Amazon product data API and MCP for AI agents
TollNode gives Claude, Cursor or any AI agent live Amazon.com data (search, bestsellers, prices, specs and reviews) over API and MCP, from $0.007 per call, no subscription.
Ask in plain words, like 'compare the top air fryers by price and rating', and get a clean table back in seconds.
No subscription · Sign-up optional · From $0.007 per call · Charged only when it works · No Amazon account needed
Search Amazon for air fryers and show the price and rating of the top 4
TollNode · Amazon · search$0.055 · 10 products · 4.8 s
| Product | Price (USD) | Rating |
|---|---|---|
| bella 6qt Slim Air Fryer | 47.99 | 4.6 |
| Ninja Air Fryer Pro, 5 Qt | 89.99 | 4.7 |
| Midea Flexify Pro Air Fryer Oven | 215.99 | 4.1 |
| Ninja Digital Air Fry Oven | 149.99 | 4.6 |
| +6 more | ||
Real result.
What your agent can pull from Amazon
- from $0.055
Search
Amazon product search API
Any search a shopper types, with price and rating.
- Title
- Ninja Air Fryer Pro, 5 Qt, 4-in-1, Grey, AF141
- Price
- 89.99 USD
- List price
- 129.99 USD
- Rating
- 4.7
- Reviews
- 11,025
You get
- asin: Amazon's product ID
- title: the listing title
- price: current price in USD
- list price: the crossed-out price, for discounts
- rating: average stars
- review count: how many buyers rated it
- offers: number of sellers
- sponsored flag: paid placement or not
- bestseller badge: Amazon's badge when it has one
- position: rank in the results
- from $0.069
Bestsellers
Amazon bestsellers by category
The top 10 products in any category, in rank order.
- Rank
- 1 in Kitchen & Dining
- Name
- Owala FreeSip Stainless Steel Water Bottle 32 oz
- Price
- 28.00 USD
- Rating
- 4.6
- Reviews
- 145,970
You get
- position: rank in the category
- name: the listing title
- asin: Amazon's product ID
- price: current price in USD
- rating: average stars
- review count: how many buyers rated it
- category: the bestseller list it is on
- link: the product page
- from $0.007
Product details
Amazon product data by ASIN
One product's price, stock, rank, specs and images.
- Title
- Ninja Air Fryer Pro, 5 Qt, 4-in-1, Grey, AF141
- Price
- 89.99 USD (list 129.99 USD)
- In stock
- In Stock
- Rank
- 1 in Air Fryers
- Bought
- 10K+ bought in past month
You get
- title and brand: what it is and who makes it
- price and list price: today's price and the strike-through price
- in stock: availability, as Amazon shows it
- rating and breakdown: average stars and the share of 1 to 5 star ratings
- best seller rank: rank in each category it ranks in
- bought last month: Amazon's own sales signal, when shown
- feature bullets: the seller's selling points
- specs: wattage, size, color and other attributes
- variants: ASINs for other colors and sizes
- images: high-resolution product photos
- review summary: Amazon's short summary of buyer opinion
- delivery: the delivery date shown for the US
- from $0.014
Reviews
Amazon reviews API
Overall rating plus the latest buyer reviews.
- Overall
- 4.7 out of 5 · 11,026 ratings
- Stars
- 5.0 out of 5 stars
- Title
- Great air fryer
- Review
- Very compact doesn't take up a lot of space, looks cute on my kitchen counter...
- Verified
- Yes
You get
- overall rating: average stars for the product
- rating count: total ratings given
- stars: the reviewer's rating
- title: the review headline
- text: the full review
- date: when it was posted
- verified purchase: whether Amazon confirmed the buy
- helpful votes: how many readers found it useful
Every result is structured JSON your agent can sort, filter, summarize or turn into a spreadsheet. Reviewer names are removed.
What people ask their AI to do with it
Shoppers
Pick a product from what owners say
“Search Amazon for air fryers, then read the reviews of the best-rated one and tell me what owners complain about”
search + reviews
Cost today$0.069
Ecommerce sellers
Watch competitors' prices and stock
“Check price, list price and stock on these 5 competitor ASINs and flag any that are out of stock”
5 × product
Cost today$0.035
Market researchers
See what is selling in a category
“List the top 10 kitchen bestsellers with price and review count, then summarize what they have in common”
bestsellers
Cost today$0.069
Content creators
Draft a pros and cons post from buyer feedback
“Pull the specs and latest reviews for this air fryer and write a pros and cons list for my blog”
product + reviews
Cost today$0.021
Product managers
Benchmark competing products side by side
“Look up these three blender ASINs and compare price, rating, best seller rank and key specs in one table”
3 × product
Cost today$0.021
Deal hunters
Find the deepest discounts in a search
“Search Amazon for wireless earbuds and rank the top 10 by discount from the list price”
search
Cost today$0.055
Use it as an Amazon MCP server in Claude, Cursor or Codex
Connect once. Then just ask.
Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.
npx agentcash add https://tollnode.comCopy for your AI agent
Paste this into your agent so it knows what this node does and how to call it.
You can use TollNode's Amazon node to look up live Amazon.com data. Call POST https://tollnode.com/api/v1/nodes/amazon with an "action" and its fields. Actions: search (query), bestsellers (category, as in Amazon's bestseller URLs, e.g. electronics, books, kitchen, beauty), product (asin), reviews (asin). Search and bestsellers return 10 products, reviews returns the latest reviews, product returns price, stock, rank, specs and images. Each action has its own price and is charged only when it returns a result. Over MCP, call the "amazon" tool; use list_models to see prices. Return results as tables when I ask for lists.4 actions, one node
Send action plus the fields that action needs, to the same address. Each action has its own price, charged only when it returns a result. Leave out action and you get product.
- product$0.007
Price, availability and details of one product. Title, brand, price, list price, in-stock status, rating, review count, images, feature bullets and product details..
needs: asin
- reviews$0.014
Customer reviews of one product. Overall rating and rating count, and 10 reviews with stars, title, text, date and verified-purchase flag. No reviewer identities..
needs: asin
- search$0.055
10 search results for a query. 10 products: ASIN, title, price, list price, rating, review count, position, sponsored and bestseller flags, and image..
needs: query
- bestsellers$0.069
Top 10 bestsellers in a category. 10 products in rank order: ASIN, name, price, rating, review count, offers and link..
needs: category
{"action":"product","asin":"B0BSHF7WHW"}{"action":"reviews","asin":"B0BSHF7WHW"}POST either body to https://tollnode.com/api/v1/nodes/amazon. From an AI assistant you don't write this yourself: ask in plain words and it picks the action.
Charged only when a call returns a result. Failed or empty calls cost $0.
Amazon data without a scraper
No subscription, no credit packs
Pay per action: a search is $0.055, a product check is $0.007, a review pull is $0.014.
No Amazon account, no browser, no login
Your agent gets public listing data without touching your Amazon account or sharing cookies.
Only charged when it works
If an ASIN isn't found or a search comes back empty, it costs nothing.
One connection, much more than Amazon
The same setup also gives your agent eBay sold prices, Google search and review sites like Trustpilot.
FAQ
- Is this the official Amazon API?
- No. Amazon's official Product Advertising API requires an approved affiliate account with recent sales. TollNode returns public Amazon.com product data through its own API and MCP server, priced per call.
- Can I use it as an Amazon MCP server in Claude?
- Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the "amazon" tool appears with every action and its price.
- Do I need an Amazon account?
- No. Your agent calls TollNode, and you never log in to Amazon or share cookies.
- What if the ASIN or search returns nothing?
- You're not charged. The response comes back empty and your agent can try a different ASIN or query.
- How many results come back per call?
- Search and bestsellers each return 10 products. Reviews returns the latest reviews, about 10, plus the overall rating and rating count. Product returns one product in full.
- How fresh is the data?
- Every call reads the live Amazon.com page, so prices and stock are current. Nothing is cached or stored as history, so ask your agent to save results if you want to track changes over time.
- Can this place an order or check my own seller account?
- No. It only reads public listing, bestseller and review data from Amazon.com. It can't buy anything or access seller dashboards.
- Does it cover Amazon stores outside the US?
- No, this node covers Amazon.com only, not other country stores like amazon.co.uk or amazon.de.
Works well with
- eBay sold pricesCompare an Amazon price against what it actually sold for on eBay$0.049
- Google data: web, news, trends, Maps, adsCheck web and news results for the same product or brandfrom $0.014
- Trustpilot reviewsSee what buyers say about the brand beyond Amazon$0.022
- YouTube data: search, channels, transcriptsFind video reviews and unboxings of the same productfrom $0.005
Ready in a minute
Connect your AIFor developers: endpoint, inputs and an example response
POST https://tollnode.com/api/v1/nodes/amazon
Input
| Field | Type | Notes |
|---|---|---|
| asin | string | The 10-character Amazon product ID (ASIN), e.g. B0BSHF7WHW (for: product, reviews) |
| query | string | What to look for, e.g. wireless earbuds (for: search) |
| action* | enum | What to do; sets the price. product (needs asin), reviews (needs asin), search (needs query), bestsellers (needs category). Default product (product, reviews, search, bestsellers) |
| category | string | Category as in Amazon's best-seller URLs, e.g. electronics, books, kitchen, beauty (for: bestsellers) |
Example response
{
"results": [
{
"url": "https://www.amazon.com/dp/B0BSHF7WHW",
"asin": "B0BSHF7WHW",
"brand": "Apple",
"input": "https://www.amazon.com/dp/B0BSHF7WHW",
"price": null,
"stars": 4.7,
"title": "Apple 2023 MacBook Pro Laptop with Apple M2 Pro chip with 12‑core CPU and 19‑core GPU: 16.2-inch Liquid Retina XDR Di…",
"author": null,
"seller": null,
"inStock": false,
"support": null,
"delivery": null,
"condition": null,
"listPrice": null,
"brandStory": null,
"hasReviews": true,
"priceRange": null,
"breadCrumbs": "",
"description": null,
"inStockText": "Currently unavailable. Currently unavailable.",
"reviewsLink": "https://www.amazon.com/product-reviews/B0BSHF7WHW",
"videosCount": 0,
"aPlusContent": null,
"locationText": "Delivering to Nashville 37217 Update location",
"originalAsin": "B0BSHF7WHW",
"returnPolicy": null,
"reviewsCount": 384,
"shippingPrice": null,
"isAmazonChoice": false,
"bestsellerRanks": null,
"bookDescription": null,
"fastestDelivery": null,
"amazonChoiceText": null,
"answeredQuestions": null,
"loadedCountryCode": "US",
"productComparison": null,
"importantInformation": null,
"monthlyPurchaseVolume": null,
"unNormalizedProductUrl": "https://www.amazon.com/dp/B0BSHF7WHW"
}
]
}Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.