CNC / MACHINE TOOL · CANONICAL DATA MODEL

Trumpf canonical data model: connect your Trumpf equipment to any AI agent

2,086 mappings·19 verticals·13 protocols

Forge turns raw Trumpf tags into one clean, governed schema your AI agent already understands. One MCP call, no per-machine integration project.

Try it free: 3 machines, no credit card → See it work →

Paste your Trumpf data and see it normalized in 30 seconds. No POC required.

Read-only. Forge reads your Trumpf data through standard industrial protocols. Read-only. Your equipment is never at risk.

The problem

Why Trumpf data is hard to integrate

Trumpf sheet-metal machines expose data through the OPC UA-based Trumpf ecosystem and MQTT, with laser-specific tags that don't fit generic CNC schemas until they're mapped.

Typical Trumpf equipment communicates over OPC UA, MQTT Sparkplug B. Each firmware revision, model line and integrator names the same physical quantity differently, so every AI or analytics project pays the integration tax again, the tax that cancels 40% of industrial AI deployments before they ship.

The solution

One universal schema for every Trumpf machine

Forge resolves Trumpf telemetry into Forge's canonical field set, the same 985 canonical fields defined, used across 45 vendor packs. Point Forge at the machine, pass oem: "trumpf", and spindle speed is spindle_speed_rpm whether it came from a Trumpf controller or anything else on the floor.

OPC UAMQTT Sparkplug B

45OEM packs in production

17Canonical CNC / machine tool fields

2,086Mappings in production

Field coverage

What Forge resolves for Trumpf

Confirmed canonical fields your agent gets from Trumpf machines, drawn from Forge's 2,086-mapping corpus:

spindle_speed_rpmspindle_load_pctspindle_current_ampsaxes.0.position_actualaxes.0.load_percentaxes.0.temperature_cfeed_ratecnc.path.feedrateprogram_nameprogram_numberpart_counttool_id

Sample normalization

Raw tag in		Canonical field out	Meaning
spindle_rpm: 4200	→	spindle_speed_rpm: 4200	actual spindle speed
sp_load_pct: 63	→	spindle_load_pct: 63	spindle load
active_prog: "TRUMPF-01"	→	program_name: "TRUMPF-01"	active program
part_ct: 1540	→	part_count: 1540	part count

30-second deployment

Add Trumpf to your agent with one call

No SDK, no per-tag mapping, no historian project. Connect the MCP server and normalize live Trumpf data:

claude mcp add --transport http forge https://mcp.foundrynet.io/mcp --header 'Authorization: Bearer YOUR_API_KEY'

# normalize raw Trumpf telemetry into the universal schema

curl -s https://forge.foundrynet.io/v1/normalize \

-H 'Content-Type: application/json' \

-d '{"data": {"spindle_rpm": 4200, "sp_load_pct": 63, "active_prog": "TRUMPF-01"}, "oem": "trumpf"}'

{"spindle_speed_rpm": 4200, "spindle_load_pct": 63, "program_name": "TRUMPF-01", "coverage": "100%", "confidence": 0.97}

Unknown tags never get force-mapped. Fields below the confidence floor abstain rather than guess, so your agent never acts on a bad reading.

Start free: Forge API, 3 machines → See the full demo →

Where Trumpf fits

Protocols
OPC UA MQTT Sparkplug B

Vertical
CNC / machine tool

Other CNC / machine tool vendors
DMG Mori Fanuc Haas Heidenhain Mazak Okuma

Same protocols, other industries
ABB Robotics KUKA Universal Robots Chemical process

Also searched as trumpf, trulaser, tastic

Trumpf in the canonical schema

Canonical fields this OEM maps

spindle_speed_rpm spindle_load_pct axes.0.position_actual axes.0.load_percent axes.0.temperature_c feed_rate program_name part_count All fields →

Protocol comparisons

Modbus TCP vs OPC UA MTConnect vs OPC UA MQTT / Sparkplug B vs OPC UA J1939 (CAN) vs OPC UA Modbus TCP vs MQTT / Sparkplug B