Source: Dev.to

The Problem

I make games in Godot and use AI (Claude Code) to write code daily.
The workflow always had the same bottleneck:

AI writes code → I run the game → I check if it works → I report back → AI fixes → I run again…

That “run and check” part adds up, especially when tweaking UI, testing edge cases, or iterating on a mechanic. I wanted to hand off the entire build‑test‑fix cycle to AI.

Existing Godot MCP servers fell short:

None could do what I needed: AI builds the game, runs it, tests it, and fixes what’s broken—without any manual steps.

So I built Godot MCP Pro – 84 tools across 14 categories, including input simulation, runtime analysis, and screenshot capture, enabling AI to autonomously test a running game.

Demo: One Prompt → Complete Reversi + AI Playtest

The Prompt (summary)

Build a complete Reversi game in this Godot project.
Single scene, single script, all rendering via _draw().

Requirements: 8×8 board, pieces, highlights, flip animation,
standard rules, score display, restart button...

After building, set as main scene and play it.
Then playtest: play 4 moves, screenshot after each,
fix anything that's wrong.

The key is the last instruction—“playtest it yourself, fix anything that’s wrong.” That single line turns the AI from a code generator into a QA tester.

What Happened

Build Phase (~2 min)

AI autonomously chains tool calls to build the game:

create_script("main.gd")          → Full game logic in one file
create_scene("main.tscn")         → Scene with Node2D root
attach_script                     → Wire script to root
add_node × 4                      → Score, Turn, Message labels + Restart button
save_scene
set_project_setting
reload_project
play_scene

The editor updates in real time: nodes appear in the scene tree, and the game window opens with a fully rendered Reversi board.

Playtest Phase (~2 min)

AI takes a screenshot, inspects the board, clicks a cell, takes another screenshot to verify:

The AI made mistakes, but it caught them from the screenshots and fixed them without any human input. This is the workflow I wanted: tell the AI to test, and it figures out the rest.

Report

After testing, the AI outputs a full checklist:

How It Works

Architecture

AI Assistant ←─MCP/stdio──→ Node.js Server ←─WebSocket──→ Godot Editor Plugin

MCP (Model Context Protocol) is an open protocol by Anthropic that gives AI access to tools. Godot MCP Pro implements this protocol with 84 tools across 14 categories.

Four tool categories that enable autonomous testing

Without these, AI can write code but can’t verify it works. With them, AI closes the loop.

Why Not Just Edit Files?

File editing gives you code generation, but it doesn’t provide:

• Game launch/stop control
• Input simulation (keyboard, mouse, action sequences)
• Screenshot capture from the running game
• Runtime state inspection (live scene tree, node properties)
• Undo/redo (all MCP mutations go through Godot’s UndoRedoManager)

The build → test → fix cycle needs bidirectional communication with the editor—that’s the whole point.

Full Tool List (84 tools / 14 categories)

Input simulation, runtime analysis, signal management, animation, tilemap, shader, and profiling tools are exclusive to Godot MCP Pro—no other Godot MCP server offers them.

How I Actually Use It Day‑to‑Day

The Reversi demo is a showcase. In practice, the most useful things are more mundane:

• UI setup – “Set this Label’s font to 24, anchor to center‑top.” AI changes it directly in the editor.
• Signal wiring – “Connect this button’s pressed signal to on_restart.” Done without opening the Node dock.
• Prototyping – “Make a temporary health bar that follows the player.” AI creates the node, adds it to the scene, and wires the script.

Because the AI can see the running game, interact with it, and inspect the live scene tree, it can iterate far faster than a pure file‑editing workflow.

Bottom Line

Godot MCP Pro gives AI the tools it needs to build, launch, test, and fix a game entirely inside the editor. The result is a dramatically tighter feedback loop and a workflow where the “run and check” step is fully automated.

Player Dash When Pressing Shift — AI writes the code, launches the game, tests it

Bug investigation: “Run the game, do X, then read the player’s position and velocity” — AI reports back with actual runtime values.

It lets me focus on game design and final decisions while AI handles the editor busy‑work.

Getting Started

Requirements

• Godot 4.x (4.3+)
• Node.js 18+
• MCP‑compatible AI client (Claude Code, Claude Desktop, Cursor, Cline, etc.)

Get it from godot-mcp.abyo.net

1. Copy addons/godot_mcp/ into your Godot project.
2. Enable the plugin in Project Settings → Plugins.

Add to your AI client’s MCP config

{
  "mcpServers": {
    "godot-mcp-pro": {
      "command": "node",
      "args": ["path/to/mcp/server/build/index.js"]
    }
  }
}

• Enter fullscreen mode
• Exit fullscreen mode

Godot MCP Pro

• 84 tools
• 14 categories
• $5 one‑time, lifetime updates

godot-mcp.abyo.net