Workhr
JhrvisPricing
Help

Help and documentation

Last updated: 22 August 2026

How to get help with Workhr, and how the Claude connector works — what it can read, whose permissions it uses, and how to switch it off.

Getting help

Every screen in Workhr has a Help button in the bottom right. It opens the article for the page you are on, and it can start a conversation with our team without you losing your place.

If you would rather email: support@workhr.co.nz. For anything security-related, see workhr.app/security — please report vulnerabilities there rather than through general support.

Connecting Claude (the MCP connector)

Workhr publishes a remote Model Context Protocol server, so you can ask Claude questions about your own workspace — “which credentials expire in the next fortnight”, “what was our margin at East Tamaki last week” — and get answers from your live data rather than a guess.

Turning it on. In Workhr, go to Settings → Integrations → Claude / MCP and switch the connector on. It is off until an administrator turns it on, and any administrator can turn it back off.

Connecting. Workhr is listed in Claude's Connectors Directory: in Claude, open Settings → Connectors, find Workhr and choose Connect. Claude sends you back to Workhr to sign in and approve the connection. The same server can also be added as a custom connector using the URL shown on the Workhr integration page.

What the connector can and cannot do

It reads. It never writes. Every tool is a query, and the database transaction is switched read-only before the query runs — so nothing can be written even if a query tries.

It uses your access, not the workspace’s. Approving the connection grants Claude what you can see. Queries run as you, through your own row-level security. A consultant and a client-portal supervisor asking the identical question get different answers, and neither can reach another organisation’s data — that boundary is enforced by the database, not by the connector.

Some things are never readable, whatever your role allows: bank accounts, IRD numbers and tax codes; integration credentials, API tokens and OAuth state; calendar connections; and anything in the authentication, storage or vault schemas.

Every call is logged. The audit log records what was asked and how many rows came back — never the rows themselves — including calls that were refused.

Switching it off is immediate. Permission is re-checked on every single request, so turning the connector off stops it on the next call rather than whenever a token happens to expire.

The tools it exposes

All seven are read-only, and none of them accepts an organisation as a parameter.

  • Search candidates — find people by name, email or role title.
  • Get assignment detail — one assignment with its worker, site, client, job order, rates and recent shifts.
  • List expiring credentials — tickets and licences expiring within a window, with the person they belong to.
  • Weekly margin by client — pay, charge and margin per client company for a given week.
  • Financial forecast — where this month and quarter land against target, as floor, likely and stretch with every part shown, for your own office unless you can see them all.
  • Describe the database schema — table and column names only, no rows.
  • Run a read-only SQL query — a single SELECT for questions the other tools do not cover. Results are capped, comments and multiple statements are rejected, and the same row-level security applies.

Authentication

The connector uses OAuth 2.0. Workhr publishes protected-resource metadata at /api/mcp-meta/prm naming its authorization server, which supports dynamic client registration, PKCE, and the authorization-code and refresh-token grants. You are never asked to paste an API key into Claude, and no long-lived shared secret exists to leak.

Privacy and terms

How we handle personal information is set out in our privacy policy, and the terms of use in our terms. Our security posture, including how to report a vulnerability, is at workhr.app/security.