Toggl Track for AI agents
Toggl Track is a time tracking platform for recording work, managing projects, and producing reports, used by teams that need clear records of billable hours. 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 Toggl Track.
Start and stop a time entry
Log time against a task and stop the timer when the work is done.
Run a detailed time report
Pull a report of logged hours across a workspace for a given period, a read-only summary.
Confirm before deleting a project
Check with the user before deleting a project, since its logged time entries reference it.
21 Toggl Track actions, graded by risk.
Every Toggl Track action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- toggl_track.get_time_entryGet Time Entry
- toggl_track.list_workspacesList Workspaces
- toggl_track.get_current_userGet Current User
- toggl_track.list_time_entriesList Time Entries
- toggl_track.get_current_time_entryGet Current Time Entry
- toggl_track.list_workspace_resourcesList Workspace Resources
write
11Create and change things. Allow, or ask the user first.
- toggl_track.create_taskCreate Task
- toggl_track.update_taskUpdate Task
- toggl_track.create_clientCreate Client
- toggl_track.update_clientUpdate Client
- toggl_track.create_projectCreate Project
- toggl_track.update_projectUpdate Project
- toggl_track.create_time_entryCreate Time Entry
- toggl_track.update_time_entryUpdate Time Entry
- toggl_track.stop_time_entryStop Time Entry
- toggl_track.bulk_update_time_entriesBulk Update Time Entries
- toggl_track.run_detailed_time_reportRun Detailed Time Report
destructive
4Delete, cancel or archive. Ask first, or deny outright.
- toggl_track.delete_taskDelete Task
- toggl_track.delete_clientDelete Client
- toggl_track.delete_projectDelete Project
- toggl_track.delete_time_entryDelete Time Entry
Toggl Track in three steps.
- 01Your users connect Toggl TrackThey add their Toggl Track api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Task” can wait for the user, and “delete Task” can be denied outright.
- 03Any agent can actYour agent calls Toggl Track through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('toggl_track', { read: 'allow', write: 'ask', // create_task destructive: 'deny', // delete_task }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Toggl Track connects.
Users add their Toggl Track 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 Toggl Track 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 Toggl Track from any agent.
Toggl Track and Arc0, answered.
Can I use Toggl Track with Claude, ChatGPT or Cursor?
Yes. Connect Toggl Track 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 Toggl Track actions you allow.
How do users connect Toggl Track?
Users add their Toggl Track 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 Toggl Track actions can my agent take?
21 in total: 6 read, 11 write and 4 destructive, such as “create Task”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Toggl Track?
Yes. Actions like “delete Task” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Toggl Track too?
Yes. The same Toggl Track connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Toggl Track into your agent.
Your users connect Toggl Track once, under your brand. Your agent gets 21 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan