mcp-server

fennara-godot-ai: Build AI-powered games

Name: fennara-godot-ai: Build AI-powered games
Author: fennaraOfficial

Get AI chat and agent tooling for Godot with fennara-godot-ai, for startup game founders and developers, 153 GitHub stars

231 stars7 forksC++Guide quality 8/10Updated 7/25/2026100% free · open source

What it does

Fennara-godot-ai integrates AI chat and agent capabilities into Godot, a game engine, allowing for more interactive and dynamic gameplay experiences.

When to use it

•You're building a game in Godot and want to add conversational AI elements
•Your game requires NPCs with autonomous behavior and decision-making
•You need a tool that integrates MCP support and native editor integration for streamlined development

Ready-to-paste prompt

Create a conversational AI that responds to player input: `chat.add_response('hello', 'Hello, how are you?')`

Heads up: Make sure you have the correct version of Godot installed (3.4 or later) and that the MCP server is running before attempting to use the AI chat and agent features

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/fennara-godot-ai && curl -fsSL https://workflowstacks.com/api/skills/fennara-godot-ai/claude-skill -o ~/.claude/skills/fennara-godot-ai/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How fennara-godot-ai: Build AI-powered games works

Codeflow

Free to inspect

Fennara-godot-ai: Build AI-powered games is a very large Rust project (~104k lines across 474 code files, plus 20 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~104k lines · 474 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Rust

No API keys detected

Rust 42%C++ 39%JavaScript 10%GDScript 6%CSS 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows

What's in each folder

ui/Frontend / UI31 files

docs/Documentation292 files

fennara-cpp/Folder269 files

local/Folder187 files

scripts/Helper scripts54 files

godot_demo/Folder39 files

runtime/Folder13 files

.github/CI / automation (GitHub Actions)15 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/fennara-godot-ai && curl -fsSL https://workflowstacks.com/api/skills/fennara-godot-ai/claude-skill -o ~/.claude/skills/fennara-godot-ai/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

fennaraOfficial

Language

C++