GameDev MCP Hub
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GameDev MCP Hub create a new Blender scene with a cube"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GameDev MCP Hub
Version: 0.1.0 · Status: active development
MCP hub that aggregates game-development MCP servers (Blender, Godot, GitHub, Obsidian, …) behind one interface for Claude, LM Studio, Cursor, and other MCP clients. Includes a local GUI, smart task routing, and SSE multi-client support.
Quick start
Prerequisites: Node.js 20+
# Install
pnpm install # or: npm install
# First-run config (.env, hub-config, mcp-servers)
pnpm setup # or: npm run setup
# Edit secrets / enable servers
# .env
# config/mcp-servers.json
# Multi-client SSE hub + GUI (recommended)
pnpm start:sse # after: pnpm build
# or: ./scripts/start.shMCP SSE:
http://127.0.0.1:3000/sseGUI:
http://127.0.0.1:3100(port auto-scans 3100–3109)Stdio mode (single client):
pnpm start
Windows: scripts\start.bat or START_ALL.bat.
Related MCP server: MetaMCP
What works today
Area | Status |
Downstream MCP via stdio ( | Working |
Tool namespacing ( | Working |
Local GUI + WebSocket | Working |
SSE multi-client (one Server per session) | Working |
Smart Router ( | Wired |
Skills as MCP resources ( | Working |
Auth / rate limits | Optional (config + |
Enable servers in config/mcp-servers.json. Example configs ship as *.example.json.
Architecture
AI clients (Claude / LM Studio / Cursor)
│ MCP (stdio or SSE)
▼
GameDev MCP Hub
· Smart Router (hub__route_task)
· Tool registry + search
· GUI (localhost)
│
▼
Downstream MCP servers (Blender, Godot, GitHub, …)Configuration
File | Purpose |
| API keys (see |
| Hub features, security, logging |
| Downstream servers |
| Tool categories |
GITHUB_TOKEN and GITHUB_PERSONAL_ACCESS_TOKEN are both accepted; the hub mirrors them when spawning servers.
By default HTTP/SSE/GUI bind to 127.0.0.1. Set security.bind_localhost_only: false only if you understand the risk. Set security.require_authentication: true and HUB_API_KEY to protect GUI mutation endpoints.
Scripts
pnpm build # compile + copy GUI assets
pnpm start # stdio transport
pnpm start:sse # SSE multi-client
pnpm test # unit tests
pnpm type-check
pnpm lintDocs
Session notes and historical status dumps live under archive/session-docs/.
License
MIT
Available Tools
5 toolshub__check_tokensB
Check current token usage and get recommendations
Inputs: no named parameters.
hub__get_analyticsC
Get usage analytics for tools and servers
Inputs: timeframe.
hub__list_serversC
List connected servers
Inputs: no named parameters.
hub__route_taskB
Route a natural-language task to the best tool(s)
Inputs: task (required).
hub__search_toolsC
Search tools by name/category
Inputs: query (required), category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
The tools are mostly distinct: search vs list vs analytics vs token check vs routing all have clear purposes. The only slight overlap is between 'search_tools' and 'route_task' (both help find tools), though route_task takes natural-language and adds routing logic, so the boundary is mostly clear.
All tools follow a consistent verb_noun snake_case pattern: search_tools, list_servers, get_analytics, check_tokens, route_task. Every name uses a clear action verb followed by a noun, with no style mixing.
Five tools is a reasonable, well-scoped count for a hub/meta-coordination server. Each tool addresses a distinct purpose (discovery, listing, analytics, token management, task routing). It sits slightly on the sparse side but is appropriate for the coordination-focused role with no apparent need for more.
The surface covers discovery, listing, analytics, token monitoring, and routing, which forms a coherent hub workflow. However, there's no tool to register/disconnect a server, no way to inspect a specific tool's detail beyond search, and no configuration or error-reporting capability, leaving some operational gaps for a hub that manages connected servers.
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAggregates multiple MCP servers and custom Python tools behind a single endpoint, with intelligent context and tool discovery for AI agents.-

MetaMCPofficial
AlicenseAqualityBmaintenanceAggregates multiple MCP servers into a single interface, reducing token overhead and simplifying tool management for LLMs.619Apache 2.0- AlicenseNot gradedqualityBmaintenanceThe most advanced MCP server for Godot Editor that lets AI assistants operate directly inside your running Godot project for scene creation, script generation, UI authoring, and more.55MIT
- AlicenseNot gradedqualityBmaintenanceSelf-hosted MCP gateway that aggregates many MCP servers into a single endpoint for AI clients, supporting hosted, local stdio, and Git-sourced MCPs.3MIT