ES

Espresso Steals

com.espressosteals/catalog

Espresso gear price history: live Amazon prices, 2+ years of daily data, BUY calls at verified lows.

Yes, your AI can use this right now.Answered a live MCP handshake in 141 ms with no sign-in needed and exposes 4 tools.

Connect it

Settings → Connectors → Add custom connector
URL: https://espressosteals.com/api/mcp

4 tools, verified live

Pulled straight from the server with tools/list on 2026-10-17.
search_catalogread-only

Search the espresso gear this site tracks. `products` have a live Amazon price and, when at a genuine low, a BUY call computed from their own price history; otherwise no call. Filter by slot (the role a product plays in a setup), free-text words (brand and model names, partial words and small typos are fine), a price band, a brand, or on-sale only. Products we know but cannot price (sold direct by

get_productread-only

Full detail for one product by slug: community sentiment, reference price and basis, date of the latest price observation, portafilter size (machines) or accessory size (sized accessories), superautomatic / manual-lever / hand-grinder flags, product URL and Amazon link. A known product with no price returns price null, the reason, and priced alternatives. An unknown slug returns did_you_mean.

list_slotsread-only

The slots an espresso setup is built from (machine, grinder, scale, tamper…), with what each is for. Use the ids as search_catalog's `slot`.

watch_price

Email the user when a product is at a good price (a verified low), or at or under a target price they name. Use after search_catalog/get_product when the user wants to be told when to buy. Ask the user for their email; never invent or reuse one. One watch per email per product; calling again updates the target. The first time an address is used it receives a confirmation email and the watch arms w

Alternatives in E-commerce

Compare →
Try “Notion”, “Stripe”, “create invoice”, “browser”