · Godot

GodotAvailable

Add the godot_mcp addon to your C# Godot project and drive the editor with AI.

Godot 4.3–4.5C# / .NET 8 (mono)
01

Install the plugin

Two ways to get the plugin into your project — pick whichever fits your workflow.

Recommended

CLI

Install via the godot-cli tool on npm. install-plugin downloads the godot_mcp addon from the matching GitHub release, adds the two NuGet packages and the extension-catalog embed to your .csproj, and enables the plugin — idempotently.

1Install the CLI

Install godot-cli globally from npm.

npm install -g godot-cli
2Install the plugin

Download the addon, add the NuGet packages to your .csproj, and enable godot_mcp in project.godot.

godot-cli install-plugin ./MyGodotProject
3Wire up your AI client

Generate the MCP config for your client (e.g. Claude Code).

godot-cli setup-mcp claude-code ./MyGodotProject
4Open & wait

Open the project and wait until the editor is ready.

godot-cli open ./MyGodotProject

After opening you can also gate scripts on editor-readiness: godot-cli wait-for-ready ./MyGodotProject.

Asset Library

Install the godot_mcp addon from the Godot Asset Library (or the same zip from GitHub Releases), then add the two NuGet packages and enable the plugin.

View on Asset Library
1Install the addon

Get godot_mcp from the Godot AssetLib tab, or download the zip from the GitHub Releases page, and place it in your project's addons/ folder.

2Add the NuGet packages

Add both packages to your project .csproj: com.IvanMurzak.ReflectorNet version 5.4.3 and com.IvanMurzak.McpPlugin version 8.7.1, plus the addons/godot_mcp/extensions.catalog.json EmbeddedResource (without it the Extensions panel is empty). The exact block is in the Godot-MCP README.

3Enable the plugin

In the editor: Project → Project Settings → Plugins, then enable godot_mcp.

4Open & build

Reopen the project so Godot builds the C# solution with the new packages.

02

Connect

Run through the hosted cloud endpoint, or point at your own server.

Cloud

Default

Connect through ai-game.dev using the device-code OAuth flow — no tokens to copy by hand. From the AI Game Developer window choose Cloud, click Authorize, and approve the device code in your browser. Works across firewalls and gives you usage analytics. This is the default and what we recommend for most users.

Custom

Prefer to run everything locally? Point the plugin at your own gamedev-mcp-server instance instead of the hosted endpoint. Your AI client then talks straight to your machine. Client-by-client config snippets live on the MCP endpoint page.

Need client config snippets (Claude, Cursor, Copilot, Gemini and more)? See the MCP endpoint page →

03

Configure your AI agent

Pick the AI agent you use and copy the exact godot-cli command that wires it up to the Godot MCP server.

Your AI agent

Run this in your project to configure Claude Code for Godot:

godot-cli setup-mcp claude-code ./MyGodotProject

Restart your agent after configuring. The new MCP server is only picked up on a full restart of the agent — quit it completely and reopen it (not just reload the window).

04

First run

Open the window, authorize, and try your first prompt.

  1. Open the project in the Godot editor and open the AI Game Developer dock.
  2. Choose Cloud and click Authorize to complete the device-code flow.
  3. Wait for the status to go green, then connect your AI client.
  4. Try a prompt like the one below and watch it act in the editor.
Example prompt
Add a Node3D scene with a Camera3D and a MeshInstance3D cube, then save it as Main.tscn.

Want more example prompts and the patterns for effective AI requests? See Godot best practices →

The Godot plugin exposes 99 MCP tools for your AI client.

Browse the Godot tool catalog →

Want even more tools? Browse Godot extensions →