Niches · Shopping, returns & refunds

Watch a price or stock level and act on a change

One company's docs show a full fit.

1companies, full fit
5companies, fit with a limit
12companies carry the tag
8share of the category's work
3first-hand accounts

What counts as done

Repeated reads by product id return price and stock with a timestamp inside the published rate limit and the retailer's caching terms, through an official route that does not hit a bot check.

How agents ask for it: tell me when this drops below $80, let me know when a bag is available, watch this item for restock

Does the job 1

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Best Buy Developer API E
BestBuy.com, LLC
Repeat reads by SKU (batched with the in operator) return salePrice with priceUpdateDate and availability with update dates, inside 50,000 calls a day and 5 a second, with caching allowed up to 72 hours, on an official keyed API. source

Does the job, with a limit 5

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Amazon Creators API F
Amazon.com Services LLC
Repeated GetItems by ASIN is the official route, but content may be cached at most 24 hours and prices refreshed less than hourly must show a date and time; eligibility lapses without sales (acc-16). source
Etsy Open API v3 B
Etsy, Inc.
A listing read by id returns price, quantity, state and updated_timestamp on the official API; caching rules sit in Section 1 of the API Terms, which were not read, and Personal App review applies. source
MealMe API E
MealMe, Inc.
Get Product Details and Get Inventory re-read price and quote by id through the official API, but no rate limit or caching terms are published and every call is billed. source
Shop MCP B
Shopify Inc.
get_product and lookup_catalog are read-only and idempotent for repeat reads by id, but no rate figure or caching terms are published. source
Walmart Affiliate Marketing API F
Wal-Mart.com USA, LLC
Product Lookup by item id is an official keyed route within 5,000 calls a day, but caching terms and price timestamps were not found in the readable bundle, and acc-18 left open whether fields return without a publisher ID. source

Couldn't check 1

The docs were closed to us, or silent. These carry no mark either way.

ListingWhy
Walmart Agent Gateway F
Walmart Inc.
The post says agents see the same prices as Walmart.com, but no read route or limits are published. source

Doesn't do this job 5

Listings in the category that do something else, with the reason.

ListingWhy
Instacart Developer Platform API + MCP E
Maplebear Inc. dba Instacart
No price or stock read. source
Ocado F
Ocado Retail Limited
No official price or stock read; the site's /api/ paths are disallowed to crawlers. source
opencommerce C
Agentcard Corporation
No repeated price or stock read by product id outside a purchase conversation. source
Too Good To Go F
Too Good To Go ApS
Watching bag availability needs the unofficial app API, which sits behind a bot check (acc-26, acc-28), so there is no official route. source
Zillow in Claude F
Zillow Group, Inc.
Zestimate history and listing reads exist, but nothing is built for repeated retail price or stock checks. source

What stops agents finishing

  • unofficial app API behind DataDome
  • cache limit in the terms (Best Buy 72 hours)

Around it

Before: shopping.find-compare. After: notifications.alert-operator, shopping.place-order.

Where this comes from

Weight 8 of 100 in Shopping, returns & refunds: 3 accounts (acc-13, acc-16, acc-28); a notifications account (watch a page, push on change) shows the same job from the other side

The same as data: /api/v1/use-cases/shopping.price-watch.json, or the MCP tool get_use_case with id shopping.price-watch. Other jobs in this category: /api/v1/niches?category=shopping.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.