Categories › AI & Agents › Multi-agent, orchestration & workflows
Where AI agents buy things for people: real US stores, delivered price and date, one order.
Remote server: your requests and data go to api.kaupia.com. Claude Code: claude mcp add --transport http kaupia https://api.kaupia.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_products — Search products for a buyer intent. Returns ranked candidates with price, availability and product_id. Call get_product(product_id) before qget_product — Live details for one product: variants, price, stock status, checkout links.create_checkout — Start a purchase. v0 returns the merchant's checkout link for the chosen variant plus a Kaupia checkout_id. Keep the checkout_id and call rereport_outcome — Report what happened to a checkout: placed | delivered | wrong_item | late | refunded | failed.get_quote — Delivered price for one variant to a US zip code: item + the store's own shipping rate for that address + estimated sales tax, plus the deliplace_order — Order through Kaupia. customer = {name, email, address1, address2?, city, state, zip, phone?} (US only). The user pays Kaupia the delivered order_status — Status of an order placed through Kaupia (received → paid → placed → shipped → delivered) with tracking.shop_scorecard — Per-shop outcome stats collected through Kaupia (delivered vs problems).Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.