Connect Justworks to Claude Code

Have Claude onboard hires and file PTO in Justworks. From the terminal, inside the sessions where you already work.

How do you connect Justworks to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Justworks, you add a Justworks MCP server: a small hosted service that exposes Justworks's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Justworks account. No API keys pasted into config files.

claude mcp add --transport http justworks https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Justworks once connected?

Full read-write Justworks access lets Claude kick off an onboarding for a new hire, record a time-off request, update direct-deposit or compensation details, and pull a payroll summary, all after you approve. The HR admin work that used to mean tab-switching happens where the employee record already lives.

Start an onboarding workflow for a new hire and pre-fill their details
File or approve a paid-time-off request for an employee
Update an employee's compensation or direct-deposit information
Add or update a dependent on someone's benefits enrollment
Pull a payroll run summary and flag entries that need review
Mark an employee as terminated and start offboarding once you approve

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Justworks access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Justworks API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Justworks changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Justworks connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Justworks connector work in claude.ai and Claude Code?

Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Justworks account, so access always matches what that person can already see and do.

Do I need to host or maintain anything myself?

No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Justworks's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.

Is it safe to give a coding agent write access to Justworks?

Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Justworks account it signs in with. Revoking access is one click in Justworks.

More on the Justworks connector

Justworks connector for claude.ai Deel + Claude Code Paychex + Claude Code Paycor + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connector Talk to us