Connect Mercury to Claude Code

Have Claude draft payments and reconcile transactions in Mercury. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect Mercury to Claude Code?

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

claude mcp add --transport http mercury 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 Mercury once connected?

Full read-write Mercury access lets Claude draft and queue payments, add or update recipients, label and categorize transactions, and pull statements, all from a chat. The reconciliation and payment prep that used to mean tab-switching happen where you already ask Claude to work, with each money move gated behind your approval.

Draft an ACH or wire payment to an existing recipient for your approval
Add or update a payment recipient and their account details
Categorize and add notes or memos to transactions for bookkeeping
Queue a batch of vendor payments from an invoice list you provide
Pull a statement or transaction export for a given account and period

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

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

More on the Mercury connector

Mercury 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