MakeIntelligent Get access
MCP server, included with every plant hub

Ask your plant questions in Claude or Cursor.

A plant-local MCP server that turns tags, assets, history and alarms into typed tools. Plug it into Claude, Cursor or your own agent and ask the factory questions in plain language.

Claude DesktopClaude CodeCursorAny MCP client
  Cursor · mii MCP 14 tools
Which alarms are active on the packaging area, and what do they stop?
mii_monitor_alarms(area: "Packaging", state: "active")
2 active · HI Sealer-3.temp 212 °C · LO Air-Header.pressure 4.1 bar
mii_understand_impact(asset: "Air-Header")
depends_on ← Sealer-3, Wrapper-1, Labeler-2
mii_history_last(tag: "Air-Header.pressure")
4.1 bar · setpoint 6.0 · falling since 09:42
Two alarms. The low air pressure is the real one: three machines depend on that header, and it has been falling since 09:42. Sealer-3's temperature alarm is likely a knock-on effect.

Fourteen tools. One plant model.

Grouped into toolsets you can enable per client with ?toolsets=see,history. Every result is enriched with name, unit, quality and source.

Seelive

Live values

Find tags by name or asset, read current values with unit and quality.

mii_see_find · mii_see_values
mii_see_describe · mii_see_read
Historylive

Time series

Ranges and last-known values from the plant historian — no export, no CSV.

mii_history_series
mii_history_last
Understandlive

Asset graph

contains · feeds · controls · depends_on. Ask "what stops if this stops?"

mii_understand_graph
mii_understand_impact
Monitorlive

Plant health

Inventory, device connection state, runtime status and active alarms.

mii_monitor_inventory · mii_monitor_devices
mii_monitor_runtimes · mii_monitor_alarms
Actpropose

Proposals

The model can suggest a change. A person approves it in Console.

mii_act_proposals
Metalive

Identity

Which user, which role, which plant — so the model knows its limits.

mii_meta_whoami
Step 1

Add one server. Done.

Create an agent credential in Console, then export ready-made settings with ?export=claude or ?export=cursor. Streamable HTTP, JSON-RPC, nothing to install on the client.

# Claude Code
claude mcp add --transport http mii \
  https://plant.local/agent/v1/mcp \
  --header "Authorization: Bearer mii_ac_••••"

# Cursor · .cursor/mcp.json
{ "mcpServers": { "mii": {
    "url": "https://plant.local/agent/v1/mcp" } } }
Step 2

Answers with a trail.

Because every value comes from a typed tool call, every answer can be traced back to a tag, a time range and a quality flag. No hallucinated readings.

  • Shift handover summaries
  • Root-cause from alarm floods
  • "What changed since yesterday?"
  • Engineering in Cursor with live plant context
tools/call mii_history_series
{
  "tag": "Line2/P-101/vibration",
  "from": "-8h", "step": "5m"
}
→ 96 points · unit mm/s · quality GOOD
  source mi-tsdb@plant-hub

Built for OT security teams, not around them.

Identity

Console RBAC

Each call carries a Console JWT or a scoped mii_ac_* credential. Roles filter which tools even appear.

Isolation

No PLC socket

The model talks to the hub, never to the floor. Field protocols stay inside Site Runtimes.

Change control

Propose, then approve

Writes become proposals with a human approval step. Every call and decision lands in the audit log.

Data residency

Plant-local

History never leaves the hub unless you send it. One plant, one historian.

Model choice

Bring any model

Claude over MCP, or a local OpenAI-compatible model for fully air-gapped sites.

Scoping

Toolsets per client

Give a shift assistant see,monitor and an engineer history,understand.

Ask your plant something real.

We'll connect one line and hand your team an MCP URL. Bring Claude or Cursor; we bring the context.