Skip to content
Custom Connectors

Connect TriNet to Claude Code

Have Claude add new hires and pull payroll data in TriNet. From the terminal, inside the sessions where you already work.

How do you connect TriNet to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect TriNet, you add a TriNet MCP server: a small hosted service that exposes TriNet'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 TriNet account. No API keys pasted into config files.

claude mcp add --transport http trinet 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 TriNet once connected?

Read-write TriNet access lets Claude look up employee details and pay info, add a new hire's core record, write deductions and benefits contributions where your plan supports it, and pull payroll and benefits reports. The HR admin work that used to mean clicking through the portal happens in the same conversation, with you approving each change.

  • Look up an employee's profile details, such as address, title, or department
  • Read an employee's pay info to confirm their compensation and status
  • Write a deduction or benefits contribution for your approval before it posts
  • Add a new hire's core record so onboarding can begin
  • Pull a payroll summary or benefits enrollment report on demand
  • Look up an employee and surface their roles and pay details in one step

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 TriNet 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 TriNet API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when TriNet 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 TriNet 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 TriNet 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 TriNet 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 TriNet'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 TriNet?
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 TriNet account it signs in with. Revoking access is one click in TriNet.

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.