The price before the postage
Ask what a parcel will cost and Memtro quotes every carrier you have connected, cheapest first. Buying is a separate step against the rate you were quoted, so the figure in the answer is the figure on the account.
Every carrier you ship with, behind one question: what will this cost, and where is it now?
Royal Mail, Parcelforce, DPD, Evri, InPost, Yodel, UPS, FedEx and DHL each have their own API, their own credentials and their own idea of what a parcel is. ShipEngine sits in front of all of them on your own carrier accounts, so the rates are the ones you negotiated. Memtro quotes a parcel across every carrier you have connected, tracks one, checks an address before you send to it and finds the lockers and ParcelShops near a customer. Buying a label, voiding one and booking a collection are granted by name — and quoting is always separate from buying, so the price is known before the money goes.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right ShipEngine tool, reads what it needs, and answers with the source cited.
Ask what a parcel will cost and Memtro quotes every carrier you have connected, cheapest first. Buying is a separate step against the rate you were quoted, so the figure in the answer is the figure on the account.
A daily job lists every parcel with no carrier scan in 48 hours, with the customer and the order, so support writes to them before they write to you.
These tools change something in ShipEngine. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Questions people ask once ShipEngine 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 ShipEngine in Memtro, with the rest of their stack attached.
A record in ShipEngine 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 ShipEngine 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.