Choose theme
AI Visuals
Godot MCP Toolkit
Godot MCP Toolkit connects an AI coding assistant to the Godot game editor. Its tools let the assistant create scene objects, edit scripts, run a game and inspect what happens during a playtest.
It is an independent plugin from NPGameDev. You install it in your Godot project and connect your assistant through a separate Node.js bridge. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
An assistant connected to Godot
The plugin exposes Godot operations through MCP, a protocol that lets an assistant call tools. You can ask for a player object with a sprite and collision shape, then inspect those objects in the editor.
Why it stands out
Inspect the player while the game runs
Editor tools work on the scene you are building. Runtime tools work on the game while it is playing. That lets an assistant read a moving player's position and velocity instead of inferring them from the script alone.
Availability
Godot plugin and Node.js bridge
The source, releases and setup guide are public. The plugin requires desktop Godot 4.2 or later, with features varying by version. The companion bridge requires Node.js 22 or later.
Why it matters
What makes it useful
In a small platformer, adding a player is only part of the job. You also need to see whether it moves when you press a direction. The toolkit documents creating the player and its child objects, reading live properties, simulating input and capturing the game screen.
What to know
Where it fits
Scene and asset tools cover 2D and 3D work, including tilemaps, SpriteFrames animations, lights and cameras. This is useful when you already have a Godot project and want an assistant to work with the same scene objects you can inspect in the editor.
Notable points
What stands out
A property changed in the running game belongs to that live instance. The tool reference provides a separate operation for editing the scene in the editor. If a playtest adjustment is one you want to keep, make the corresponding editor change, save the scene and check it in a new run.
Before using
What to review
The Godot Asset Store marks the current version as unstable. Start with a small test project and keep a copy of your work before allowing edits.
Connect an MCP-compatible assistant and use the compatibility guide for your Godot version. Some tools appear only after the assistant requests them, so the client must support tool-list updates.
The toolkit includes operations that write files and execute code. Review your client permissions. Its read-only mode hides mutating toolkit tools, while reads and permissions granted elsewhere in the client still need attention.
The bridge connects to the editor on your machine. Your chosen AI client and model provider determine how the conversation and returned project content are handled.
Reader fit
Who may find it relevant
This is aimed at Godot users who can review scene changes and try the game themselves. A small scene with a player and a few objects gives you something manageable to inspect while learning which actions the assistant can take.
Editorial note
Why LifeHubber lists it
LifeHubber lists Godot MCP Toolkit because it offers a Make Unique option when changing a property inside an external resource. If several objects share the same material, a tweak intended for one object can affect the others. The option copies the resource into that object's scene entry before the edit, giving you a way to try a different material setting on one object while keeping the shared resource.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Paperclip
paperclipai/paperclip
A self-hosted server and dashboard for coordinating agent teams through companies, goals, roles, issues, heartbeats, budgets, approvals, and persistent activity records.
assistant-ui
assistant-ui/assistant-ui
A React and TypeScript library for building AI chat interfaces, with message editing, branch controls for alternative replies, and runtime adapters for different backends.
Microsoft Agent Governance Toolkit
microsoft/agent-governance-toolkit
A Microsoft toolkit for adding policy enforcement, identity, sandboxing, audit records, reliability tooling, and the Agent Control Specification runtime layer around AI agents, with Python, TypeScript, .NET, Rust, and Go surfaces.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
