Factory Supervisor MCP Server

An enterprise-grade Model Context Protocol (MCP) server and interactive supervisory dashboard built with NitroStack, Node.js, Express, and React for real-time factory operations management, telemetry analysis, predictive maintenance, material forecasting, order estimation, and AI supervisor copilot capabilities.

Overview

The Factory Supervisor MCP Server connects AI assistants (such as Claude Desktop, Cursor, Antigravity, or custom MCP clients) directly to industrial shop floor telemetry, equipment diagnostics, inventory levels, maintenance schedules, and production orders.

Featuring 10 modular domains and 18 specialized MCP tools alongside an Express REST API and a React + Tailwind Control Center UI, operators and AI assistants can perform diagnostic checks, detect bottlenecks, forecast equipment failures, calculate risk exposure, and interact via natural language to maintain optimal factory productivity.

Related MCP server: Industrial MCP Agent Platform

Key Features

• Dual Architecture -- Serves as a standard Model Context Protocol (MCP) server over Stdio transport as well as a full Express REST API and Web Control Center UI.

• Real-Time Analytics and Scoring -- Automated numeric health scoring (0-100), machine severity assessment, inventory stockout warnings, and risk exposure calculations.

• Predictive Machine Intelligence -- Risk models for failure prediction, material depletion forecasting, bottleneck detection, and order completion estimation.

• AI Supervisor Copilot -- Natural language prompt routing, daily supervisor shift briefings, and executive financial summaries.

• Web Control Center UI -- Built with Vite, React 18, TailwindCSS, Lucide icons, and Framer Motion for telemetry visualization and AI interaction.

Modules and Tools Reference

Project Architecture

factory-supervisor-mcp/
├── src/
│   ├── index.ts                     Entry point and Express REST API
│   ├── app.module.ts                Root AppModule importing 10 feature modules
│   ├── ai/                          LLM Provider and MCP Client Integration
│   ├── mock/                        Mock telemetry data JSON files
│   └── modules/                     10 MCP Feature Modules
│       ├── analytics/               Consolidated factory analysis
│       ├── assistant/               Copilot, shift brief and executive tools
│       ├── health/                  System ping and health checks
│       ├── inventory/               Stock levels and low-stock detection
│       ├── kpi/                     OEE, Uptime and Quality metrics
│       ├── machines/                Telemetry and status tools
│       ├── maintenance/             Maintenance history and logs
│       ├── orders/                  Work orders and progress tracking
│       ├── prediction/              Prediction tools
│       └── schedule/                Production schedule data
├── ui/                              Web Control Center (React + Vite + Tailwind)
│   ├── src/                         Dashboard components, APIs, and state
│   └── index.html                   UI entry point
├── package.json                     Scripts and dependencies
├── run.bat                          Batch launcher for Backend + Frontend
├── run-server.bat                   Batch launcher for MCP Server
└── README.md

Quick Start

Prerequisites -- Node.js v18+ and npm v9+.

Clone the repository and install dependencies:

git clone https://github.com/Heytish-V/factory-supervisor-mcp.git
cd factory-supervisor-mcp
npm install

Copy .env.example to .env:

cp .env.example .env

Optionally configure your OpenAI API key in .env for LLM Copilot capabilities:

OPENAI_API_KEY=your_openai_api_key_here
REST_PORT=3001

One-Click Launcher (Windows) -- Run run.bat to build the project, launch the backend on port 3001, start the frontend on port 5173, and open the browser automatically.

run.bat

Development Mode -- Start the backend and frontend separately:

npm run dev          # Terminal 1: Backend MCP server
npm run ui:dev       # Terminal 2: Frontend dashboard

Production Build -- Compile TypeScript, sync mock data, and build UI assets:

npm run build
npm start

REST API Endpoints

When running the Express REST API (port 3001 by default), the following endpoints are available:

• GET /health -- Diagnostic health check.

• POST /chat -- Natural language interaction with the Factory Supervisor AI Copilot.

• GET /api/tools/:toolName or POST /api/tools/:toolName -- Direct execution of any of the 18 MCP tools.

MCP Client Integration

Add this MCP server to your MCP client configuration (such as Claude Desktop, Cursor, or Antigravity):

{
  "mcpServers": {
    "factory-supervisor": {
      "command": "node",
      "args": ["C:/projecctttt/factory-supervisor-mcp/dist/index.js"]
    }
  }
}

Example Prompts

When interacting through the web UI or an MCP client, try these sample queries:

• "What is the overall health score of the factory right now?"

• "Are any CNC machines at risk of failing in the next 24 hours?"

• "Which inventory items are currently below reorder thresholds?"

• "Will order ORD-2026-001 complete on time or experience delays?"

• "Generate a daily supervisor shift briefing for the current shift."

• "Provide an executive summary of factory performance and financial risk exposure."

License

Private / Enterprise Proprietary