Connect Ramp to Claude Code

Have Claude code expenses and draft bills in Ramp. From the terminal, inside the sessions where you already work.

How do you connect Ramp to Claude Code?

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

claude mcp add --transport http ramp 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 Ramp once connected?

Full read-write Ramp access lets Claude code transactions to the right category and GL account, draft a bill or reimbursement, attach a memo, and route it for approval in Ramp once you confirm. The expense triage and bill prep that used to mean clicking through screens happen where the spend data already lives.

Code an uncategorized transaction to the correct category and GL account
Draft a bill for a vendor and route it into the approval queue
Add a memo or receipt note to a flagged expense
Prepare a reimbursement request for an employee submission
Create a draft bill that a person then approves in the Ramp dashboard
Pull transactions matching a query and propose batched coding

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 Ramp 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 Ramp API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Ramp 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 Ramp 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 Ramp 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 Ramp 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 Ramp'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 Ramp?

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 Ramp account it signs in with. Revoking access is one click in Ramp.

More on the Ramp connector

Ramp connector for claude.ai Expensify + Claude Code Bill.com + Claude Code QuickBooks Online + 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