How do I use Flockbay with my own AI agent?

By Eduardo Orellana · Updated

Flockbay is free on your own Claude or ChatGPT plan. Claude Pro or Max, or ChatGPT Plus or higher, builds a real Godot project in the Godot editor. Claude Free and ChatGPT Free do not run here. More models are optional, a credit reload at API prices. Windows today. The engine is the official Godot release. Connect Claude Code, Codex, Cursor or any MCP client to the Flockbay app, free with a free Flockbay account. Or build in Flockbay's own chat on your Claude or ChatGPT plan, or your own API key.

TL;DR. Flockbay is a free AI game maker built on Godot: a Windows download, with the Mac release later, that makes a Godot 4 project operable by an AI. Connect your own agent over MCP for free, or build in Flockbay's chat on your Claude or ChatGPT plan or your own API key. The builder lives in the Godot editor, and the game runs locally. There is no browser editor and no cloud building.

The idea in one paragraph

A game project is normally opaque to a language model. It is scenes, binary resources, an editor that holds state, and a thousand conventions that live in a person's head. An agent asked to change something has to infer most of it and it gets things wrong in expensive ways.

Flockbay exists to close that gap. It is a free AI game maker built on Godot: a desktop app, on Windows first, that bundles the official Godot 4.7.2 engine, keeps the project in a real Godot layout, and exposes the work as things an agent can actually do rather than pixels it has to guess at. That is the layer, and it is why the code an agent writes here lands correctly more often than the same model writing into a bare project.

Flockbay's own AI, the built-in path

Flockbay's own AI is in the app. It writes GDScript and scenes into your project, shapes the world through the capability layer (terrain, water, sky, weather, the player controller and props), and playtests the game to check its work: it runs it, reads stdout and errors, captures viewports and injects input events.

You judge the result by playing it, and you can take over by hand at any point. The builder is a set of buttons around the Godot editor's own 3D and 2D view, with Godot's undo, so you and the AI use the same controls.

It runs on your own Claude plan or ChatGPT sign-in, or on your own API key, connected once in Connectors. Every new account also gets Demo, a small free allowance, and optional plans run the AI for you.

More on this: Claude for Godot: how to build a Godot game with Claude Code, step by step

Bringing your own agent over MCP

If you already work in Claude Code, Codex or Cursor, point it at Flockbay over MCP. It is one server, registered as flockbay-stage, and the app writes the line to paste: Connectors, then Another agent, then Set up.

Your agent gets the same tools as Flockbay's own AI: the world capabilities, editing the game through the open Godot editor with undo, and running, watching and playing the game. Connect your own agent has the setup for each client.

It is also the version that is honest about what an integration is. You are not getting a different Flockbay; you are getting the same capabilities addressed by a different client.

More on this: Claude or ChatGPT for Godot

What stays local and what does not

The game runs locally. Godot ships inside the app and pressing play starts the game on your machine, at your framerate. There is no streaming, no remote render and no browser preview.

Building needs an internet connection. The agent, asset generation and world data all come over the network, so this is not an offline tool and there is no degraded offline mode. Playing what you built is a different matter and needs nothing.

Cost

Free to download, and the builder itself is free. Build free on your own AI: your Claude plan (Pro or Max) or ChatGPT plan (Plus or higher) in the app, your own agent over MCP, or an API key. Every new account gets Demo, a small free allowance on a small model. Optional plans, Indie $20, Pro $60 or Ultra $200 a month, run the AI for you on a band of hosted models.

External agent access over MCP is free, with a free Flockbay account. There is no seat pricing and no enterprise tier; this is a desktop app one person installs.

More on this: Flockbay vs Summer Engine: official Godot, or an engine built on it

Why this makes cheap models work better

The interesting result is not that a model can write GDScript. It is how much less it has to invent when the surrounding project is arranged for it. Every ambiguity you remove — where a thing lives, what a scene is called, how a system is expected to be wired — is a decision the model no longer has to guess and get wrong.

That has a practical consequence. Reliability comes from the layer, not from reaching for a larger model, and a layer that makes a small model reliable is worth more than a prompt that makes a large one occasionally brilliant.

It is also why quality complaints here turn into work on the capability rather than a model upgrade. If the same request keeps producing the same wrong shape, the honest fix is upstream of the model.

More on this: How to make games in Codex: the Codex CLI, the ChatGPT app, or your ChatGPT plan inside Flockbay

Questions

Can I use my own model?
Yes, free: your Claude plan or ChatGPT Plus or higher in the app, your own agent over MCP, or an API key (OpenAI or Anthropic).
Is this an API?
It is a desktop app that an external agent can drive over MCP. It is not a hosted service and there is no cloud build.
Does the AI build the world too?
Yes. Flockbay's AI, and your own agent, shape the world through the same controls the builder gives you: terrain, water, sky, weather, the player controller and props. You can change any of it by hand in the Godot editor.
Does the game render in the cloud?
No. It runs locally on the copy of Godot bundled with the app.
Do I need an internet connection?
To build, yes, always. To play what you have already built, no.