Connect Brex to Claude Code

Have Claude submit expenses and manage budgets in Brex. From the terminal, inside the sessions where you already work.

How do you connect Brex to Claude Code?

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

claude mcp add --transport http brex 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 Brex once connected?

Full read-write Brex access lets Claude attach receipts and submit expenses, create or adjust budgets and spend limits, manage vendor records, and initiate transfers to managed vendors, each behind your approval. The spend admin work that used to mean clicking through the dashboard happens in the same place you already ask Claude to reconcile and report.

Categorize a transaction and attach the matching receipt and memo
Submit an expense for an out-of-policy purchase with a justification note
Create or adjust a budget and update its spend limit
Add or update a vendor record with payment details
Initiate a transfer to a managed vendor after you approve it

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

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

More on the Brex connector

Brex connector for claude.ai Sage Intacct + Claude Code Wave + Claude Code Zoho Books + 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