Skip to content
Custom Connectors

Connect ADP to Claude Code

Make Claude update worker records and stage payroll in ADP. From the terminal, inside the sessions where you already work.

How do you connect ADP to Claude Code?

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

claude mcp add --transport http adp 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 ADP once connected?

Full read-write ADP access lets Claude update a worker's address or status, enter or approve time-off requests, adjust scheduled hours, and stage payroll inputs for review, all inside ADP. The reconciliation and data entry that used to mean spreadsheets and re-keying happen where the worker record already lives.

  • Update a worker's profile details such as address, department, or status
  • Enter or approve time-off and leave requests for review
  • Adjust scheduled hours or correct a timecard entry
  • Stage payroll inputs like earnings or deductions for an upcoming run
  • Pull worker and pay data and reconcile it against another system
  • Draft a new-hire record from onboarding details before final submission

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

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.