MCP SERVER · ON THE PAID PLAN

Ask your own assistant about your money.

MCP is how an AI assistant plugs into a service you already use. Connect this to yours and you can ask what you spent, where it went and what changed, in whatever assistant you already talk to. No pasting a statement into a chat window.

Add the connector in your assistant's settings, approve what it may see on our consent screen, and start asking. Revoke it any time from your profile — access dies on the next request.

How much did I spend on software last quarter?

$1,412.60 across nine merchants.

One call, one number. No transaction left the server to answer it.

Ask your assistant, not us…MCP

HOW IT WILL ANSWER

THE TOOLS

What your assistant can ask for.

An assistant only sees the tools your grant covers. Without transactions:read it is never offered search_transactions at all, rather than being told no when it tries.

run_analytics_query

Totals, grouped and filtered however the question needs. Answers most questions without returning a single transaction.

SCOPE · analytics:read

category_breakdown

What a period went on, by category, with the business and personal split available as a filter.

SCOPE · analytics:read

compare_periods

This month against last. This year against the one before. Two numbers and the difference.

SCOPE · analytics:read

list_accounts

Names, currencies and types. No balances, and never a full account number.

SCOPE · accounts:read

search_transactions

The one tool that does hand back rows, for when the question really is about a specific charge.

SCOPE · transactions:read

What "it never sees your data" can honestly mean.

It cannot mean an assistant is blind to something it asked for. If a tool hands back your transactions, the assistant has your transactions. Anyone telling you otherwise is describing something they have not built.

Here is the narrower version, which is true and more useful.

  • Answers, not row dumpsThe tools are built around totals. "What did I spend on groceries in Q2" is one call and one number, and no transaction leaves the server to answer it.
  • You grant the scopes, and you take them backRead the analytics without reading the transactions. That is a real combination, and a useful one. Revoke it from your profile and the next call is the one that fails, not the next renewal.
  • On this path, your assistant is the only modelYour assistant asks, we answer — no model of ours sits in between, so nothing goes to anyone you did not pick. (The in-app chat is the exception, and the privacy policy names it: it uses Google's Gemini API to read your rows and write the reply.)
  • One write, and only oneAn assistant can import a statement. It cannot recategorise, delete, change a scope or touch your account. The worst a confused agent can do to you is waste an import.

Anyone who can bill your card can write to your agent.

A merchant name is text an attacker chooses. Whoever charges you decides what appears on the line, so a statement descriptor is an input written by someone else and read by your assistant.

So raw descriptors come back fenced as data and are never dropped into instructions, and almost the whole tool surface is read-only. The protection is that there is nothing destructive to trick an agent into doing. It is not a filter that has to catch every phrasing of an attack.

Your assistant answers from what you import.

The server answers from whatever you have already imported — so the statements you upload today are the ones your assistant reads the moment you connect it.

Start with a statement