MCP & AI Agent Integration

Onfleet
automation.

32 AI agent actions for Onfleet — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Onfleet to track shipments, trigger fulfillment, and notify customers on delivery events. 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
32
actions
100%
governed
<200ms
latency
32
AI agent actions
13
Read operations
19
Write operations
4
High-risk actions (approval gated)
Shipping Onfleet is a Shipping integration — use it to automate shipment tracking, fulfillment, and logistics from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Onfleet.

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 Destination
onfleet:get_destination
Fetch a single destination by ID with location and address details.
Read Low risk
Get Organization
onfleet:get_organization
Fetch organization details including name, email, timezone, and country.
Read Low risk
Get Recipient
onfleet:get_recipient
Fetch a single recipient by ID with contact details and notification preferences.
Read Low risk
Get Task
onfleet:get_task
Fetch a single task by ID with full details including destination, recipients, and completion info.
Read Low risk
Get Team
onfleet:get_team
Fetch a single team by ID with workers, managers, and hub information.
Read Low risk
Get Worker
onfleet:get_worker
Fetch a single worker by ID with location, state, and team information.
Read Low risk
List Administrators
onfleet:list_administrators
List all administrators in the organization.
Read Low risk
List Destinations
onfleet:list_destinations
List all destinations in the organization.
Read Low risk
List Hubs
onfleet:list_hubs
List all hubs (distribution centers) in the organization.
Read Low risk
List Recipients
onfleet:list_recipients
List recipients with optional filters for phone or name.
Read Low risk
List Tasks
onfleet:list_tasks
List tasks with optional filters for state, worker, team, recipient, or date range.
Read Low risk
List Teams
onfleet:list_teams
List all teams in the organization.
Read Low risk
List Workers
onfleet:list_workers
List workers with optional filters for state, team, or phone.
Read Low risk
Assign Task
onfleet:assign_task
Assign a task to a specific worker.
Write Medium risk
Complete Task
onfleet:complete_task
Mark a task as completed with optional notes and success status.
Write Medium risk
Create Administrator
onfleet:create_administrator
Create a new administrator in the organization.
Write Medium risk
Create Destination
onfleet:create_destination
Create a new destination with address. Onfleet will geocode the address automatically.
Write Medium risk
Create Hub
onfleet:create_hub
Create a new hub (distribution center) with name and address.
Write Medium risk
Create Recipient
onfleet:create_recipient
Create a new recipient with name, phone, and notification preferences.
Write Medium risk
Create Task
onfleet:create_task
Create a new delivery task with destination, recipients, and scheduling options.
Write Medium risk
Create Team
onfleet:create_team
Create a new team with name and optional worker/manager assignments.
Write Medium risk
Create Worker
onfleet:create_worker
Create a new worker with name, phone, and optional team assignments.
Write Medium risk
Delete Administrator
onfleet:delete_administrator
Delete an administrator from the organization. This action cannot be undone.
Write High risk
Delete Task
onfleet:delete_task
Delete a task from the organization. This action cannot be undone.
Write High risk
Delete Team
onfleet:delete_team
Delete a team from the organization. This action cannot be undone.
Write High risk
Delete Worker
onfleet:delete_worker
Delete a worker from the organization. This action cannot be undone.
Write High risk
Unassign Task
onfleet:unassign_task
Unassign a task from its current worker, returning it to unassigned state.
Write Medium risk
Update Administrator
onfleet:update_administrator
Update an existing administrator's details.
Write Medium risk
Update Recipient
onfleet:update_recipient
Update an existing recipient's details and notification preferences.
Write Medium risk
Update Task
onfleet:update_task
Update an existing task's notes, schedule, recipients, or dependencies.
Write Medium risk
Update Team
onfleet:update_team
Update an existing team's name, workers, managers, or hub assignment.
Write Medium risk
Update Worker
onfleet:update_worker
Update an existing worker's details, teams, or vehicle information.
Write Medium risk
MCP & Runtime API

Call Onfleet
from any AI agent.

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

onfleet:get_destination READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "onfleet:get_destination",
    "args": {},
    "execution_id": "agent-001"
  }'
onfleet:assign_task 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": "onfleet:assign_task",
    "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 Onfleet.

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 Onfleet data
Call onfleet:get_destination 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 Onfleet
Dry-run validates onfleet:assign_task before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Onfleet
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Onfleet action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Onfleet — 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 Onfleet action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Onfleet action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Onfleet works best
alongside these.

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

Onfleet integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →