Daily takings
Every morning the graph holds a per-location summary of yesterday's completed payments, tips and refunds, so 'how did Tuesday go?' is answered without opening the Square dashboard.
Takings, orders and customers from your Square locations.
Connect Square with a read-only access token and ask about yesterday's takings, what sold, who bought it, which payouts landed and which payments are disputed. Memtro summarises each day's payments per location and keeps order history in the graph.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Square tool, reads what it needs, and answers with the source cited.
Every morning the graph holds a per-location summary of yesterday's completed payments, tips and refunds, so 'how did Tuesday go?' is answered without opening the Square dashboard.
A new dispute becomes a memory with its amount, reason, card brand and evidence deadline, and the disputed payment can be pulled with square_payments to see the customer and order.
Questions people ask once Square is connected. In agent mode each one also checks the other systems that know about the same people, companies or identifiers.
Teams that get the most from Square in Memtro, with the rest of their stack attached.
A record in Square is rarely the whole story. Connect the systems that hold the rest and the agent cross-references them by default, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Square tools are the same everywhere.
Set it up as an MCP server →Clients and agents →Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.