IoT/Edge MCP Server

Model Context Protocol (MCP) server for Industrial IoT, Edge Computing and Automation

This server transforms industrial infrastructure into an AI-orchestrable system, exposing 11 powerful tools for complete IoT/SCADA/PLC control via HTTP endpoints. Perfect for AI-driven industrial automation, predictive maintenance, and smart factory operations.

✨ Features

• 🏭 Multi-Protocol Support - Unified interface for industrial systems:

  • MQTT for wireless IoT sensors and actuators
  • Modbus TCP/RTU for PLC and industrial devices
  • Time-series data with InfluxDB integration
  • Real-time caching with Redis
  • Simulated mode for testing without hardware

• 📊 Complete Sensor Management - Monitor and analyze industrial data:

  • Real-time sensor readings (temperature, pressure, flow, etc.)
  • Historical data with aggregations (mean, max, min)
  • Multi-sensor batch operations
  • Quality indicators and signal monitoring

• ⚡ Actuator Control - Command industrial equipment:

  • Valve control (open/close)
  • Motor management (start/stop/speed)
  • Pump operations
  • PLC register manipulation

• 🚨 Alarm System - Enterprise-grade monitoring:

  • Multi-priority alarms (LOW, MEDIUM, HIGH, CRITICAL)
  • Automatic threshold monitoring
  • Alarm acknowledgment tracking
  • Real-time notifications

• 🔒 Production Features - Enterprise-ready:

  • Rate limiting for command safety
  • Comprehensive error handling
  • Connection pooling and auto-reconnect
  • Full audit logging
  • Thread-safe operations

🚀 Quick Start

Installation

# Clone the repository
git clone https://github.com/llm-use/iot-mcp-server.git
cd iot-mcp-server

# Install dependencies
pip install -r requirements.txt

# For testing without hardware, use simulation mode
pip install -r requirements-sim.txt

Starting the Server

Option 1: Simulation Mode (No Hardware Required)

python IoT_mcp_sim.py

Option 2: Production Mode (Real Hardware)

# Configure your devices in iot_config.yaml
# Start required services (MQTT, InfluxDB, Redis)
docker-compose up -d

# Start the server
python IoT_mcp.py

Server will start on http://localhost:8000

🤖 Using with PolyMCP

This MCP server is designed to work seamlessly with PolyMCP - a powerful framework for orchestrating MCP servers with AI agents.

Example: AI-Controlled Industrial System

#!/usr/bin/env python3
import asyncio
from polymcp.polyagent import UnifiedPolyAgent, OllamaProvider

async def main():
    # Initialize your LLM provider
    llm = OllamaProvider(model="gpt-oss:120b-cloud", temperature=0.1)
    
    # Connect to IoT MCP server
    agent = UnifiedPolyAgent(
        llm_provider=llm, 
        mcp_servers=["http://localhost:8000/mcp"],  
        verbose=True
    )
    
    async with agent:
        print("✅ IoT MCP Server connected!\n")