[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)

# Hubstaff API and MCP server

> Hubstaff has a full REST API, API v2, with read and write scopes, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server reads organizations, members, projects, tasks and time and activity data for owners and managers, cannot create or change anything, and is switched on per organization after an email to Hubstaff support. The API covers approvals, time entries, projects and tasks, but you create and renew the token or OAuth app yourself.

Time tracking and workforce management: a desktop timer with activity levels and screenshots, timesheets with approvals, projects and tasks, time off, schedules and payroll.

## What is the Hubstaff API?

Cotlet's Hubstaff API exposes 15 endpoints for your own Hubstaff account: list organizations, list members, list projects, list tasks, list timesheets, list manual time requests, list time off requests, get daily activity, approve timesheet, deny timesheet, approve or deny manual time request, add time entry, create project, create task and assign project member. The list_organizations endpoint returns organizations you belong to, with ID, name and your role in each. Each endpoint takes simple JSON inputs like organization_id, cursor or limit and works both as an operation of the hubstaff_read or hubstaff_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Productivity & teams](https://cotlet.dev/integrations/category/productivity-teams.md)
- **Endpoints:** 15 (8 read, 7 write)
- **Updated:** 2026-10-20

Hubstaff has a full REST API, API v2, with read and write scopes, and an official MCP server that is read-only (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Hubstaff with 15 endpoints (8 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Hubstaff have an official API?

Hubstaff has a full REST API, API v2, with read and write scopes, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server reads organizations, members, projects, tasks and time and activity data for owners and managers, cannot create or change anything, and is switched on per organization after an email to Hubstaff support. The API covers approvals, time entries, projects and tasks, but you create and renew the token or OAuth app yourself.

| Task | Hubstaff official | Cotlet |
|---|---|---|
| List timesheets and their status | Yes: API v2 timesheets endpoint; the official MCP server is read-only | Yes |
| Approve or deny a timesheet | Yes: API v2, with two confirmation flags when manual time or time off is still pending; no MCP server tool | Yes |
| Approve or deny manual time requests | Yes: API v2, one request at a time; batch approve and deny are not in the API | Yes |
| Add a manual time entry | Partly: API v2 adds entries, but not those that need approval | Yes |
| Create a project and its tasks | Yes: API v2; a project linked to a third-party tool takes its tasks from that tool | Yes |
| Add or change project members | Yes: API v2 with roles viewer, user and manager | Yes |
| Read daily activity by member, project or task | Yes: API v2 and the read-only MCP server; 31 days per call | Yes |
| List time off requests | Yes: API v2; managers see all, others only their own | Yes |

Sources: [Hubstaff Support: Hubstaff MCP Server](https://support.hubstaff.com/hubstaff-mcp-server/), [Hubstaff developers: Authentication](https://developer.hubstaff.com/authentication/), [Hubstaff developers: Manual time requests](https://developer.hubstaff.com/manual-time-requests/), [Hubstaff developers: Timesheets](https://developer.hubstaff.com/reference/timesheets/)

## For AI agents

```text
Hubstaff has a full REST API, API v2, with read and write scopes, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server reads organizations, members, projects, tasks and time and activity data for owners and managers, cannot create or change anything, and is switched on per organization after an email to Hubstaff support. The API covers approvals, time entries, projects and tasks, but you create and renew the token or OAuth app yourself.
Cotlet provides a hosted MCP server and REST API for Hubstaff: 15 tools (8 read, 7 write).
Access       Sign up at https://cotlet.dev/app/signup?app=hubstaff, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    hubstaff_read, hubstaff_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/hubstaff, each operation at its own route, e.g. POST /api/v1/hubstaff/requests/{request_id}/manual-time-request/review
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_organizations, list_members, list_projects, list_tasks, list_timesheets, list_manual_time_requests, list_time_off_requests, get_daily_activity, approve_timesheet, deny_timesheet, review_manual_time_request, add_time_entry, create_project, create_task, assign_project_member
Confirm      approve_timesheet, deny_timesheet, review_manual_time_request, add_time_entry, create_task, assign_project_member (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/hubstaff-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=hubstaff, requests Hubstaff in the Cotlet console and creates an API key there.
2. The user signs in to Hubstaff once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Hubstaff 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 Hubstaff server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Hubstaff MCP server instead.

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 Hubstaff 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 Hubstaff 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 Hubstaff 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 Hubstaff's terms; Cotlet is not affiliated with Hubstaff.
```

## What can an AI agent do in Hubstaff?

Cotlet is best for Hubstaff owners and managers who want their AI agent to approve timesheets and manual time, add missed time and set up projects without running or fixing a server.

- **[Approve timesheets at the end of a pay period](https://cotlet.dev/integrations/hubstaff-api-mcp-server/approve-timesheets.md)** (runs: weekly): "It is the first day after the pay period. Go through the Hubstaff timesheets that are submitted. Approve the ones with no pending manual time or time off and with activity above 40 percent, and deny any with a clear problem and a reason. List the rest for me." → `list_timesheets`, `list_manual_time_requests`, `get_daily_activity`, `approve_timesheet`, `deny_timesheet`
- **[Clear the manual time approval queue](https://cotlet.dev/integrations/hubstaff-api-mcp-server/approve-manual-time-requests.md)** (runs: daily): "Go through the Hubstaff manual time requests that are waiting for approval. Approve the ones inside the member's scheduled hours with a real reason, deny the rest with a one-line reason, and leave anything over 4 hours for me." → `list_manual_time_requests`, `review_manual_time_request`
- **[Set up a new project with tasks and a team](https://cotlet.dev/integrations/hubstaff-api-mcp-server/set-up-a-project.md)**: "Create the Hubstaff project "Website relaunch", billable, with Maria Silva and Tom Becker as users and Dana Whitfield as manager. Add these four tasks and assign them as listed: homepage design to Maria, checkout flow to Tom, content migration to Maria, launch checklist to Dana." → `list_members`, `create_project`, `create_task`, `assign_project_member`
- **Send a weekly hours summary by project** (runs: weekly): "Every Monday, pull last week's Hubstaff daily activity for all active projects and send me total tracked hours per project and per member, with anyone under 50 percent activity listed separately." → `list_projects`, `get_daily_activity`
- **Add time a member forgot to track**: "Add 1 hour 30 minutes to Maria Silva on the Support rota project for yesterday at 14:00 with the note "Client call, timer was off". Ask me before you save it." → `list_projects`, `list_members`, `add_time_entry`
- **Check time off before payroll** (runs: weekly): "List the Hubstaff time off requests that start this week or next, grouped by member, and tell me which ones are still not approved." → `list_time_off_requests`, `list_members`

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

Yes. Cotlet does not replace your automation platform: it gives it a Hubstaff 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 timesheets at the end of a pay period, 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/hubstaff/organizations/{organization_id}/timesheets. | 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/hubstaff/organizations/{organization_id}/timesheets 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 401 without an API key and 403 while the key has no access to Hubstaff.

### list_organizations

Organizations you belong to, with ID, name and your role in each. Access: read. REST: `GET /api/v1/hubstaff/organizations`. MCP: `hubstaff_read → list_organizations`.

No parameters.

Returns every Hubstaff organization your account belongs to, with your role in it. Run it first: the other tools take an organization ID. What your agent can do in an organization follows your role there.

Example response:

```json
{
  "organizations": [
    {
      "organization_id": 412093,
      "name": "Northwind Studio",
      "role": "owner"
    }
  ]
}
```

### list_members

Members of an organization with user ID, name, email and role. Access: read. REST: `GET /api/v1/hubstaff/organizations/{organization_id}/members`. MCP: `hubstaff_read → list_members`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `limit` | integer | no | 1 to 100. Default: 50. |
| `cursor` | string | no | Next page cursor from the previous call. |

Lists the members of one organization with their user ID and role, as on People > Members. Use the user IDs in the tools that add time or put someone on a project.

Example response:

```json
{
  "members": [
    {
      "user_id": 3011,
      "name": "Maria Silva",
      "email": "maria@example.com",
      "role": "user"
    },
    {
      "user_id": 3012,
      "name": "Tom Becker",
      "email": "tom@example.com",
      "role": "user"
    },
    {
      "user_id": 3014,
      "name": "Dana Whitfield",
      "email": "dana@example.com",
      "role": "manager"
    }
  ],
  "next_cursor": null
}
```

### list_projects

Projects in an organization with status, billable default and client. Access: read. REST: `GET /api/v1/hubstaff/organizations/{organization_id}/projects`. MCP: `hubstaff_read → list_projects`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `status` | string | no | active, archived or all. Default: active. |
| `limit` | integer | no | 1 to 100. Default: 50. |
| `cursor` | string | no | Next page cursor from the previous call. |

Lists projects with their ID, name, status and whether new time is billable by default. Filter by status to leave out archived projects. Use the project IDs when you add time, create tasks or change members.

Example response:

```json
{
  "projects": [
    {
      "project_id": 90311,
      "name": "Support rota",
      "status": "active",
      "billable": true,
      "client_id": null
    },
    {
      "project_id": 90355,
      "name": "Brand refresh",
      "status": "active",
      "billable": true,
      "client_id": 7712
    }
  ],
  "next_cursor": null
}
```

### list_tasks

Tasks in a project with status, assignees and due date. Access: read. REST: `GET /api/v1/hubstaff/projects/{project_id}/tasks`. MCP: `hubstaff_read → list_tasks`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `project_id` | integer | yes | Project ID from list_projects. |
| `status` | string | no | active or completed. Default: both. |
| `limit` | integer | no | 1 to 100. Default: 50. |
| `cursor` | string | no | Next page cursor from the previous call. |

Lists the tasks of one project with summary, status and the members assigned to each. Filter by status to see what is still open.

Example response:

```json
{
  "tasks": [
    {
      "task_id": 551020,
      "summary": "Homepage design",
      "status": "active",
      "assignee_ids": [
        3011
      ],
      "due_at": null
    },
    {
      "task_id": 551021,
      "summary": "Checkout flow",
      "status": "completed",
      "assignee_ids": [
        3012
      ],
      "due_at": null
    }
  ],
  "next_cursor": null
}
```

### list_timesheets

Timesheets for a pay period with member, status, tracked time and activity levels. Access: read. REST: `GET /api/v1/hubstaff/organizations/{organization_id}/timesheets`. MCP: `hubstaff_read → list_timesheets`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `status` | string | no | open, submitted, approved or denied. |
| `start_date` | date | no | First day of the range, ISO 8601. |
| `stop_date` | date | no | Last day of the range, ISO 8601, inclusive. |
| `limit` | integer | no | 1 to 100. Default: 50. |
| `cursor` | string | no | Next page cursor from the previous call. |

Lists timesheets, the approval records Hubstaff builds from each member's pay period, not single time entries. Filter by status (open, submitted, approved or denied) and by dates. Tracked time is in seconds; keyboard, mouse and overall are percentages.

Example response:

```json
{
  "timesheets": [
    {
      "timesheet_id": 8841201,
      "user_id": 3011,
      "status": "submitted",
      "start_date": "2026-10-06",
      "stop_date": "2026-10-12",
      "tracked": 144000,
      "overall": 58,
      "submitted_on": "2026-10-13"
    },
    {
      "timesheet_id": 8841202,
      "user_id": 3012,
      "status": "submitted",
      "start_date": "2026-10-06",
      "stop_date": "2026-10-12",
      "tracked": 136800,
      "overall": 49,
      "submitted_on": "2026-10-13"
    }
  ],
  "next_cursor": null
}
```

### list_manual_time_requests

Manual time requests with member, project, times, reason and status. Access: read. REST: `GET /api/v1/hubstaff/organizations/{organization_id}/manual-time-requests`. MCP: `hubstaff_read → list_manual_time_requests`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `status` | string | no | submitted, approved or denied. |
| `start_date` | date | no | Needs stop_date too. |
| `stop_date` | date | no | Needs start_date too. |
| `limit` | integer | no | 1 to 100. Default: 50. |
| `cursor` | string | no | Next page cursor from the previous call. |

Lists the manual time requests members submit when your organization requires approval for added time. Use status submitted for the review queue. Give start_date and stop_date together: Hubstaff matches requests whose time range overlaps those days in the organization time zone.

Example response:

```json
{
  "manual_time_requests": [
    {
      "request_id": 5530117,
      "user_id": 3011,
      "project_id": 90311,
      "start_time": "2026-10-14T14:00:00Z",
      "stop_time": "2026-10-14T15:30:00Z",
      "reason": "Client call, timer was off",
      "status": "submitted"
    },
    {
      "request_id": 5530121,
      "user_id": 3012,
      "project_id": 90355,
      "start_time": "2026-10-15T09:00:00Z",
      "stop_time": "2026-10-15T14:00:00Z",
      "reason": "Offline workshop",
      "status": "submitted"
    }
  ],
  "next_cursor": null
}
```

### list_time_off_requests

Time off requests with member, policy, dates and status. Access: read. REST: `GET /api/v1/hubstaff/organizations/{organization_id}/time-off-requests`. MCP: `hubstaff_read → list_time_off_requests`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `user_ids` | integer[] | no | Only requests from these members. |
| `starts_after` | datetime | no | Only requests that start after this time. |
| `starts_before` | datetime | no | Only requests that start before this time. |
| `cursor` | string | no | Next page cursor from the previous call. |

Lists time off requests in an organization, filtered by when they start or by member. Owners and managers see all requests; other roles see only their own and those of teams they lead with time off approval. Use it before approving a timesheet, because pending time off in the same period matters.

Example response:

```json
{
  "time_off_requests": [
    {
      "request_id": 77120,
      "user_id": 3012,
      "policy": "Vacation",
      "starts_at": "2026-10-19T00:00:00",
      "stops_at": "2026-10-21T23:59:59",
      "all_day": true,
      "status": "submitted"
    }
  ],
  "next_cursor": null
}
```

### get_daily_activity

Tracked time and activity levels per day, member, project and task. Access: read. REST: `GET /api/v1/hubstaff/organizations/{organization_id}/daily-activity`. MCP: `hubstaff_read → get_daily_activity`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `start_date` | date | yes | First day, ISO 8601. |
| `stop_date` | date | yes | Last day, ISO 8601, inclusive. At most 31 days after start_date. |
| `user_ids` | integer[] | no | Only these members. |
| `project_ids` | integer[] | no | Only these projects. |
| `task_ids` | integer[] | no | Only these tasks. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns data aggregated by day in the organization time zone: tracked seconds, with keyboard, mouse and overall activity. Filter by members, projects or tasks. The range is at most 31 days and starts no earlier than 3 years ago; ask for longer periods in several calls.

Example response:

```json
{
  "daily_activities": [
    {
      "date": "2026-10-12",
      "user_id": 3011,
      "project_id": 90311,
      "task_id": 551020,
      "tracked": 25200,
      "overall": 61
    },
    {
      "date": "2026-10-12",
      "user_id": 3012,
      "project_id": 90355,
      "task_id": 551021,
      "tracked": 21600,
      "overall": 47
    }
  ],
  "next_cursor": null
}
```

### approve_timesheet

Approve a submitted timesheet so its hours count for payroll. Access: write, asks the user first. REST: `POST /api/v1/hubstaff/timesheets/{timesheet_id}/approve`. MCP: `hubstaff_write → approve_timesheet`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `timesheet_id` | integer | yes | Timesheet ID from list_timesheets. |
| `confirm_pending_manual_time_request_denial` | boolean | no | true to approve although pending manual time requests will be denied. Default: false. |
| `acknowledge_pending_time_off_requests` | boolean | no | true to approve although time off requests are pending in the period. Default: false. |

Approves one timesheet. When the period still has pending manual time requests, Hubstaff would deny them; set confirm_pending_manual_time_request_denial only if you want that. Pending time off requests in the period need acknowledge_pending_time_off_requests. Approving before the pay period ends stops the member from tracking more time in it. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "timesheet_id": 8841201,
  "user_id": 3011,
  "status": "approved",
  "tracked": 144000,
  "approved_on": "2026-10-13"
}
```

### deny_timesheet

Deny a timesheet with a reason so the member can fix it. Access: write, asks the user first. REST: `POST /api/v1/hubstaff/timesheets/{timesheet_id}/deny`. MCP: `hubstaff_write → deny_timesheet`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `timesheet_id` | integer | yes | Timesheet ID from list_timesheets. |
| `denial_reason` | string | yes | Why the timesheet is denied. |

Denies one timesheet and records your reason. Use it to reopen a timesheet that was approved too early, too. A reason is required. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "timesheet_id": 8841202,
  "user_id": 3012,
  "status": "denied",
  "denial_reason": "Overlaps a manual entry for 12 Oct, please resubmit"
}
```

### review_manual_time_request

Approve or deny one manual time request that is waiting for review. Access: write, asks the user first. REST: `POST /api/v1/hubstaff/requests/{request_id}/manual-time-request/review`. MCP: `hubstaff_write → review_manual_time_request`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `request_id` | integer | yes | Request ID from list_manual_time_requests. |
| `decision` | string | yes | approve or deny. |
| `denial_reason` | string | no | Required when decision is deny. |

Approves or denies one submitted request. Approving adds activity for the full requested range, subject to limits, collisions, budgets and timesheets; if Hubstaff warns about one of them, the call returns the warning and changes nothing. Denying needs a reason. Requests that are no longer submitted cannot be changed. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "request_id": 5530117,
  "status": "approved",
  "user_id": 3011,
  "project_id": 90311,
  "tracked": 5400
}
```

### add_time_entry

Add manual time to a member on a project. Access: write, asks the user first. REST: `POST /api/v1/hubstaff/users/{user_id}/time-entries`. MCP: `hubstaff_write → add_time_entry`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `user_id` | integer | yes | Member ID from list_members. |
| `project_id` | integer | yes | Project ID from list_projects. |
| `start_time` | datetime | yes | Start of the entry, ISO 8601. |
| `tracked` | integer | yes | Seconds tracked. |
| `task_id` | integer | no | Task ID from list_tasks. |
| `billable` | boolean | no | Default: the project setting. |
| `note` | string | no | Reason for the entry. Required unless your organization made it optional. |

Adds a manual time entry for a member: project, start time and seconds tracked, with an optional task. Hubstaff requires a note by default and records manual time with 0 percent activity. If your organization requires approval for added time, the entry cannot be added this way and the call says so. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "success": true,
  "user_id": 3011,
  "project_id": 90311,
  "start_time": "2026-10-14T14:00:00Z",
  "tracked": 5400
}
```

### create_project

Create a project with a billable default and its members. Access: write. REST: `POST /api/v1/hubstaff/organizations/{organization_id}/projects`. MCP: `hubstaff_write → create_project`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `organization_id` | integer | yes | Organization ID from list_organizations. |
| `name` | string | yes | Project name. |
| `description` | string | no | Project description. |
| `billable` | boolean | no | Whether time is billable by default. Default: true. |
| `client_id` | integer | no | Client to link; clients need a Teams or Enterprise plan. |
| `members` | object[] | no | List of { user_id, role }, role is viewer, user or manager. |

Creates a project and returns it. Only the name is required; add a description, a client, a billable default and members with roles viewer, user or manager in the same call. It reaches no one outside the members you list, and you can archive the project in Hubstaff in one click, so it does not ask for confirmation by default.

Example response:

```json
{
  "project_id": 90417,
  "name": "Website relaunch",
  "status": "active",
  "billable": true,
  "members": [
    {
      "user_id": 3011,
      "role": "user"
    },
    {
      "user_id": 3014,
      "role": "manager"
    }
  ]
}
```

### create_task

Add a task to a project and assign it to members. Access: write, asks the user first. REST: `POST /api/v1/hubstaff/projects/{project_id}/tasks`. MCP: `hubstaff_write → create_task`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `project_id` | integer | yes | Project ID from list_projects. |
| `summary` | string | yes | Task summary. |
| `assignee_ids` | integer[] | no | Member IDs from list_members. |

Creates a task with a summary in a project and assigns it to one or more members. A project linked to a third-party tool takes tasks from that tool, so the call fails there and says so. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "task_id": 551030,
  "project_id": 90417,
  "summary": "Homepage design",
  "status": "active",
  "assignee_ids": [
    3011
  ]
}
```

### assign_project_member

Add a member to a project or change their role on it. Access: write, asks the user first. REST: `POST /api/v1/hubstaff/users/{user_id}/projects/{project_id}/member/assign`. MCP: `hubstaff_write → assign_project_member`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `project_id` | integer | yes | Project ID from list_projects. |
| `user_id` | integer | yes | Member ID from list_members. |
| `role` | string | yes | viewer, user, manager or remove. |

Sets one member's role on a project: viewer, user, manager, or remove to take them off. A viewer cannot track time against the project. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "project_id": 90417,
  "user_id": 3012,
  "role": "user",
  "success": true
}
```

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

Connecting Hubstaff takes three steps: sign up, sign in to Hubstaff 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 Hubstaff to your agent.

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

2. **Sign in to Hubstaff in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Hubstaff 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 Hubstaff 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.

```
It is the first day after the pay period. Go through the Hubstaff timesheets that are submitted. Approve the ones with no pending manual time or time off and with activity above 40 percent, and deny any with a clear problem and a reason. List the rest for me.
```

### Call Hubstaff 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/hubstaff 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/hubstaff/requests/5530121/manual-time-request/review \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"decision":"deny","denial_reason":"Over 4 hours, please add a reason and resubmit"}'
```

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

```
{
  "request_id": 5530121,
  "status": "denied",
  "user_id": 3012,
  "project_id": 90355,
  "denial_reason": "Over 4 hours, please add a reason and resubmit"
}
```

## Why use Cotlet for Hubstaff?

**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 Hubstaff 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 Hubstaff changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Hubstaff to Cotlet?

Yes. You sign in to Hubstaff yourself, in your own Cloud Browser, and we never save your password. Your agents only get Hubstaff 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 Hubstaff integration?**

No, Cotlet is independent of Hubstaff. Hubstaff's own API is too limited for this work. Cotlet works through your own Hubstaff account, the way you use Hubstaff 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 Hubstaff in your console: your agents lose access at once and you stay signed in. Signing out of Hubstaff in the browser works too, and Reset browser deletes the whole profile.

## Is there a Hubstaff MCP server on GitHub?

Yes. Community Hubstaff MCP servers exist on GitHub, usually maintained by one person. You install one yourself, give it a Hubstaff token, and fix it when Hubstaff changes. Cotlet hosts the same kind of server for you, signs in as you, and our team keeps it working.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, create a personal access token or an OAuth app, store it, add the server to each MCP client | Sign up, sign in to Hubstaff once, add one MCP server or API key |
| When Hubstaff changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your Hubstaff access | A token in a file on your computer, readable by any program you run, acting as your user | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When access expires | Tools fail until you refresh or replace the token; a personal access token lapses after 90 days without a refresh | Your Cloud Browser keeps you signed in; if Hubstaff logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your 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 Hubstaff 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 Hubstaff API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Hubstaff 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 Hubstaff 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 Hubstaff 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 Hubstaff only after you enable it. When Hubstaff 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 Hubstaff, sign out of Hubstaff 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.
- **Hubstaff's terms:** You use your own Hubstaff account and stay responsible for following Hubstaff's terms. Cotlet is independent and not affiliated with Hubstaff. [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 Hubstaff in the console and press Request access. Then you create your API key and connect Hubstaff there.

**Do I need to be technical?**

No. You sign in to Hubstaff 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 Hubstaff to Cotlet?**

Yes. You sign in to Hubstaff yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Hubstaff 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 Hubstaff 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 Hubstaff 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 Hubstaff's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Hubstaff 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 Hubstaff 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?**

Hubstaff 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).

**Which Hubstaff role does my agent need?**

The role you sign in with. Approving timesheets and manual time needs an owner or manager, and manual time can also be reviewed by a project manager or a team lead with manual time approval for that member. Creating projects needs an owner, an organization manager or a team lead with the permission.

**Do I need Hubstaff's official MCP server or an API token?**

No. Cotlet works in your own Hubstaff account and needs neither. Hubstaff's official MCP server is read-only, switched on per organization on request, and the API needs a token or OAuth app on an organization with an active plan.

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

No. Every call to approve_timesheet, deny_timesheet, review_manual_time_request, add_time_entry, create_task or assign_project_member waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. create_project runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the Hubstaff 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/hubstaff 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.