Connect Rippling to Claude Code
Let Claude file time off and push candidates into onboarding in Rippling. From the terminal, inside the sessions where you already work.
How do you connect Rippling to Claude Code?
Claude Code reaches outside tools through MCP servers. To connect Rippling, you add a Rippling MCP server: a small hosted service that exposes Rippling'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 Rippling account. No API keys pasted into config files.
claude mcp add --transport http rippling https://your-connector-url/mcpThen 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 Rippling once connected?
Scoped Rippling access lets Claude create and approve time-off requests, create a new employee, push a candidate into onboarding, and read employee, compensation, and roster data. The HR busywork that used to mean clicking through forms happens where the workforce data already lives, with you approving anything sensitive.
- Look up an employee's job title, department, manager, or work location
- Push a candidate into the onboarding flow for a new hire
- Create or approve a time-off request and check remaining balances
- Read an employee's current compensation alongside their record
- Create a new employee record in Rippling
- Pull a roster or headcount report and draft the summary for your team
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 Rippling 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 Rippling API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Rippling 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 Rippling 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 Rippling connector work in claude.ai and Claude Code?
Do I need to host or maintain anything myself?
Is it safe to give a coding agent write access to Rippling?
More on the Rippling connector
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.
