DeskTime for AI agents
DeskTime automatically tracks time and productivity for teams and freelancers, giving managers visibility into projects and work habits without manual timesheets. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in DeskTime.
Check an employee's tracked time
Check an employee's basic time data before reviewing their productivity for the week.
Start a project task
Start tracking time against a specific project task assigned to an employee.
Look up a project's assigned employees
Look up an employee's assigned projects before reassigning any of their workload.
11 DeskTime actions, graded by risk.
Every DeskTime action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- desktime.get_employeeGet Employee
- desktime.get_employee_appsGet Employee Apps
- desktime.get_projects_listGet Projects List
- desktime.get_account_detailsGet Account Details
- desktime.get_employee_projectsGet Employee Projects
- desktime.get_all_company_employeesGet All Company Employees
- desktime.get_employee_projects_and_appsGet Employee Basic Data
- desktime.ping_requestPing DeskTime API
write
3Create and change things. Allow, or ask the user first.
- desktime.create_project_with_taskCreate Project with Optional Task
- desktime.stop_project_taskStop Project Task
- desktime.start_project_taskStart Project Task
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
DeskTime in three steps.
- 01Your users connect DeskTimeThey add their DeskTime api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Project with Optional Task” can wait for the user to approve.
- 03Any agent can actYour agent calls DeskTime through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('desktime', { read: 'allow', write: 'ask', // create_project_with_task destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How DeskTime connects.
Users add their DeskTime api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same DeskTime connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use DeskTime from any agent.
DeskTime and Arc0, answered.
Can I use DeskTime with Claude, ChatGPT or Cursor?
Yes. Connect DeskTime to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the DeskTime actions you allow.
How do users connect DeskTime?
Users add their DeskTime api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which DeskTime actions can my agent take?
11 in total: 8 read, 3 write and 0 destructive, such as “create Project with Optional Task”. Your policies decide which of them each agent may call.
Can I make my agent read-only in DeskTime?
Yes. Allow read actions and deny writes in the DeskTime policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call DeskTime too?
Yes. The same DeskTime connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug DeskTime into your agent.
Your users connect DeskTime once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan