FoundryNet / OEMs / Okuma

CNC / MACHINE TOOL · TELEMETRY NORMALIZATION

Okuma telemetry normalization: connect your Okuma equipment to any AI agent

16,908 confirmed mappings·18 OEM families·14 protocols·99% field coverage

Forge turns raw Okuma 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 the full demo →

The problem

Why Okuma data is hard to integrate

Okuma's THINC-API is powerful but proprietary: SpindleRPM, SpLoadPct and MainPrg are exposed as THINC objects that each app has to translate before an agent can use them.

Typical Okuma equipment communicates over MTConnect, OPC UA. 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 Okuma machine

Forge normalizes Okuma telemetry into Forge's canonical field set, the same 366 canonical fields used across all 18 manufacturers. Point Forge at the machine, pass oem: "okuma", and spindle speed is spindle_speed_rpm whether it came from a Okuma controller or anything else on the floor.

MTConnectOPC UA
99%Field coverage
17Canonical CNC / machine tool fields
16,908Corpus mappings

Field coverage

What Forge normalizes for Okuma

Confirmed canonical fields your agent gets from Okuma machines, drawn from Forge's 16,908-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 inCanonical field outMeaning
SpindleRPM: 4500spindle_speed_rpm: 4500THINC spindle rpm
SpLoadPct: 66spindle_load_pct: 66spindle load
MainPrg: "OKU_45.MIN"program_name: "OKU_45.MIN"main program
PartsMachined: 1780part_count: 1780parts machined

30-second deployment

Add Okuma to your agent with one call

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

claude mcp add --transport http forge https://mcp.foundrynet.io/mcp --header 'Authorization: Bearer YOUR_API_KEY'
# normalize raw Okuma telemetry into the universal schema
curl -s https://forge.foundrynet.io/v1/normalize \
  -H 'Content-Type: application/json' \
  -d '{"data": {"SpindleRPM": 4500, "SpLoadPct": 66, "MainPrg": "OKU_45.MIN"}, "oem": "okuma"}'
{"spindle_speed_rpm": 4500, "spindle_load_pct": 66, "program_name": "OKU_45.MIN", "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 Connect, 3 machines → See the full demo →