CMMS MCP Server
Integrates with MES, CMMS, and IoT systems to manage manufacturing operations, maintenance tasks, and asset tracking. It enables users to query production orders, create maintenance records, and monitor real-time sensor data and alerts.
README
CMMS MCP Server
A Model Context Protocol (MCP) server that integrates with MES (Manufacturing Execution System), CMMS (Computerized Maintenance Management System), and IoT systems. This server provides tools and resources to interact with manufacturing, maintenance, and IoT data.
Features
MES Integration
- Production Orders: Query production orders by status or ID
- Work Orders: Get work orders filtered by status or production order
- Equipment: Monitor equipment status and details
CMMS Integration
- Maintenance Tasks: Query, filter, and create maintenance tasks
- Assets: Get asset information and status
- Maintenance History: Access historical maintenance records
IoT Integration
- Sensors: Query sensor information and configurations
- Sensor Readings: Get real-time and historical sensor data
- Devices: Monitor IoT device status
- Alerts: View and acknowledge IoT alerts
Installation
- Install dependencies:
npm install
- Build the project:
npm run build
Usage
Running the Server
The server runs on stdio and can be used with MCP-compatible clients:
npm start
For development with auto-reload:
npm run dev
MCP Client Configuration
Add this server to your MCP client configuration (e.g., in Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"cmms-mcp-server": {
"command": "node",
"args": ["/path/to/cmms-mcp-server/dist/index.js"]
}
}
}
Available Tools
MES Tools
get_production_orders
Get production orders from MES system.
Parameters:
status(optional): Filter by status (planned,in-progress,completed,cancelled)orderId(optional): Get specific production order by ID
Example:
{
"status": "in-progress"
}
get_work_orders
Get work orders from MES system.
Parameters:
status(optional): Filter by status (pending,in-progress,completed,on-hold)productionOrderId(optional): Filter by production order ID
get_equipment
Get equipment status from MES system.
Parameters:
status(optional): Filter by status (running,idle,maintenance,error)equipmentId(optional): Get specific equipment by ID
CMMS Tools
get_maintenance_tasks
Get maintenance tasks from CMMS system.
Parameters:
status(optional): Filter by status (scheduled,in-progress,completed,cancelled,overdue)priority(optional): Filter by priority (low,medium,high,critical)taskType(optional): Filter by type (preventive,corrective,inspection,calibration)assetId(optional): Filter by asset ID
get_assets
Get assets from CMMS system.
Parameters:
status(optional): Filter by status (operational,maintenance,out-of-service,retired)assetId(optional): Get specific asset by ID
get_maintenance_history
Get maintenance history from CMMS system.
Parameters:
assetId(optional): Filter by asset IDstartDate(optional): Start date for history (ISO format)endDate(optional): End date for history (ISO format)
create_maintenance_task
Create a new maintenance task in CMMS system.
Required Parameters:
assetId: Asset ID for the maintenance tasktaskType: Type of maintenance task (preventive,corrective,inspection,calibration)priority: Priority of the task (low,medium,high,critical)scheduledDate: Scheduled date (ISO format)dueDate: Due date (ISO format)assignedTo: Technician ID assigned to the taskdescription: Description of the maintenance task
Optional Parameters:
estimatedDuration: Estimated duration in minutes (default: 240)
Example:
{
"assetId": "asset-001",
"taskType": "preventive",
"priority": "high",
"scheduledDate": "2024-02-15T08:00:00Z",
"dueDate": "2024-02-15T17:00:00Z",
"assignedTo": "tech-001",
"description": "Monthly preventive maintenance",
"estimatedDuration": 480
}
IoT Tools
get_sensors
Get sensors from IoT system.
Parameters:
type(optional): Filter by type (temperature,pressure,vibration,humidity,flow,level)status(optional): Filter by status (active,inactive,error)equipmentId(optional): Filter by equipment ID
get_sensor_readings
Get sensor readings from IoT system.
Parameters:
sensorId(optional): Filter by sensor IDstatus(optional): Filter by reading status (normal,warning,critical)hours(optional): Get readings from last N hours
get_devices
Get IoT devices.
Parameters:
status(optional): Filter by status (online,offline,error)type(optional): Filter by device type
get_alerts
Get IoT alerts.
Parameters:
severity(optional): Filter by severity (info,warning,critical)acknowledged(optional): Filter by acknowledged status (boolean)deviceId(optional): Filter by device ID
acknowledge_alert
Acknowledge an IoT alert.
Required Parameters:
alertId: Alert ID to acknowledgeacknowledgedBy: User ID acknowledging the alert
Available Resources
The server provides the following resources:
mes://production-orders- All production orders from MES systemmes://equipment- All equipment from MES systemcmms://maintenance-tasks- All maintenance tasks from CMMS systemcmms://assets- All assets from CMMS systemiot://sensors- All sensors from IoT systemiot://alerts- All active (unacknowledged) alerts from IoT system
Mock Data
This server currently uses mock data for demonstration purposes. The mock data includes:
- MES: 3 production orders, 3 work orders, 4 equipment items
- CMMS: 4 maintenance tasks, 4 assets, 2 maintenance history records
- IoT: 5 sensors, 6 sensor readings, 4 devices, 4 alerts
To connect to real systems, replace the mock data imports in src/index.ts with actual API clients.
Project Structure
cmms-mcp-server/
├── src/
│ ├── index.ts # Main server implementation
│ └── mock-data/
│ ├── mes-data.ts # MES mock data
│ ├── cmms-data.ts # CMMS mock data
│ └── iot-data.ts # IoT mock data
├── dist/ # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
└── README.md
Testing
See TESTING.md for detailed testing instructions.
Quick test:
npm test
Development
Building
npm run build
Development Mode
npm run dev
This runs the server in watch mode with auto-reload using tsx.
License
MIT
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。