[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Connecteam API and MCP server

> Connecteam has a REST API with read and write endpoints, but only on the Expert plan or higher, and its official MCP server only looks up API endpoints and cannot act on your account (checked 20 Oct 2026). Basic and Advanced plans get no API. No endpoint approves a timesheet or copies last week's schedule.

Workforce app for frontline teams: a time clock with timesheets, a job scheduler for shifts, time off, Quick Tasks, forms and chat, sold as three hubs.

## What is the Connecteam API?

Cotlet's Connecteam API exposes 14 endpoints for your own Connecteam account: list users, list time clocks, list timesheets, get a timesheet, list schedules, list shifts, list time off requests, list tasks, approve a timesheet, copy the previous week, publish shifts, approve or decline time off, create a task and send a chat message. The list_users endpoint returns employees and admins of your Connecteam account with their user IDs. Each endpoint takes simple JSON inputs like cursor, user_id or status and works both as an operation of the connecteam_read or connecteam_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Productivity & teams](https://cotlet.dev/integrations/category/productivity-teams.md)
- **Endpoints:** 14 (8 read, 6 write)
- **Updated:** 2026-10-22

Connecteam has a REST API with read and write endpoints, but only on the Expert plan or higher, and its official MCP server only looks up API endpoints and cannot act on your account (checked 20 Oct 2026). Cotlet is a hosted MCP server and REST API for Connecteam with 14 endpoints (8 read, 6 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Connecteam have an official API?

Connecteam has a REST API with read and write endpoints, but only on the Expert plan or higher, and its official MCP server only looks up API endpoints and cannot act on your account (checked 20 Oct 2026). Basic and Advanced plans get no API. No endpoint approves a timesheet or copies last week's schedule.

| Task | Connecteam official | Cotlet |
|---|---|---|
| Read timesheet totals and time activities | Partly: Time Clock endpoints, Expert plan or higher | Yes |
| Approve or reopen a timesheet | No: Webhooks report approvals, no endpoint makes one | Yes |
| Create and update shifts | Partly: Scheduler endpoints, Expert plan or higher | Yes |
| Copy last week's schedule | No | Yes |
| List, create and update time off requests | Partly: Time Off endpoints, Expert plan or higher and the HR & Skills hub | Yes |
| Create and update tasks | Partly: Task endpoints, Expert plan or higher | Yes |
| Send chat messages | Partly: Chat endpoints, Expert plan or higher and the Communications hub | Yes |
| Any of the above on a Basic or Advanced plan | No: API access starts at the Expert plan | Yes |

Sources: [Connecteam Developer: API access](https://developer.connecteam.com/docs/api-access), [Connecteam Developer: MCP](https://developer.connecteam.com/docs/mcp), [Connecteam Developer: Rate limiting](https://developer.connecteam.com/docs/rate-limiting-1), [Connecteam pricing](https://connecteam.com/pricing/)

## For AI agents

```text
Connecteam has a REST API with read and write endpoints, but only on the Expert plan or higher, and its official MCP server only looks up API endpoints and cannot act on your account (checked 20 Oct 2026). Basic and Advanced plans get no API. No endpoint approves a timesheet or copies last week's schedule.
Cotlet provides a hosted MCP server and REST API for Connecteam: 14 tools (8 read, 6 write).
Access       Sign up at https://cotlet.dev/app/signup?app=connecteam, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    connecteam_read, connecteam_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/connecteam, each operation at its own route, e.g. POST /api/v1/connecteam/time-clocks/{time_clock_id}/timesheet/approve
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_users, list_time_clocks, list_timesheets, get_timesheet, list_schedulers, list_shifts, list_time_off_requests, list_tasks, approve_timesheet, copy_previous_week, publish_shifts, decide_time_off_request, create_task, send_message
Confirm      approve_timesheet, copy_previous_week, publish_shifts, decide_time_off_request, create_task, send_message (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/connecteam-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=connecteam, requests Connecteam in the Cotlet console and creates an API key there.
2. The user signs in to Connecteam once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Connecteam for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Connecteam server that someone else maintains, including non-developers.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Connecteam in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Connecteam only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Connecteam login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Connecteam's terms; Cotlet is not affiliated with Connecteam.
```

## What can an AI agent do in Connecteam?

Cotlet is best for Connecteam admins and managers on Basic or Advanced plans who want their AI agent to approve timesheets, publish schedules and answer time off requests without running or fixing a server.

- **[Approve submitted timesheets](https://cotlet.dev/integrations/connecteam-api-mcp-server/approve-submitted-timesheets.md)** (runs: weekly): "Go through the submitted timesheets of the Main Floor time clock for last week. Approve every timesheet with no day over 9 hours, and leave the rest for me with the day that broke the rule." → `list_time_clocks`, `list_timesheets`, `get_timesheet`, `approve_timesheet`
- **[Copy last week's schedule and publish it](https://cotlet.dev/integrations/connecteam-api-mcp-server/copy-last-weeks-schedule.md)** (runs: weekly): "Copy last week's Front of House schedule to the week of Oct 19 as drafts. If no shift clashes with approved time off, publish them. Otherwise tell me which shifts clash and publish nothing." → `list_schedulers`, `list_shifts`, `copy_previous_week`, `list_time_off_requests`, `publish_shifts`
- **[Approve or decline time off requests](https://cotlet.dev/integrations/connecteam-api-mcp-server/approve-time-off-requests.md)** (runs: daily): "Go through pending time off requests. Approve requests of up to 3 days that start at least 14 days from now and do not overlap an approved request. Leave the rest for me with the reason." → `list_time_off_requests`, `decide_time_off_request`
- **Create and assign tasks**: "Create a Quick Task "Restock the walk-in cooler" for Marco Bell and Ana Lopez, due this Friday, as a separate task for each of them." → `list_users`, `create_task`
- **Chase missing timesheets** (runs: weekly): "Every Tuesday, message each employee in the Main Floor time clock who has not submitted last week's timesheet, and tell me whom you messaged." → `list_timesheets`, `send_message`

## Can Connecteam automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Connecteam connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to approve submitted timesheets, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/connecteam/time-clocks. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/connecteam/time-clocks with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 14 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Connecteam.

### list_users

Employees and admins of your Connecteam account with their user IDs. Access: read. REST: `GET /api/v1/connecteam/users`. MCP: `connecteam_read → list_users`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `status` | enum | no | active (default) or archived. |
| `name` | string | no | Only users whose name contains this text. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns the users of your account, one row each, with user_id, name and role. Use user_id in the other tools. status active is the default; archived shows archived users. Pass next_cursor back as cursor for the next page.

Example response:

```json
{
  "users": [
    {
      "user_id": 8821034,
      "name": "Dana Whitfield",
      "role": "user"
    },
    {
      "user_id": 8821051,
      "name": "Luis Ortega",
      "role": "user"
    },
    {
      "user_id": 8821077,
      "name": "Priya Nair",
      "role": "user"
    }
  ],
  "next_cursor": null
}
```

### list_time_clocks

Time clocks of your account and whether Timesheets approval is on for each. Access: read. REST: `GET /api/v1/connecteam/time-clocks`. MCP: `connecteam_read → list_time_clocks`.

No parameters.

Returns every time clock you can open under Time Clock in the left sidebar. timesheets_approval is the switch under Settings > Payroll; it is set for each time clock, so approve_timesheet works only where it is on. Use time_clock_id in the timesheet tools.

Example response:

```json
{
  "time_clocks": [
    {
      "time_clock_id": 2041,
      "name": "Main Floor",
      "timesheets_approval": true
    },
    {
      "time_clock_id": 2058,
      "name": "Kitchen",
      "timesheets_approval": false
    }
  ]
}
```

### list_timesheets

Timesheets of a pay period with each employee's submission and approval state and total hours. Access: read. REST: `GET /api/v1/connecteam/time-clocks/{time_clock_id}/timesheets`. MCP: `connecteam_read → list_timesheets`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `time_clock_id` | integer | yes | Time clock ID from list_time_clocks. |
| `period_start` | date | yes | First day of the pay period, YYYY-MM-DD. |
| `period_end` | date | yes | Last day of the pay period, YYYY-MM-DD. |
| `status` | enum | no | all (default), submitted, not_submitted or approved. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns one row per employee for the dates you pass, as the Timesheets tab shows them: submission is submitted or not_submitted (the User Submission column), approval is approved or not_approved, and total_hours is the sum for the period. Filter with status. Pass next_cursor back as cursor for the next page. Approving works for a pay period, so pass its first and last day.

Example response:

```json
{
  "time_clock_id": 2041,
  "period_start": "2026-10-12",
  "period_end": "2026-10-18",
  "timesheets": [
    {
      "user_id": 8821034,
      "name": "Dana Whitfield",
      "submission": "submitted",
      "approval": "not_approved",
      "total_hours": 38.5
    },
    {
      "user_id": 8821051,
      "name": "Luis Ortega",
      "submission": "submitted",
      "approval": "not_approved",
      "total_hours": 41
    },
    {
      "user_id": 8821077,
      "name": "Priya Nair",
      "submission": "not_submitted",
      "approval": "not_approved",
      "total_hours": 36.25
    }
  ],
  "next_cursor": null
}
```

### get_timesheet

One employee's timesheet day by day, with clock in, clock out, hours and locked days. Access: read. REST: `GET /api/v1/connecteam/time-clocks/{time_clock_id}/timesheet`. MCP: `connecteam_read → get_timesheet`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `time_clock_id` | integer | yes | Time clock ID from list_time_clocks. |
| `user_id` | integer | yes | User ID from list_users or list_timesheets. |
| `period_start` | date | yes | First day of the pay period, YYYY-MM-DD. |
| `period_end` | date | yes | Last day of the pay period, YYYY-MM-DD. |

Returns the days of one employee in the dates you pass, in date order, each with its time entries (clock_in, clock_out), the hours for the day and whether the day is locked. total_hours is the sum of the days. Read it before approve_timesheet to judge the hours.

Example response:

```json
{
  "user_id": 8821051,
  "name": "Luis Ortega",
  "period_start": "2026-10-12",
  "period_end": "2026-10-18",
  "days": [
    {
      "date": "2026-10-12",
      "entries": [
        {
          "clock_in": "08:00",
          "clock_out": "16:00"
        }
      ],
      "hours": 8,
      "locked": false
    },
    {
      "date": "2026-10-13",
      "entries": [
        {
          "clock_in": "08:00",
          "clock_out": "16:30"
        }
      ],
      "hours": 8.5,
      "locked": false
    },
    {
      "date": "2026-10-14",
      "entries": [
        {
          "clock_in": "07:30",
          "clock_out": "17:00"
        }
      ],
      "hours": 9.5,
      "locked": false
    },
    {
      "date": "2026-10-15",
      "entries": [
        {
          "clock_in": "08:00",
          "clock_out": "16:00"
        }
      ],
      "hours": 8,
      "locked": false
    },
    {
      "date": "2026-10-16",
      "entries": [
        {
          "clock_in": "09:00",
          "clock_out": "16:00"
        }
      ],
      "hours": 7,
      "locked": false
    }
  ],
  "total_hours": 41
}
```

### list_schedulers

The schedules of your Job Scheduler with their IDs and names. Access: read. REST: `GET /api/v1/connecteam/schedulers`. MCP: `connecteam_read → list_schedulers`.

No parameters.

Returns every schedule you can open under the scheduler in the left sidebar. Use scheduler_id in list_shifts, copy_previous_week and publish_shifts.

Example response:

```json
{
  "schedulers": [
    {
      "scheduler_id": 1177,
      "name": "Front of House"
    },
    {
      "scheduler_id": 1203,
      "name": "Back of House"
    }
  ]
}
```

### list_shifts

Shifts of one schedule in a date range, drafts and published, with their assigned users. Access: read. REST: `GET /api/v1/connecteam/schedulers/{scheduler_id}/shifts`. MCP: `connecteam_read → list_shifts`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `scheduler_id` | integer | yes | Schedule ID from list_schedulers. |
| `start_date` | date | yes | First day, YYYY-MM-DD. |
| `end_date` | date | yes | Last day, YYYY-MM-DD. |
| `published` | boolean | no | true for published shifts only, false for drafts only. Default: both. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns the shifts of one schedule between the two dates, in start order, each with title, start and end, assigned user names and published (false for a draft). Drafts are invisible to employees until published. Pass next_cursor back as cursor for the next page.

Example response:

```json
{
  "shifts": [
    {
      "shift_id": 90412,
      "title": "Opening",
      "start": "2026-10-19T07:00",
      "end": "2026-10-19T15:00",
      "users": [
        "Dana Whitfield"
      ],
      "published": false
    },
    {
      "shift_id": 90413,
      "title": "Closing",
      "start": "2026-10-19T15:00",
      "end": "2026-10-19T23:00",
      "users": [
        "Marco Bell"
      ],
      "published": false
    }
  ],
  "next_cursor": "2"
}
```

### list_time_off_requests

Time off requests with employee, policy type, dates and status, pending first. Access: read. REST: `GET /api/v1/connecteam/time-off-requests`. MCP: `connecteam_read → list_time_off_requests`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `status` | enum | no | pending (default), approved or declined. |
| `start_date` | date | no | Only requests that end on or after this date. |
| `end_date` | date | no | Only requests that start on or before this date. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns the requests of the users your account can act on: users you manage directly or whose smart group you administer. status pending is the Pending Requests window, approved and declined show past decisions. Each row has request_id, employee, policy type, dates and days. Pass next_cursor back as cursor for the next page.

Example response:

```json
{
  "requests": [
    {
      "request_id": "5528",
      "user_id": 8821077,
      "name": "Priya Nair",
      "policy_type": "Vacation",
      "start_date": "2026-10-22",
      "end_date": "2026-10-23",
      "days": 2,
      "status": "pending"
    },
    {
      "request_id": "5531",
      "user_id": 8821090,
      "name": "Marco Bell",
      "policy_type": "Vacation",
      "start_date": "2026-12-14",
      "end_date": "2026-12-23",
      "days": 8,
      "status": "pending"
    }
  ],
  "next_cursor": null
}
```

### list_tasks

Quick Tasks with title, assignees, due date and whether they are done. Access: read. REST: `GET /api/v1/connecteam/tasks`. MCP: `connecteam_read → list_tasks`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `user_id` | integer | no | Only tasks assigned to this user. |
| `status` | enum | no | open (default) or done. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns the Quick Tasks you can see, newest first, each with task_id, title, assignees, due_date and status. Filter by assignee or status. Pass next_cursor back as cursor for the next page.

Example response:

```json
{
  "tasks": [
    {
      "task_id": 70331,
      "title": "Restock the walk-in cooler",
      "assignees": [
        "Marco Bell"
      ],
      "due_date": "2026-10-23",
      "status": "open"
    }
  ],
  "next_cursor": null
}
```

### approve_timesheet

Approve one employee's submitted timesheet for a pay period. Your account needs approve permission. Access: write, asks the user first. REST: `POST /api/v1/connecteam/time-clocks/{time_clock_id}/timesheet/approve`. MCP: `connecteam_write → approve_timesheet`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `time_clock_id` | integer | yes | Time clock ID from list_time_clocks. |
| `user_id` | integer | yes | User ID from list_users or list_timesheets. |
| `period_start` | date | yes | First day of the pay period, YYYY-MM-DD. |
| `period_end` | date | yes | Last day of the pay period, YYYY-MM-DD. |

Approves the timesheet like the Approve button in the upper right of the employee's timesheet. It works only on a time clock with Timesheets approval on, for a pay period, and with an admin account that may approve; otherwise it fails with APP_PERMISSION_DENIED. Once approved, only an admin with reopen permission can change the timesheet, and Connecteam notifies the employee right away. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "approved": true,
  "time_clock_id": 2041,
  "user_id": 8821034,
  "name": "Dana Whitfield",
  "period_start": "2026-10-12",
  "period_end": "2026-10-18",
  "total_hours": 38.5
}
```

### copy_previous_week

Copy every shift of the previous week into the week you name, as drafts, or only one employee's shifts. Access: write, asks the user first. REST: `POST /api/v1/connecteam/schedulers/{scheduler_id}/previous-week/copy`. MCP: `connecteam_write → copy_previous_week`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `scheduler_id` | integer | yes | Schedule ID from list_schedulers. |
| `week_start` | date | yes | First day of the week to fill, YYYY-MM-DD. |
| `user_id` | integer | no | Copy only this employee's shifts. |

Runs copy previous week of the Job Scheduler for the week that starts on week_start. Copied shifts are drafts: employees do not see them until publish_shifts runs. Pass user_id to copy one employee's shifts only. Connecteam does not say how existing shifts in the target week are treated, so read the week with list_shifts first. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "scheduler_id": 1177,
  "week_start": "2026-10-19",
  "copied": 14,
  "published": false
}
```

### publish_shifts

Publish the draft shifts of a schedule so employees see them. All drafts, or only the shift ids you pass. Access: write, asks the user first. REST: `POST /api/v1/connecteam/schedulers/{scheduler_id}/shifts/publish`. MCP: `connecteam_write → publish_shifts`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `scheduler_id` | integer | yes | Schedule ID from list_schedulers. |
| `shift_ids` | array | no | Shift IDs from list_shifts. Default: all drafts of the schedule. |

Publishes drafts, which makes them visible to the assigned users. Without shift_ids it publishes every draft of the schedule, like the Publish button at the top right; with shift_ids it publishes only those, which is a bulk action of the Advanced plan in the Operations hub. A shift needs a title or a job, and assigned users or claiming turned on, to be published. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "scheduler_id": 1177,
  "published": 14
}
```

### decide_time_off_request

Approve or decline one pending time off request. Your account must be allowed to act on that employee. Access: write, asks the user first. REST: `POST /api/v1/connecteam/requests/{request_id}/time-off-request/decide`. MCP: `connecteam_write → decide_time_off_request`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `request_id` | string | yes | Request ID from list_time_off_requests. |
| `decision` | enum | yes | approve or decline. |

Approves or declines the request like the buttons in the Pending Requests window. An approved request lands on the employee's timesheet automatically, and the employee sees the new status in the mobile app. You can only act on users you manage directly or whose smart group you administer; otherwise it fails with APP_PERMISSION_DENIED. A decision can be changed later in the History tab of the request. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "request_id": "5528",
  "status": "approved",
  "name": "Priya Nair",
  "policy_type": "Vacation",
  "start_date": "2026-10-22",
  "end_date": "2026-10-23",
  "days": 2
}
```

### create_task

Create and publish a Quick Task for one or more users, with a title, optional description and due date. Access: write, asks the user first. REST: `POST /api/v1/connecteam/tasks`. MCP: `connecteam_write → create_task`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `title` | string | yes | Task title. |
| `assignee_ids` | array | yes | User IDs from list_users. |
| `description` | string | no | More detail for the assignees. |
| `due_date` | date | no | Due date, YYYY-MM-DD. |
| `separate_tasks` | boolean | no | true creates one task for each assignee. Default: false, one task for the team. |

Creates a single Quick Task like Add Task > Single Task > Publish Task. Connecteam requires a title and an assignee. With several assignees the task is done by them together as a team; set separate_tasks to create one task for each user instead. Assignees can read everything in the task, and it appears in their Quick Tasks. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "tasks": [
    {
      "task_id": 70331,
      "title": "Restock the walk-in cooler",
      "assignees": [
        "Marco Bell"
      ],
      "due_date": "2026-10-23",
      "status": "open"
    },
    {
      "task_id": 70332,
      "title": "Restock the walk-in cooler",
      "assignees": [
        "Ana Lopez"
      ],
      "due_date": "2026-10-23",
      "status": "open"
    }
  ]
}
```

### send_message

Send a private message to one user in Connecteam Chat. Access: write, asks the user first. REST: `POST /api/v1/connecteam/users/{user_id}/messages`. MCP: `connecteam_write → send_message`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `user_id` | integer | yes | User ID from list_users or list_timesheets. |
| `text` | string | yes | Message text. |

Sends the text to the user in a private conversation, the same message you start from the Chat icon next to the approval progress bar. The employee gets it in the Connecteam app. The message is text only, and it cannot be recalled by this tool. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "sent": true,
  "user_id": 8821077,
  "name": "Priya Nair"
}
```

## How do I connect Connecteam to Claude Code, Codex or Cursor?

Connecting Connecteam takes three steps: sign up, sign in to Connecteam once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect Connecteam to your agent.

1. **Create an account** Sign up and add Connecteam in the console. Your API key is there too.

2. **Sign in to Connecteam in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Connecteam there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   Claude Code:

```
claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"
```

   Cursor:

```
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

   Codex:

```
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

4. **Ask your agent** Ask in plain words. Your agent finds the Connecteam tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

```
Go through the submitted timesheets of the Main Floor time clock for last week. Approve every timesheet with no day over 9 hours, and leave the rest for me with the day that broke the rule.
```

### Call Connecteam from your scripts.

1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

```
export COTLET_API_KEY="cotlet_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/connecteam with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.

```
curl -X POST https://cotlet.dev/api/v1/connecteam/time-clocks/2041/timesheet/approve \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"user_id":8821034,"period_start":"2026-10-12","period_end":"2026-10-18"}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "approved": true,
  "time_clock_id": 2041,
  "user_id": 8821034,
  "name": "Dana Whitfield",
  "period_start": "2026-10-12",
  "period_end": "2026-10-18",
  "total_hours": 38.5
}
```

## Why use Cotlet for Connecteam?

**Built for agents**

- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to Connecteam yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.

**Kept working for you**

- We test every integration every 6 hours.
- When Connecteam changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Connecteam to Cotlet?

Yes. You sign in to Connecteam yourself, in your own Cloud Browser, and we never save your password. Your agents only get Connecteam once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

- **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### Common concerns

**Who runs Cotlet?**

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

**Is this an official Connecteam integration?**

No, Cotlet is independent of Connecteam. Connecteam's own API is too limited for this work. Cotlet works through your own Connecteam account, the way you use Connecteam in the browser, so you need no partner approval and no developer setup.

**What about client data and GDPR?**

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

**Can I start with read only?**

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

**Is it reliable?**

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

**How do I stop?**

Press Disable for agents next to Connecteam in your console: your agents lose access at once and you stay signed in. Signing out of Connecteam in the browser works too, and Reset browser deletes the whole profile.

## Is there a Connecteam MCP server on GitHub?

Connecteam has its own REST API on the Expert plan or higher, and Zapier and hosted wrappers build on it. You upgrade, get the key, map the endpoints and live with the gaps. Cotlet works in your own Connecteam login on the plan you have, hosted, and our team keeps it working.

|  | Connecteam API | Cotlet |
|---|---|---|
| Setup | Move to the Expert plan, get the API key from Connecteam, build the calls or wire a Zap | Sign up, sign in to Connecteam once, add one MCP server or API key |
| Plan needed | Expert or higher; Basic and Advanced have no API | The plan you already have; a tool needs that feature in your plan |
| What it can do | The endpoints Connecteam publishes: no timesheet approval, no copy of last week | The same steps you click in the dashboard, such as approving a timesheet or copying a week |
| Your access | An API key or OAuth client secret in your scripts and tools | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| Upkeep | You host, monitor and update your calls when endpoints change | Nothing to host or update; our team tests it daily and fixes it for you |
| Where it runs | Wherever you run your code, or inside Zapier | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | The plan upgrade plus your build time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |

### Which one fits you

**Pick Cotlet if**

- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Connecteam changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off

**Pick an open-source server if**

- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the Connecteam API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Connecteam API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

| Credits | Price, one time | Calls at 25 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 200 | $5.80 |
| 15,000 | $79 | 600 | $5.27 |
| 32,000 | $149 | 1,280 | $4.66 |
| 60,000 | $249 | 2,400 | $4.15 |

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Connecteam account.

- **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to Connecteam yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Connecteam only after you enable it. When Connecteam signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to Connecteam, sign out of Connecteam in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA.
- **Connecteam's terms:** You use your own Connecteam account and stay responsible for following Connecteam's terms. Cotlet is independent and not affiliated with Connecteam. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open Connecteam in the console and press Request access. Then you create your API key and connect Connecteam there.

**Do I need to be technical?**

No. You sign in to Connecteam once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

**Is it safe to connect Connecteam to Cotlet?**

Yes. You sign in to Connecteam yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Connecteam once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

**Is a hosted server safer than a local one? My Connecteam sign-in would leave my computer.**

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Connecteam cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

**Why does Cotlet send requests instead of clicking in my browser?**

To be fast, Cotlet doesn't click through Connecteam's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Connecteam sees the same browser and IP you signed in with, and every request is listed in your Background activity.

**What if someone gets my Cotlet API key?**

The key holds no Connecteam login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

**Why a signed-in browser and not OAuth, like other integration platforms?**

Connecteam offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

**Do I need the Expert plan or an API key?**

No. Cotlet works in your own Connecteam dashboard login, so it does not use the API, which starts at the Expert plan. Your admin permissions still count: approving a timesheet needs an admin chosen in the time clock's Payroll settings, and acting on time off needs a user you manage or whose smart group you administer. A call without the permission fails with APP_PERMISSION_DENIED.

**Which tools need which Connecteam hub?**

A tool works where your account has the feature. Time clock, schedules and Quick Tasks belong to the Operations hub, time off to HR & Skills and chat to Communications. Publishing only some drafts is a bulk action of the Advanced plan, and time off approval needs the HR Basic plan or higher.

**Can my agent post or send messages in Connecteam without asking me?**

No. Every call to approve_timesheet, copy_previous_week, publish_shifts, decide_time_off_request, create_task or send_message waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals.

**Can I use the Connecteam API in n8n?**

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/connecteam from the HTTP Request node.

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.

## For AI agents: sign your user up

Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed.

1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests
2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them.
3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests.

One call creates the account and sends the access request; we email the user when access is granted.