Timelink for AI agents

Timelink tracks employee work hours through software and hardware time clocks, used by employers who need accurate attendance records. 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.

HR and recruitingAPI keyMCP + RESTtimelink.pt
AUDIT LOG · TIMELINKPOLICY: acme-support
09:41:12 · claude · u_8f2destructive
timelink.delete_person
Delete Person✕ blocked · policy: deny
EVERY TIMELINK CALL, ON THE RECORD
01 · USE CASES

What agents do in Timelink.

01

Review a person's record before removal

Check a person's attendance history before removing them from the system.

02

Confirm before deleting a person

Get approval before deleting a person record, since it also removes their tracked time history.

03

Audit who was recently removed

Review recent deletions as a read-only check on data changes.

02 · ACTIONS

1 Timelink actions, graded by risk.

Every Timelink action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

0

Look things up. Allowed by default.

  • No read actions.

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • timelink.delete_person
    Delete Person
03 · HOW IT WORKS

Timelink in three steps.

  1. 01Your users connect TimelinkThey add their Timelink api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “updates” can wait for the user, and “delete Person” can be denied outright.
  3. 03Any agent can actYour agent calls Timelink through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('timelink', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  // delete_person
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Timelink connects.

Users add their Timelink 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 Timelink 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
05 · WORKS WITH

Use Timelink from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Timelink and Arc0, answered.

Q01

Can I use Timelink with Claude, ChatGPT or Cursor?

Yes. Connect Timelink 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 Timelink actions you allow.

Q02

How do users connect Timelink?

Users add their Timelink 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.

Q03

Which Timelink actions can my agent take?

1 in total: 0 read, 0 write and 1 destructive. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Timelink?

Yes. Actions like “delete Person” 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.

Q05

Can my own backend call Timelink too?

Yes. The same Timelink connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Timelink into your agent.

Your users connect Timelink once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan