GameCodex
A game development MCP server with 950+ curated docs across 29 engines and 5 power tools for scaffolding, debugging, design, and scope tracking. It connects to any AI supporting the Model Context Protocol.
README
GameCodex
Your AI forgets game dev mid-project. This fixes that.
GameCodex is a game dev AI assistant — an MCP server with 950+ curated docs across 29 engines, 5 power tools, structured workflows, and scope tracking. It connects to any AI that supports the Model Context Protocol: Claude, Cursor, Windsurf, Continue.dev, and more.
Every doc is hand-written for AI consumption — typed examples, anti-pattern warnings, decision trees. Not scraped docs. Not training data guesses. Structured knowledge that actually helps you build.
Install
npx gamecodex setup
That's it. Zero-install, auto-detects your AI tool, writes the MCP config for you.
Manual setup
Add to your MCP config (claude_desktop_config.json, .cursor/mcp.json, etc.):
{
"mcpServers": {
"gamecodex": {
"command": "npx",
"args": ["-y", "gamecodex"]
}
}
}
Or with Claude Code:
claude mcp add gamecodex -- npx -y gamecodex
What Can It Do?
Search 950+ curated docs — Ask about ECS, pathfinding, state machines, shaders, or any game system. Get structured answers grounded in real documentation, not hallucinations.
Scaffold projects — Describe your game, get architecture and starter code that compiles. Every snippet includes comments explaining why.
Debug like a mentor — Paste an error, get a diagnosis. Not a Stack Overflow link — a real explanation of what went wrong and how to fix it.
Track scope creep — Built-in project health tracking warns when your feature list is getting heavy. Knows when to say "cut this" before your game becomes vaporware.
Structure your workflow — Session workflows for planning, debugging, deciding, and scoping. Not chat history — orchestrated development process management.
5 Power Tools
| Tool | What it does |
|---|---|
project |
Project state, goals, decisions, scope health, session workflows |
design |
GDD generation, phase checklists, launch prep, marketing guidance |
docs |
Search and browse 950+ game dev docs across 29 engines |
build |
Scaffold projects, generate code, debug errors, review architecture |
meta |
Server diagnostics, license info, module discovery |
29 Supported Engines
Godot | Unity | Unreal | MonoGame | Bevy | Phaser | GameMaker | Pygame | Love2D | Raylib | Defold | Construct | Ren'Py | RPG Maker | PixiJS | Three.js | Babylon.js | SFML | SDL3 | LibGDX | Stride | HaxeFlixel | Heaps | PlayCanvas | Excalibur | Macroquad | FNA | GDevelop | Kaplay
Plus a core module with 52 engine-agnostic docs on design patterns, architecture, and programming fundamentals.
Knowledge Base
957 curated markdown docs organized into 30 modules:
- Game Design — GDD templates, scope management, playtesting
- Architecture — ECS, state machines, event systems, scene composition
- Programming — Input handling, physics, pathfinding, save/load, networking
- Engine Guides — Per-engine implementation guides, reference sheets, best practices
- Project Management — Phase checklists, scope tracking, launch preparation
Every doc includes: typed code examples, "when to use" guidance, common pitfalls, and cross-engine comparisons where relevant.
Why GameCodex?
| GameCodex | Single-engine MCPs | Raw AI (no MCP) | |
|---|---|---|---|
| Engines | 29 | 1 | 0 (training data only) |
| Docs | 950+ curated | Varies | None |
| Tools | 5 (lean schema) | 10-95+ (schema bloat) | N/A |
| Scope tracking | Yes | No | No |
| Privacy | stdio-only, no network | Varies | Cloud-dependent |
| Price | Free (MIT) | Varies | Varies |
Configuration
| Variable | Description |
|---|---|
GAMECODEX_LICENSE |
Pro license key (enables all engine modules) |
GAMEDEV_MODULES |
Comma-separated module IDs to load (default: all) |
Development
git clone https://github.com/WesleySalzer/GameCodex.git
cd GameCodex
npm install
npm run build
npm test # 303 tests
npm run typecheck
Monorepo Structure
GameCodex/
├── packages/
│ ├── server/ # MCP server (5 tools, 950+ docs, 29 engines)
│ └── site/ # Marketing site (Next.js)
├── package.json # npm workspaces root
└── README.md
Links
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.