Industrial MCP Server
Enables AI assistants to monitor and interact with industrial systems, providing real-time system health monitoring, operational data analytics, and equipment maintenance tracking. Built with Next.js and designed for industrial automation environments.
README
🏭 Industrial MCP Server
A comprehensive Model Context Protocol (MCP) server designed for industrial system monitoring and control. Built with Next.js, TypeScript, and the Vercel MCP adapter, this server provides Claude AI with powerful tools to interact with industrial systems.
🚀 Live Demo
- Production Server: https://industrial-mcp-delta.vercel.app
- MCP Endpoint: https://industrial-mcp-delta.vercel.app/api/mcp
✨ Features
Available MCP Tools
- 🔄 Echo Tool - Basic communication testing
- 📊 System Status - Real-time industrial system health monitoring
- 📈 Operational Data - Performance metrics and analytics
- 🔧 Equipment Monitor - Individual equipment status and maintenance tracking
Industrial Metrics Provided
- System uptime and health status
- CPU, memory, disk, and network monitoring
- Throughput and performance analytics
- Equipment temperature, vibration, and pressure readings
- Maintenance scheduling and alerts
- Historical trend analysis
🛠️ Quick Start
Prerequisites
- Node.js 18+
- npm or yarn
- Git
Installation
- Clone the repository:
git clone https://github.com/intecrel/industrial-mcp.git
cd industrial-mcp
- Install dependencies:
npm install
- Start development server:
npm run dev
- Verify the server is running:
# Test basic endpoint
curl http://localhost:3000/api/mcp
# Test MCP protocol initialization
curl -X POST http://localhost:3000/api/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2024-11-05",
"capabilities": {"roots": {"listChanged": false}},
"clientInfo": {"name": "test-client", "version": "1.0.0"}
}
}'
🧪 Testing with MCP Inspector
The MCP Inspector provides a web interface for testing your MCP server:
# Install MCP Inspector globally
npm install -g @modelcontextprotocol/inspector
# Run inspector against local server
mcp-inspector http://localhost:3000/api/mcp
# Or run against production server
mcp-inspector https://industrial-fvucjqopi-samuels-projects-2dd2e35e.vercel.app/api/mcp
🤖 Claude Desktop Integration
To connect this MCP server to Claude Desktop:
1. Edit Claude Desktop Configuration
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
2. Add Server Configuration
{
"mcpServers": {
"industrial-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-fetch",
"http://localhost:3000/api/mcp"
]
}
}
}
3. Restart Claude Desktop
After saving the configuration, restart Claude Desktop to load the new MCP server.
4. Test in Claude
You can now use commands like:
- "Get the industrial system status"
- "Show me operational data for the last 24 hours"
- "Monitor equipment ID-12345 with history"
- "Echo test message"
🌐 Deployment
Deploy to Vercel
# Install Vercel CLI
npm install -g vercel
# Deploy to Vercel
vercel
# Deploy to production
vercel --prod
📁 Project Structure
industrial-mcp/
├── app/
│ ├── api/
│ │ └── [transport]/
│ │ └── route.ts # Main MCP server implementation
│ ├── dashboard/
│ │ └── page.tsx # Web dashboard
│ ├── globals.css # Global styles
│ ├── layout.tsx # Root layout
│ └── page.tsx # Home page
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── tailwind.config.js # Tailwind CSS configuration
├── next.config.js # Next.js configuration
└── README.md # This file
🔧 API Reference
MCP Protocol Endpoints
All MCP communication happens via JSON-RPC 2.0 over HTTP:
Base URL: /api/mcp
Initialize Connection
{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2024-11-05",
"capabilities": {"roots": {"listChanged": false}},
"clientInfo": {"name": "client", "version": "1.0.0"}
}
}
List Available Tools
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/list",
"params": {}
}
Call a Tool
{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "get_system_status",
"arguments": {}
}
}
Tool Specifications
Echo Tool
- Name:
echo - Parameters:
message(string, required) - Returns: Echoed message
System Status Tool
- Name:
get_system_status - Parameters: None
- Returns: System health metrics, uptime, alerts
Operational Data Tool
- Name:
get_operational_data - Parameters:
timeRange(string, optional): "1h", "24h", "7d"system(string, optional): Specific system to query
- Returns: Performance metrics and trends
Equipment Monitor Tool
- Name:
monitor_equipment - Parameters:
equipmentId(string, required): Equipment identifierincludeHistory(boolean, optional): Include historical data
- Returns: Equipment status, metrics, maintenance info
🐛 Troubleshooting
Common Issues
-
"Cannot find module '@vercel/mcp-adapter'"
npm install @vercel/mcp-adapter -
"Method not allowed" errors
- Ensure you're using POST requests for MCP protocol
- Include proper headers:
Content-Type: application/jsonandAccept: application/json, text/event-stream
-
Connection refused in Claude Desktop
- Verify the server is running on the correct port
- Check Claude Desktop configuration file syntax
- Restart Claude Desktop after configuration changes
-
Build errors on deployment
npm run build # Test build locally first npm run lint # Fix any linting issues
Debug Mode
Enable verbose logging by setting the environment variable:
DEBUG=mcp:* npm run dev
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit changes:
git commit -m 'Add amazing feature' - Push to branch:
git push origin feature/amazing-feature - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Model Context Protocol - The protocol specification
- Vercel MCP Adapter - MCP implementation for Vercel
- Claude AI - AI assistant integration
- Next.js - React framework
- Anthropic - MCP protocol development
📞 Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Email: sam@industrial.marketing
Made with ❤️ for Industrial Automation and AI Integration
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。