Shelfglance

Agent endpoint

What an agent sees at trees.com

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

ProductPriceCategorySKU
Deodar Cedar Tree $37.95 set na 13669
American Sycamore Tree $76.95 set na 11222
Little Gem Magnolia Tree $41.95 set na MAG-LIT12
Quaking Aspen Tree $71.95 not set 11680
White Spruce Tree $54.95 set na 11278
Eastern Redbud Tree $69.95 set na 31060
Royal Star Magnolia Tree $71.95 set na 11517
Autumn BlazeĀ® Red Maple Tree $74.95 set na 11522
Juniper 'Wichita Blue' Tree $45.95 not set 15529
Sugar Maple Tree $63.95 set na 10749

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 8 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.