Skip to content
Custom Connectors

Connect Wave to Claude Code

Have Claude draft invoices and record transactions in Wave. From the terminal, inside the sessions where you already work.

How do you connect Wave to Claude Code?

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

claude mcp add --transport http wave 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 Wave once connected?

Full read-write Wave access lets Claude draft invoices from your line items, record income and expense transactions, attach them to the right customer, and propose reconciliations against your bank feed, then act once you approve. The bookkeeping that used to mean manual entry happens where your ledger already is.

  • Draft a customer invoice from agreed line items and amounts
  • Record an income or expense transaction against the correct account
  • Create or update a customer record
  • Categorize uncategorized transactions and propose reconciliations for review
  • Mark an invoice sent or paid 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 Wave 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 Wave API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Wave 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 Wave 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 Wave 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 Wave 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 Wave'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 Wave?
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 Wave account it signs in with. Revoking access is one click in Wave.

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.