Shelfglance

Agent endpoint

What an agent sees at cafely.com

Searching cafely.com for cafely the way a shopping agent would returned 10 products. This is what it received.

ProductPriceCategorySKU
BanMe Coffee (100% Peaberry Robusta) $28.99 set fb-1-3-1 ccbb
Vietnamese Awakening Coffee Trio (Dark Roast) $79.99 set fb-1-3-1 ccgba
VC2 Pouch (Oat Milk Latte) $99.99 set hb-1-9-6 ccitm
HaNoi Coffee (100% Robusta) $28.99 set fb-1-3-1 ccbh
SaiGon OG Coffee (Robusta x Arabica) $28.99 set fb-1-3-1 ccbs
VC2 Pouch (Espresso) $99.99 set hb-1-9-6 ccitb
VC2 Coconut Latte Travel Sticks $54.99 set hb-1-9-6 ccic-s
VC2 Oat Milk Latte Travel Sticks $54.99 set hb-1-9-6 ccim-s
VC2 Espresso Travel Sticks $54.99 set hb-1-9-6 ccib-s
VĂ ng Phin Filter $49.00 set hg-11-7-4-1 cpf

Price, title, description and URL are Shopify’s doing and are filled in for you. Category and SKU are yours, set per product in your admin. Here 10 of 10 carried a category and 10 of 10 carried a SKU.

Read another one

Leave the search term blank and we use the store name. Any Shopify store, not just your own.

What you are looking at

Your store answers AI shopping agents at /api/ucp/mcp, speaking the Universal Commerce Protocol. Shopify switched it on; it is not in your admin and nothing in your theme controls it. We sent it the same search_catalog request an agent would and put the answer in a table. The long version, with what we found across sixty stores, explains why the two columns on the right are the only ones you can change.

This is not a score and nothing here is a fault. If you want the graded version — whether your pages can be read, not just your endpoint — the scan covers that.