roblox-mcp
Click on "Install 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., "@roblox-mcpCheck the current player count in my Roblox game"
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.
Roblox MCP — AI God Mode Dashboard
Version: 1.0
Author: Zsombi & Hermes Agent (Nous Research)
Status: Working prototype
Description
Roblox MCP (Model Context Protocol) is an AI-driven dashboard for Roblox games. The system operates as an MCP server, enabling AI assistants (Gemini/OpenAI) to communicate with Roblox games in real time. The project includes a Starlette/uvicorn web application with a modern "God Mode" themed frontend.
Related MCP server: Roblox MCP Server
File Structure
Roblox MCP/
│
├── roblox_ai_client.py # Main AI client and server (293 lines)
├── requirements.txt # Python dependencies
│
├── static/ # Static files
│ ├── index.html # Dashboard HTML (God Mode theme)
│ ├── style.css # Stylesheet
│ └── script.js # JavaScript client
│
└── README.md # This documentUsage
Installation
pip install -r requirements.txtStarting the Server
python roblox_ai_client.pyThe server starts at http://localhost:8000 by default.
Accessing the Dashboard
Open in your browser:
http://localhost:8000Features
AI Chat — Real-time chat with Gemini/OpenAI models
MCP Connection — Model Context Protocol integration
WebSocket — Real-time bidirectional communication
Log System — Real-time log forwarding to frontend
Multiple AI Providers — Gemini and OpenAI support
Chat History — Session-based chat history
God Mode Dashboard — Cyberpunk/sci-fi themed interface
API Endpoints
Endpoint | Type | Description |
| GET | Dashboard HTML |
| POST | Create MCP connection |
| POST | Send chat message |
| WebSocket | Real-time connection |
| Mount | Static files |
Dependencies
Python 3.10+
mcp ≥ 1.0.0 — Model Context Protocol
openai ≥ 1.12.0 — OpenAI API client
python-dotenv ≥ 1.0.0 — Environment variables
fastapi ≥ 0.100.0 — Web framework (Starlette)
uvicorn ≥ 0.22.0 — ASGI server
websockets ≥ 11.0.0 — WebSocket support
Environment Variables
Create a .env file:
# Gemini API
GOOGLE_API_KEY=your_key_here
# OpenAI API (optional)
OPENAI_API_KEY=your_key_hereDeveloper
Zsombi & Hermes Agent (Nous Research)
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zsomborturcsanyi7-lang/roblox-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server