digital-twin-mcp

Package the device data capabilities of digital twin scenarios into MCP tools—any MCP client (WorkBuddy, Claude Desktop, Cursor, etc.) can directly query device status, read real-time metrics, pull time-series data, and check alerts.

Architect of the Digital Pipeline · Second Building Block: Device Monitoring Pipeline First building block: https://github.com/xici001/workflow-templates (AI automation workflow templates)

What it can do

Related MCP server: MCP PLC Core

Architecture

MCP 客户端（WorkBuddy / Claude Desktop / ...）
        │  stdio 或 streamable-http
┌───────▼───────────────┐
│  server.py (FastMCP)  │  ← 工具 / 资源 / 提示词定义
└───────┬───────────────┘
        │
┌───────▼───────────────┐
│  alerts.py             │  告警规则引擎（阈值分级）
│  device_registry.py    │  设备台账 + 指标配置 + 3D 坐标
│  simulator.py          │  PLC 数据驱动（BasePLCDriver 接口）
└───────────────────────┘

• The v0 data source is a simulated PLC driver (fixed random seed, reproducible; injection molding machine temperature is deliberately drifted close to the threshold to make alert escalation easy to demonstrate).

• To connect real devices, inherit BasePLCDriver and implement read_metrics / write_value (OPC-UA / Modbus / gateway API all work), with zero changes to the Server layer.

Quick Start

pip install -e .
# 方式一：stdio 传输（MCP 客户端默认）
python -m digital_twin_mcp.server
# 方式二：streamable-http 传输
python -m digital_twin_mcp.server --transport streamable-http

End-to-end test (start the server subprocess and call it via the stdio protocol):

python examples/client_test.py

Integrate with WorkBuddy

Merge the contents of examples/workbuddy_mcp.json into the mcpServers key of C:\Users\33033\.workbuddy\mcp.json, then click "Trust" on digital-twin-mcp in the custom connector entry at the top right of the Connector Management page to enable it.

Relationship with workflow-templates

Two building blocks under the same "Digital Pipeline" brand:

• workflow-templates: Package mental work (financial report analysis, etc.) into workflows

• digital-twin-mcp: Package device data capabilities (digital twin / PLC) into MCP tools

The two can be combined in the future: templates such as "Device Health Report" in workflow templates can directly call this MCP's tools to fetch real data.

Roadmap

• v0.1: Simulated PLC + 5 tools + 2 resources + 1 prompt (current)

• v0.2: Real OPC-UA integration, time-series data persistence (SQLite/InfluxDB), WebSocket push

• v0.3: 3D scene integration (scene layout resource connected to Three.js rendering), multi-factory instances

License

MIT License