Skip to main content
Glama
Sign In
deenesjakoruzh
digital-twin-mcp

digital-twin-mcp

by xici001
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

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

Tool

Description

list_devices

List all devices in the scene (type / location)

get_device_metrics

Read real-time device metrics (simulated PLC polling)

get_metric_history

Read recent time-series data for a metric (for trend charts / 3D visualization)

set_device_value

Write device parameters (simulated PLC write / fault injection testing)

check_alerts

Threshold alert check (warning / critical levels)

Resource

Description

device://{id}/profile

Device ledger: metadata + metric ranges and alert thresholds

scene://layout

3D scene layout: device world coordinates (directly overlayable in Three.js / Unity)

Prompt

Description

device_health_report

Generate a health report for the specified device

Related MCP server: AetherEdge

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

Available Tools

6 tools
check_alertsA

检查告警：不传 device_id 时遍历全部设备，返回 warning / critical 分级告警列表。

Inputs: device_id. Returns: result

get_device_metricsA

读取设备实时指标，返回指标名 / 数值 / 单位（每次调用推进一个采样周期）。

Inputs: device_id (required). Returns: object

get_metric_historyA

读取设备某指标的最近 N 个采样值（时序数据，供趋势图 / 3D 可视化使用）。

Inputs: metric (required), device_id (required), points. Returns: object

get_scene_snapshotA

数字孪生场景快照：一次调用返回全部设备的坐标、实时指标与分级告警（专供可视化 / 监控轮询）。

Inputs: no named parameters. Returns: object

list_devicesA

列出数字孪生场景中的所有设备（含类型与所在位置）。

Inputs: no named parameters. Returns: result

set_device_valueA

写入设备参数（模拟 PLC 写值；也可用于演示故障注入，如手动抬高温度触发告警）。

Inputs: value (required), metric (required), device_id (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.1/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool addresses a distinct concern: device enumeration, live metric read, historical metric retrieval, parameter write, alert checking, and a full scene snapshot. No two tools overlap in purpose, and the descriptions reinforce their boundaries.

    Naming Consistency5/5

    All tool names follow the verb_noun pattern in snake_case (list_devices, get_device_metrics, get_metric_history, set_device_value, check_alerts, get_scene_snapshot). The pattern is predictable and consistent.

    Tool Count5/5

    Six tools form a well-scoped set for a digital twin server, covering read, write, history, alerts, and snapshot use cases without bloat. The count is ideal for the domain and avoids both thin and heavy footprints.

    Completeness5/5

    The tool surface covers the full lifecycle of interacting with a simulated twin: listing devices, reading live metrics and history, writing values for control or fault injection, checking alerts, and obtaining a complete scene snapshot. No obvious gaps exist for the stated purpose.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MCP PLC Core

      Maxkrempl
      A
      license
      B
      quality
      C
      maintenance
      Universal MCP server for industrial PLC communication, enabling AI agents to read sensors, alarms, status, setpoints, and write setpoints via adapters for Modbus, S7, or custom PLCs.
      6
      MIT

    • AetherEdge

      EvanL1
      A
      license
      B
      quality
      C
      maintenance
      Exposes a deterministic IoT edge runtime — Modbus/CAN/J1939 acquisition, local rules, alarms, and history — to AI assistants as typed, governed MCP tools. Reads are safe by default; device control stays deny-by-default, explicitly confirmed, and audited.
      23
      3
      Apache 2.0

    • mcp-live-telemetry

      Younes-Alaoui-Ismaili
      A
      license
      A
      quality
      C
      maintenance
      Exposes live industrial IoT telemetry to any MCP client, streaming simulated sensor data from a fleet of machines and detecting anomalies, with the ability to inject faults on demand.
      4
      MIT