MCP & AI Agent Integration

Twin
automation.

18 AI agent actions for Twin — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Twin to automate business processes and connect tools in your stack. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
18
actions
100%
governed
<200ms
latency
18
AI agent actions
8
Read operations
10
Write operations
2
High-risk actions (approval gated)
Business Tools Twin is a Business Tools integration — use it to automate business operations and workflow automation from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Twin.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Alerts
twin:get_alerts
Retrieve alerts with optional filtering and pagination.
Read Low risk
Get Device
twin:get_device
Fetch a single device by ID with its properties and current status.
Read Low risk
Get Sensor
twin:get_sensor
Fetch a single sensor by ID with its properties and latest reading.
Read Low risk
Get Sensor Data
twin:get_sensor_data
Retrieve sensor data readings with optional time range and aggregation.
Read Low risk
Get Space
twin:get_space
Fetch a single space by ID with its properties and metadata.
Read Low risk
List Devices
twin:list_devices
List devices with optional filtering and pagination.
Read Low risk
List Sensors
twin:list_sensors
List sensors with optional filtering and pagination.
Read Low risk
List Spaces
twin:list_spaces
List spaces with optional filtering and pagination.
Read Low risk
Acknowledge Alert
twin:acknowledge_alert
Acknowledge an active alert to indicate it has been seen and is being handled.
Write Medium risk
Create Device
twin:create_device
Create a new device in a space.
Write Medium risk
Create Sensor
twin:create_sensor
Create a new sensor on a device.
Write Medium risk
Create Space
twin:create_space
Create a new space in the Twin platform.
Write Medium risk
Delete Device
twin:delete_device
Delete a device permanently. This will also remove all associated sensors and data.
Write High risk
Delete Space
twin:delete_space
Delete a space permanently. This will also remove all associated devices and sensors.
Write High risk
Resolve Alert
twin:resolve_alert
Resolve an alert to mark it as fixed and close it.
Write Medium risk
Send Sensor Data
twin:send_sensor_data
Send a new data reading to a sensor.
Write Medium risk
Update Device
twin:update_device
Update an existing device's properties.
Write Medium risk
Update Space
twin:update_space
Update an existing space's properties.
Write Medium risk
MCP & Runtime API

Call Twin
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Twin actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

twin:get_alerts READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "twin:get_alerts",
    "args": {},
    "execution_id": "agent-001"
  }'
twin:acknowledge_alert WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "twin:acknowledge_alert",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Twin.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Twin data
Call twin:get_alerts via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Twin
Dry-run validates twin:acknowledge_alert before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Twin
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Twin action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Twin — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Twin action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Twin action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Twin works best
alongside these.

Build multi-step workflows that connect Twin to the rest of your stack. All governed. All audited.

Twin integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Twin in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →