Connect Plaid to Claude Code

Let Claude pull balances and draft transfers in Plaid. From the terminal, inside the sessions where you already work.

How do you connect Plaid to Claude Code?

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

claude mcp add --transport http plaid 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 Plaid once connected?

Full read-write Plaid access lets Claude create a link token to onboard an account, trigger a transactions refresh on an item, update or rotate webhook settings, draft a transfer or payment, and remove a stale item, then execute once you approve. The account and money-movement steps that meant hand-editing API calls happen where you already work.

Create a link token to start onboarding a new bank account
Trigger a transactions refresh or sync for a specific item
Update or rotate the webhook URL on an item after your review
Draft a transfer or payment and submit it only after you confirm
Remove a stale item or rotate its access token
Reconcile pulled transactions against an internal ledger record

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

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

More on the Plaid connector

Plaid connector for claude.ai Stripe + Claude Code QuickBooks Online + Claude Code Ramp + 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