> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentkey.app/llms.txt
> Use this file to discover all available pages before exploring further.

# JD.com product data for AI agents

> Search JD.com by keyword, read product details and current prices, page through buyer comments and list a shop's products through AgentKey.

JD.com is China's largest direct retailer and the benchmark for electronics
and appliance pricing there. Its open platform serves merchants only, and the
storefront asks for a login almost immediately. Through AgentKey your agent
reads public JD.com data the same way it reads everything else — `find_tools`,
`describe_tool`, `execute_tool` — including a lightweight price check for
when the full listing is more than you need.

## What you can ask

* *"京东搜 'iPhone 16 128G'，列出前 10 个结果和价格。"*
* *"这个京东商品现在多少钱？"*
* *"Pull the details of this JD item and summarize the listing."*
* *"Summarize the buyer comments on this JD product — what do people complain about most?"*
* *"List the products in this JD shop and collect their item IDs."*
* *"Check the current JD price of these five items and tell me which ones changed since my last check."*

## What's covered

**Search**

* Keyword search with page-based pagination — discover products and collect
  item IDs for follow-up lookups

**Product details & price**

* Details for a known item ID — inspect an individual product after finding
  its identifier
* A separate current-price lookup by item ID, for a quick check before
  comparison or purchase analysis

**Comments**

* Paginated customer comments for a product by item ID — buyer feedback for a
  known product

**Shops**

* A page of products from a shop by shop ID — browse a seller's catalog and
  collect item IDs

## How to use it

Pass the request in plain language and let the router pick the tool:

```text theme={null}
find_tools(q="京东上这个商品现在的价格")
find_tools(q="buyer comments on this JD.com product")
find_tools(prefix="ecommerce/jd")           # browse everything for JD.com
describe_tool("<returned Provider/Operation>")
execute_tool("<Provider/Operation>", { ...params })
```

Prices come back in yuan, as JD shows them, not converted. Aliases resolve
(京东, JD and JD.com all land here). Always `describe_tool` before executing:
several operations are listed in more than one version, and it shows the exact
parameters, the identifier expected (item ID or shop ID) and the per-call cost.

> [!NOTE]
>
> **Building with code?** The same capability is available as fixed-contract
> [Scenario Methods](/api-reference/scenario/overview) with automatic provider
> failover:
> [`ecommerce.jd.product.search`](/api-reference/scenario/methods/ecommerce-jd-product-search),
> [`ecommerce.jd.product.get`](/api-reference/scenario/methods/ecommerce-jd-product-get),
> [`ecommerce.jd.product.reviews`](/api-reference/scenario/methods/ecommerce-jd-product-reviews),
> [`ecommerce.jd.shop.products`](/api-reference/scenario/methods/ecommerce-jd-shop-products).

## FAQ

> **Do I need a JD.com account or merchant access?**
>
> No. AgentKey holds the upstream access; your agent only needs your AgentKey
> subscription.

> **Is there a way to check only the price?**
>
> Yes. A dedicated price lookup returns the current price for an item ID
> without the rest of the listing. `describe_tool` shows what it costs
> compared with the full detail lookup.

> **How fresh are prices and comments?**
>
> Every call goes to JD.com at request time; nothing is served from a stale
> archive. A price is what the product shows at that moment, in yuan.
> AgentKey does not keep a price history — to track a price, call again on
> your own schedule.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.