Manage Connecteam's deskless workforce: employees, time clock, scheduling, forms and tasks.
Connecteam ships in the w6w first-party pack. It declares 27 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.connecteamConnecteam is deskless workforce management: employee directory, GPS time clock, shift scheduling, digital forms and task boards for teams that don’t sit at a desk.
This app covers Connecteam’s REST API v1 (api.connecteam.com) end to end for the surfaces a workflow needs most: read, create, update and archive employees; clock a user in and out and read or write their time-clock entries and timesheet totals; list, create, update and delete shifts on a schedule; read forms and their submissions; and list, create and update tasks on a task board.
Every action stays inside what the vendor’s own OpenAPI document declares — no endpoint here was inferred from a sibling integration or guessed from a UI screenshot.
Three routes to the same 27 actions. The Workflow tab is generated from Connecteam's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
time-activity-create Back-fill shifts and/or manual breaks for one or more users on a time clock.
time-activity-delete Delete one shift, manual break or time-off entry from a time clock.
time-activity-list List shifts, manual breaks and time-off entries recorded on a time clock.
timesheet-get Get hour totals per user for a time clock over a date range (max 45 days).
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Connecteam's real ids.
{
"manifestVersion": "2",
"name": "connecteam-example",
"steps": [
{
"id": "clock-in",
"uses": {
"app": "io.w6w.connecteam",
"action": "clock-in",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"timeClockId": "<timeClockId>",
"userId": "<userId>"
}
}
]
}clock-in account-get clock-out form-get form-list +22 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Connecteam, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Connecteam. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "clock-in",
payload: {
timeClockId: "<value>",
userId: "<value>",
// jobId: "<value>",
// timezone: "<value>",
// schedulerShiftId: "<value>",
// timestamp: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action clock-in --payload '{"timeClockId":"<value>","userId":"<value>"}' Give an AI agent Connecteam — without giving it Connecteam's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.connecteam#clock-in",
"input": {
"timeClockId": "<timeClockId>",
"userId": "<userId>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Connecteam connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Connecteam's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Connecteam itself is MIT, and the runtime that executes it is source-available (FSL).
Connecteam declares its own checks, so its health is a property of the app rather than something the host guesses at.
Component status from connecteam.statuspage.io: Platform, Job Scheduler, Time Clock, Task Management, Forms, Chat and the rest of Connecteam's own status page.