# DeskTime — how to use (mcp.ai)

Connect your DeskTime account and use 11 tools for time tracking straight from your AI agent. Connect with your own API key. DeskTime is an automatic time tracking software that helps teams and freelancers monitor productivity, manage projects, and analyze work habits.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_desktime?ms=1787291220000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `desktime_create_project_with_task`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/desktime`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/desktime/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/desktime/create/project/with/task` — Tool to create a new project with an optional initial task. Use when you need to set up a new DeskTime project programmatically.
  - body: { task?: string, project: string }
- `POST https://api.mcp.ai/api/desktime/get/account/details` — Retrieves company account configuration including work schedule and timezone settings. This action fetches company-level information such as company name, work hours (start/end times), work duration, 
- `POST https://api.mcp.ai/api/desktime/get/all/company/employees` — Tool to list all employees in the company, including their roles and statuses. Use after confirming valid credentials to fetch the organization’s roster.
  - body: { date?: string, period?: string }
- `POST https://api.mcp.ai/api/desktime/get/employee` — Tool to retrieve information about a single employee including user info, work settings, and tracking data for a specific date. Use when you need detailed information for one employee. Returns data fo
  - body: { id?: string, date?: string }
- `POST https://api.mcp.ai/api/desktime/get/employee/apps` — Retrieves employee tracking data including tracked apps for a specific date. Returns data for the currently logged-in user if no employee ID is specified. Use this action to view detailed application 
  - body: { id?: string, date?: string }
- `POST https://api.mcp.ai/api/desktime/get/employee/projects` — Retrieves comprehensive employee project tracking data including project assignments, time tracking metrics, work hours, and productivity statistics for a specific employee and date. Returns detailed 
  - body: { id?: integer, date?: string }
- `POST https://api.mcp.ai/api/desktime/get/employee/projects/and/apps` — Retrieve an employee's basic information and daily tracking statistics from DeskTime. Returns employee profile data, work hours, productivity metrics, attendance status, and currently active project. 
  - body: { id?: integer, date?: string }
- `POST https://api.mcp.ai/api/desktime/get/projects/list` — Tool to retrieve all active projects for the company, including related tasks. Use when you need projects overview after authentication.
- `POST https://api.mcp.ai/api/desktime/ping/request` — Tool to check the API's availability and confirm the service is operational. Use when you need to verify that the DeskTime API is reachable and responsive.
- `POST https://api.mcp.ai/api/desktime/start/project/task` — Starts time tracking for a specified project and optional task in DeskTime. This action begins recording time against the specified project. If a task name is provided, time is also tracked at the tas
  - body: { task?: string, project: string }
- `POST https://api.mcp.ai/api/desktime/stop/project/task` — Tool to stop tracking time for a specified project and optional task. Use when you have finished work and need to record end time.
  - body: { task?: string, project: string }

## Example prompts
- "What can I do in DeskTime?"
- "Show me a summary of my DeskTime account"

## More
- Page: https://mcp.ai/desktime
- Agent spec (llms.txt): https://mcp.ai/desktime/llms.txt
- Postman collection: https://mcp.ai/desktime/postman.json