# ClockShark API and MCP server

> ClockShark has no public developer API or API docs (checked 10 Oct 2026). Admins can only generate a Zapier API key, which Zapier uses for 6 triggers and 2 actions: Create Job and Create Task.

GPS time clock, scheduling and job costing for construction and field service crews, part of the Simpro Group.

## What is the ClockShark API?

Cotlet's ClockShark API exposes 15 endpoints for your own ClockShark account: list time entries, list who's clocked in, list shifts, list jobs, get job, list time off requests, export time CSV, add time entry, edit time entry, approve timesheets, create job, create shift, publish shifts, respond to time off request and add job comment. The list_time_entries endpoint returns shifts from Time > View: employee, job, task, start, end, breaks, notes, alerts and approval status. Each endpoint takes simple JSON inputs like from, to or employee_ids and works both as an MCP tool for agents and as a REST call for scripts.

- **Category:** [Local services & SaaS](https://cotlet.dev/integrations/category/local-services-saas)
- **Endpoints:** 15 (7 read, 8 write)
- **Updated:** 2026-10-10

ClockShark has no public developer API or API docs (checked 10 Oct 2026). Cotlet is a hosted MCP server and REST API for ClockShark with 15 endpoints (7 read, 8 write): your AI agent signs in as you and does the work.

## Does ClockShark have an official API?

ClockShark has no public developer API or API docs (checked 10 Oct 2026). Admins can only generate a Zapier API key, which Zapier uses for 6 triggers and 2 actions: Create Job and Create Task.

| Task | ClockShark official | Cotlet |
|---|---|---|
| Read time entries for a pay period | Partly: Zapier fires on new clock ins and outs, no history | Yes |
| Approve timesheets | No | Yes |
| Add or edit time entries | No | Yes |
| Create jobs | Yes: Zapier action Create Job | Yes |
| Build and publish schedules | No: Zapier only fires when a schedule is created | Yes |
| Approve or decline time off | No | Yes |
| Export payroll hours as CSV | Partly: Built-in pushes to QuickBooks, ADP, Gusto and others only | Yes |
| See who's clocked in now | Partly: Clock in and out triggers in Zapier | Yes |

Sources: [ClockShark: How to use the Zapier integration](https://help.clockshark.com/articles/#!help-guide/how-to-use-the-zapier-integration), [ClockShark integrations overview](https://help.clockshark.com/articles/#!help-guide/clockshark-integrations), [ClockShark on Zapier: triggers and actions](https://zapier.com/apps/clockshark/integrations), [ClockShark: How to use timesheet approvals](https://help.clockshark.com/how-to-use-timesheet-approvals), [ClockShark: Approve or decline requested time off](https://help.clockshark.com/how-to-approve-or-decline-requested-time-off)

## For AI agents

```text
ClockShark has no public developer API or API docs (checked 10 Oct 2026). Admins can only generate a Zapier API key, which Zapier uses for 6 triggers and 2 actions: Create Job and Create Task.
Cotlet provides a hosted MCP server and REST API for ClockShark: 15 tools (7 read, 8 write).
Access       Request access at https://cotlet.dev/app/signup?app=clockshark; we email the API key.

MCP server   https://cotlet.dev/mcp/v1
REST base    https://cotlet.dev/api/v1/clockshark
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one.
Tools        list_time_entries, list_clocked_in, list_shifts, list_jobs, get_job, list_time_off_requests, export_time_csv, add_time_entry, edit_time_entry, approve_timesheets, create_job, create_shift, publish_shifts, respond_time_off_request, add_job_comment
Confirm      publish_shifts, respond_time_off_request, add_job_comment (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/clockshark-api-mcp-server.md

How access works:
1. The user requests access at https://cotlet.dev/app/signup?app=clockshark (ClockShark is pre-selected). Each request is reviewed and the API key is sent by email.
2. The user signs in to ClockShark once in a browser. 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 ClockShark 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.
Session: the user signs in to ClockShark in a browser; Cotlet keeps only the session, AES-256 encrypted, revocable in the dashboard at any time.
Terms: the user stays responsible for following ClockShark's terms; Cotlet is not affiliated with ClockShark.
```

## What can an AI agent do in ClockShark?

Cotlet is best for contractors and field service managers who want their AI agent to approve timesheets, fix time, schedule crews and pull payroll hours without running or fixing a server.

- **[Approve weekly timesheets before payroll](https://cotlet.dev/integrations/clockshark-api-mcp-server/approve-weekly-timesheets)** (runs: weekly): "Approve last week's ClockShark timesheets for everyone without alerts, hold back the rest, and give me the CSV Export totals for payroll." → `list_time_entries`, `approve_timesheets`, `export_time_csv`
- **[Fix missed clock outs](https://cotlet.dev/integrations/clockshark-api-mcp-server/fix-missed-clock-outs)** (runs: daily): "Every morning, find yesterday's ClockShark shifts with a Missing Out alert, end them at the scheduled time and ask me about anyone with no schedule." → `list_time_entries`, `list_shifts`, `edit_time_entry`, `approve_timesheets`
- **Export payroll hours** (runs: weekly): "Download the payroll CSV for this pay period and tell me who has overtime." → `export_time_csv`
- **[Schedule crew shifts on a new job](https://cotlet.dev/integrations/clockshark-api-mcp-server/schedule-crew-shifts)** (runs: weekly): "Create a job for 42 Oak Street and put Ana and Luis on it Monday to Wednesday, 7:00 to 15:30. Check nobody is booked elsewhere and show me the drafts before you publish." → `list_jobs`, `create_job`, `list_shifts`, `list_time_off_requests`, `create_shift`, `publish_shifts`
- **[Approve time off requests](https://cotlet.dev/integrations/clockshark-api-mcp-server/approve-time-off-requests)** (runs: daily): "Approve every pending ClockShark time off request that does not take someone off a scheduled shift, and ask me about the rest." → `list_time_off_requests`, `list_shifts`, `respond_time_off_request`
- **See who is clocked in**: "Who is clocked in right now, and on which jobs?" → `list_clocked_in`

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

Yes. Cotlet does not replace your automation platform: it gives it a ClockShark 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 weekly timesheets before payroll, 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 to https://cotlet.dev/api/v1/clockshark/{tool}. | Schedule Trigger node. |
| Make | HTTP module: POST https://cotlet.dev/api/v1/clockshark/{tool} with an Authorization: Bearer header and a JSON body. | Scenario schedule. |
| Zapier | Webhooks by Zapier: POST https://cotlet.dev/api/v1/clockshark/{tool} with the same header and body. | Schedule by Zapier trigger. |
| Your own script | POST https://cotlet.dev/api/v1/clockshark/{tool} with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 15 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 403 until the account has an API key with access to ClockShark.

### list_time_entries

Shifts from Time > View: employee, job, task, start, end, breaks, notes, alerts and approval status. Access: read. REST: `POST /api/v1/clockshark/list_time_entries`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `from` | date | yes | First day of the range. |
| `to` | date | yes | Last day of the range. |
| `employee_ids` | string[] | no | Only these employees. Default: everyone you manage. |
| `approval_status` | enum | no | all, approved or unapproved. Default: all. |
| `with_alerts_only` | boolean | no | Only shifts with timesheet alerts, such as a missing clock out. |

Returns shifts for a date range, oldest first, with the alerts ClockShark raised on each, such as a missing clock out. Filter by employee, by approval status or to shifts with alerts only. Use entry_id and employee_id from here in the edit and approve tools.

Example response:

```json
{
  "entries": [
    {
      "entry_id": "te_90412",
      "employee_id": "e_48213",
      "employee": "Mike Torres",
      "job": "42 Oak Street",
      "task": "Framing",
      "start": "2026-10-09T07:00:00-05:00",
      "end": null,
      "break_minutes": 30,
      "alerts": [
        "Missing clock out"
      ],
      "approved": false
    },
    {
      "entry_id": "te_90420",
      "employee_id": "e_48219",
      "employee": "Luis Ortega",
      "job": "42 Oak Street",
      "task": "Framing",
      "start": "2026-10-09T07:02:00-05:00",
      "end": "2026-10-09T15:31:00-05:00",
      "break_minutes": 30,
      "alerts": [],
      "approved": false
    }
  ]
}
```

### list_clocked_in

Employees on an active shift now, with job, task and the GPS location of their last punch. Access: read. REST: `POST /api/v1/clockshark/list_clocked_in`.

No parameters.

Returns employees with an open shift at the moment of the call. Each item has the job, the task, the clock in time and the location of the last punch. An employee with no open shift is not listed.

Example response:

```json
{
  "clocked_in": [
    {
      "employee_id": "e_48219",
      "employee": "Luis Ortega",
      "job": "42 Oak Street",
      "task": "Framing",
      "since": "2026-10-11T07:02:00-05:00",
      "last_punch": {
        "lat": 41.8781,
        "lng": -87.6298
      }
    }
  ]
}
```

### list_shifts

Scheduled shifts, published and draft, with employee, job, task, times and notes. Access: read. REST: `POST /api/v1/clockshark/list_shifts`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `from` | date | yes | First day of the range. |
| `to` | date | yes | Last day of the range. |
| `employee_ids` | string[] | no | Only these employees. Default: everyone you manage. |
| `status` | enum | no | all, published or draft. Default: all. |

Returns scheduled shifts for a date range, earliest first. Status shows whether crews can already see a shift in the mobile app (published) or not yet (draft). Use shift_id with publish_shifts.

Example response:

```json
{
  "shifts": [
    {
      "shift_id": "s_77120",
      "employee_id": "e_48213",
      "job_id": "j_3307",
      "start": "2026-10-12T07:00:00-05:00",
      "end": "2026-10-12T15:30:00-05:00",
      "status": "published",
      "notes": ""
    }
  ]
}
```

### list_jobs

Jobs from Work > Jobs with number, stage, customer and address. Access: read. REST: `POST /api/v1/clockshark/list_jobs`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `active` | boolean | no | Only active jobs. Default: true. |
| `customer` | string | no | Only jobs of this customer. |
| `search` | string | no | Match on job name or number. |

Returns jobs your account can see. By default only active jobs are listed. Use job_id from here in time, schedule and comment tools.

Example response:

```json
{
  "jobs": [
    {
      "job_id": "j_3307",
      "number": "2041",
      "name": "42 Oak Street",
      "stage": "Active",
      "customer": "Harlow Homes",
      "address": "42 Oak Street, Springfield"
    }
  ]
}
```

### get_job

Job details: description, address, customer, stage, labor budget, comments and attachment list. Access: read. REST: `POST /api/v1/clockshark/get_job`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `job_id` | string | yes | Job ID from list_jobs. |

Returns one job with its labor budget, the comment thread and the names of attached files. Attachments are listed, not downloaded.

Example response:

```json
{
  "job_id": "j_3307",
  "number": "2041",
  "name": "42 Oak Street",
  "stage": "Active",
  "customer": "Harlow Homes",
  "address": "42 Oak Street, Springfield",
  "description": "Wall framing, level 1.",
  "budget_hours": 320,
  "comments": [
    {
      "author": "Dana Reed",
      "body": "Lumber arrives Monday 6:30.",
      "created_at": "2026-10-08T16:10:00-05:00"
    }
  ],
  "attachments": [
    "floor-plan.pdf"
  ]
}
```

### list_time_off_requests

Requests from Time > Requests with employee, policy, dates, hours and status. Pro plan. Access: read. REST: `POST /api/v1/clockshark/list_time_off_requests`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `status` | enum | no | pending, approved, declined or all. Default: pending. |

Returns time off requests, pending ones by default, newest first. Each has the policy, the dates and the hours requested. Time off requests are a Pro plan feature, so the call fails on other plans.

Example response:

```json
{
  "requests": [
    {
      "request_id": "r_20871",
      "employee_id": "e_48219",
      "employee": "Luis Ortega",
      "policy": "Vacation",
      "from": "2026-10-19",
      "to": "2026-10-20",
      "hours": 16,
      "status": "pending"
    }
  ]
}
```

### export_time_csv

The CSV Export report: paid, regular, overtime and double time minutes per shift, as a download link. Access: read. REST: `POST /api/v1/clockshark/export_time_csv`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `from` | date | yes | First day of the range. |
| `to` | date | yes | Last day of the range. |
| `employee_ids` | string[] | no | Only these employees. Default: everyone you manage. |
| `include_notes` | boolean | no | Add timesheet notes. Default: false. |

Returns a download link to the CSV Export report for the range, plus the row count and totals in minutes, so your agent can answer without opening the file. Notes are left out unless include_notes is true. It reads the report and changes nothing.

Example response:

```json
{
  "download_url": "https://app.clockshark.com/exports/csv/2026-10-05_2026-10-11.csv",
  "rows": 3,
  "totals": {
    "paid_minutes": 1530,
    "regular_minutes": 1440,
    "overtime_minutes": 90,
    "double_time_minutes": 0
  }
}
```

### add_time_entry

Manually add a shift to an employee timesheet, the way a manager does on the web. Access: write. REST: `POST /api/v1/clockshark/add_time_entry`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `employee_id` | string | yes | Employee ID from list_time_entries. |
| `job_id` | string | yes | Job ID from list_jobs. |
| `task_id` | string | yes | Task to log the time against. |
| `start` | datetime | yes | ISO 8601 with time zone. |
| `end` | datetime | yes | ISO 8601 with time zone. |
| `notes` | string | no | Timesheet note. |

Adds a shift for one employee against a job and a task, with start and end as ISO 8601 times with a time zone. It reaches no one and a wrong entry is fixed with edit_time_entry, so it runs without asking. The new entry is unapproved.

Example response:

```json
{
  "entry_id": "te_90433",
  "employee_id": "e_48213",
  "job_id": "j_3307",
  "start": "2026-10-09T07:00:00-05:00",
  "end": "2026-10-09T15:30:00-05:00",
  "approved": false
}
```

### edit_time_entry

Change start, end, job, task or notes of an unapproved shift. Saved to the audit log. Access: write. REST: `POST /api/v1/clockshark/edit_time_entry`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `entry_id` | string | yes | Entry ID from list_time_entries. |
| `fields` | object | yes | Any of start, end, job_id, task_id, notes. |
| `ignore_alerts` | boolean | no | Mark the shift alerts as ignored. |

Changes the fields you pass and leaves the rest. It works on unapproved shifts only, so unapprove the timesheet first if needed. Each edit is saved to the audit log. It reaches no one and is undone by editing again, so it runs without asking.

Example response:

```json
{
  "entry_id": "te_90412",
  "start": "2026-10-09T07:00:00-05:00",
  "end": "2026-10-09T16:30:00-05:00",
  "alerts": [],
  "approved": false
}
```

### approve_timesheets

Approve, or unapprove, employee timesheets for a day, week or pay period. Needs timesheet approvals turned on. Access: write. REST: `POST /api/v1/clockshark/approve_timesheets`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `employee_ids` | string[] | yes | Employees whose timesheets to approve. |
| `from` | date | yes | First day of the range. |
| `to` | date | yes | Last day of the range. |
| `action` | enum | no | approve or unapprove. Default: approve. |

Approves every shift of the listed employees in the range and returns paid and overtime hours per employee. Timesheet approvals must be turned on in your account. It reaches no one and action unapprove reverses it, so it runs without asking.

Example response:

```json
{
  "approved": 2,
  "period": {
    "from": "2026-10-05",
    "to": "2026-10-11"
  },
  "timesheets": [
    {
      "employee_id": "e_48213",
      "paid_hours": 41.5,
      "overtime_hours": 1.5,
      "status": "approved"
    },
    {
      "employee_id": "e_48219",
      "paid_hours": 38,
      "overtime_hours": 0,
      "status": "approved"
    }
  ]
}
```

### create_job

New job employees can clock into, with customer, address and description. Access: write. REST: `POST /api/v1/clockshark/create_job`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `name` | string | yes | Job name. |
| `number` | string | no | Job number. |
| `customer` | string | no | Existing customer name or ID. |
| `address` | string | no | Job site address. |
| `description` | string | no | Shown to field employees in the mobile app. |
| `budget_hours` | integer | no | Total hours budgeted for the labor budget. |

Creates a job with an optional number, customer, address and description, and a labor budget in hours. The description shows to field employees in the mobile app. It reaches no one by itself and runs without asking.

Example response:

```json
{
  "job_id": "j_3307",
  "number": "2041",
  "name": "42 Oak Street",
  "stage": "Active",
  "budget_hours": 320
}
```

### create_shift

Schedule one or more employees on a job, saved as a draft until you publish it. Access: write. REST: `POST /api/v1/clockshark/create_shift`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `employee_ids` | string[] | yes | Employees to schedule. |
| `job_id` | string | yes | Job ID from list_jobs. |
| `start` | datetime | yes | ISO 8601 with time zone. |
| `end` | datetime | yes | ISO 8601 with time zone. |
| `task_id` | string | no | Task for the shift. |
| `notes` | string | no | Shift notes for the crew. |

Creates one shift per employee on a job with start and end as ISO 8601 times. Shifts are saved as drafts, so crews see nothing until publish_shifts. It runs without asking for that reason.

Example response:

```json
{
  "shifts": [
    {
      "shift_id": "s_77201",
      "employee_id": "e_48213",
      "job_id": "j_3307",
      "start": "2026-10-12T07:00:00-05:00",
      "end": "2026-10-12T15:30:00-05:00",
      "status": "draft"
    },
    {
      "shift_id": "s_77202",
      "employee_id": "e_48219",
      "job_id": "j_3307",
      "start": "2026-10-12T07:00:00-05:00",
      "end": "2026-10-12T15:30:00-05:00",
      "status": "draft"
    }
  ]
}
```

### publish_shifts

Publish draft shifts so they appear in employees' mobile app. Access: write, asks the user first. REST: `POST /api/v1/clockshark/publish_shifts`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `shift_ids` | string[] | no | Shifts to publish. Default: all drafts in the range. |
| `from` | date | no | First day of the range. |
| `to` | date | no | Last day of the range. |

Publishes the shifts you name, or all drafts in a date range, and returns how many went out. Employees see published shifts in their mobile app. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "published": 2,
  "shift_ids": [
    "s_77201",
    "s_77202"
  ]
}
```

### respond_time_off_request

Approve or decline a request. ClockShark emails the employee; a decline cannot be undone. Access: write, asks the user first. REST: `POST /api/v1/clockshark/respond_time_off_request`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `request_id` | string | yes | Request ID from list_time_off_requests. |
| `decision` | enum | yes | approve or decline. |
| `note` | string | no | Reason, shown with a decline. |

Approves or declines one pending request. ClockShark emails the employee, and a note is shown with a decline. A decline cannot be undone. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "request_id": "r_20871",
  "employee": "Luis Ortega",
  "decision": "approve",
  "status": "approved"
}
```

### add_job_comment

Comment on a job thread; @mentioned users get a notification. Access: write, asks the user first. REST: `POST /api/v1/clockshark/add_job_comment`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `job_id` | string | yes | Job ID from list_jobs. |
| `body` | string | yes | Comment text. Mention users as @Name. |

Posts a comment on the job thread under your name. Users you @mention get a notification. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "comment_id": "c_5521",
  "job_id": "j_3307",
  "body": "@Dana Reed lumber is confirmed for Monday 6:30.",
  "created_at": "2026-10-09T16:12:00-05:00"
}
```

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

Connecting ClockShark takes three steps: request access, sign in to ClockShark once, then add one MCP server or call the REST API with the same key.

### Connect ClockShark to your agent.

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

2. **Sign in to ClockShark once** Open the connect page from the console and sign in to ClockShark the way you always do. We keep the session, never your password, and you can revoke it anytime.

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 ClockShark 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.

```
Approve last week's ClockShark timesheets for everyone without alerts, hold back the rest, and give me the CSV Export totals for payroll.
```

### Call ClockShark 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 a POST endpoint at /api/v1/clockshark/{tool}. Send its parameters as JSON, exactly as listed in the endpoints above.

```
curl https://cotlet.dev/api/v1/clockshark/approve_timesheets \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"employee_ids":["e_48213","e_48219"],"from":"2026-10-05","to":"2026-10-11","action":"approve"}'
```

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

```
{
  "approved": 2,
  "period": {
    "from": "2026-10-05",
    "to": "2026-10-11"
  },
  "timesheets": [
    {
      "employee_id": "e_48213",
      "paid_hours": 41.5,
      "overtime_hours": 1.5,
      "status": "approved"
    },
    {
      "employee_id": "e_48219",
      "paid_hours": 38,
      "overtime_hours": 0,
      "status": "approved"
    }
  ]
}
```

## Why use Cotlet for ClockShark?

**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 ClockShark yourself. We keep only the session, encrypted with AES-256.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Pick read only, or read and write.
- Anything that reaches other people waits for your OK, unless you switch it off per tool.
- Revoke access in one click.

**Kept working for you**

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

## Is there a ClockShark MCP server on GitHub?

Zapier is the one official route: it reacts to clock ins, new jobs and new schedules, and can create jobs and tasks. It cannot approve, edit, schedule or answer time off. Cotlet does those, and works next to Zapier, n8n and Make.

|  | Zapier | Cotlet |
|---|---|---|
| Setup | Generate a Zapier API key in ClockShark, connect it in Zapier, build a Zap per job | Request access, sign in to ClockShark once, add one MCP server or API key |
| What it can do | 6 triggers (clock in, clock out, new job, notification, new schedule, new task) and 2 actions (create job, create task) | Also approve timesheets, edit time, build and publish schedules, answer time off, export payroll hours |
| Reading history | Fires on new events only | Reads any date range, on demand |
| When ClockShark changes | Maintained by Zapier and ClockShark | Our team tests it daily and fixes it for you; failed calls are free |
| Your ClockShark session | An API key you can revoke | Encrypted in an EU vault, limited to the actions you allow, revoked in one click |
| When the session expires | Not applicable, the key stays valid until revoked | If ClockShark logs you out, your agent gets a link to sign in again |
| Price | Zapier plan, per task | Free 7-day trial with 5,000 credits, then credits per call |

### 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 ClockShark 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 the session to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the ClockShark API cost?

Free 7-day trial with 5,000 credits, no card needed. After that, the ClockShark API comes with the Cotlet plan, from $29 a month for 3,000 credits, with no limit on apps. Each month's credits stay valid for 3 months, so unused credits add up.

| Size | Price | Credits / month | Per credit |
|---|---|---|---|
| Solo | $29/mo | 3,000 | about $0.0097 |
| Pro | $99/mo | 12,000 | about $0.0083 |
| Agency | $299/mo | 40,000 | $0.0075 |

Each successful call uses credits for the work it takes; failed calls and timeouts cost nothing. A hard spend cap is on by default. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing)

## How Cotlet holds your access

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

- **Company details:** The legal name, address and registration numbers of the company behind Cotlet are in the Terms of service. [Terms](https://cotlet.dev/terms)
- **Your session:** You sign in to ClockShark yourself, in your browser. We keep only the session, never your password: encrypted with AES-256 in an EU vault, isolated to your account and used only when your agent calls a ClockShark tool you allowed. When it expires, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security)
- **Revoking access:** Disconnect ClockShark in your dashboard: the session is deleted and access ends at once. 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.
- **ClockShark's terms:** You use your own ClockShark account and stay responsible for following ClockShark's terms. Cotlet is independent and not affiliated with ClockShark. [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?**

Request access and pick ClockShark. Cotlet reviews each request and emails you your API key.

**Do I need to be technical?**

No. You sign in to ClockShark once in your browser 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 a hosted server safe? My ClockShark session would leave my computer.**

Cotlet keeps your ClockShark session encrypted with AES-256 in an EU vault, isolated to your account and used only for the tools you allow: read only, or read and write. The AI model never sees it, and you revoke it in one click. A local server keeps the same session in a file on your computer, readable by any program you run, and needs a fresh sign-in whenever it expires.

**Do I need Zapier or a special ClockShark plan?**

No. Cotlet works in your own ClockShark admin or manager account and does not use the Zapier API key. Time off requests are a Pro plan feature in ClockShark, and approving timesheets needs timesheet approvals turned on.

**Can it change a timesheet that is already approved?**

Not directly. edit_time_entry works on unapproved shifts, so your agent first calls approve_timesheets with action unapprove for that range, edits the shift, then approves again.

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

No. Every call to publish_shifts, respond_time_off_request or add_job_comment waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_time_entry, edit_time_entry, approve_timesheets, create_job, create_shift runs without asking, because it sends nothing to anyone and one call undoes it.

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

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call https://cotlet.dev/api/v1/clockshark/{tool} from the HTTP Request node.