amazon_batch_create
Queue up to 1000 ASINs or search queries for async processing. Returns a batch id - poll with amazon_batch_status or receive a webhook callback.
LABSCO SUMMARY
A product page becomes a record with fields, and a thousand of them become one job.
The two synchronous tools answer the questions you ask once: amazon_product for the detail behind an ASIN, amazon_search for where listings actually rank on a keyword. Anything larger goes through amazon_batch_create, which takes ASINs or search queries and hands back a batch id; from there it is either amazon_batch_status on a poll or the webhook_url firing when the job lands. The domain and language arguments are what select the marketplace, so the same ASIN can be pulled for more than one storefront.
What it is
An Amazon product data API client covering 4 tools: two synchronous lookups and an async batch queue with a webhook callback.
What you get
- One product at a time: amazon_product returns roughly 55 fields for an ASIN, including title, price, variations, reviews, the category ladder and images, on a chosen domain and language.
- Keyword results as ranked data: amazon_search returns product listings with organic and sponsored positions, prices, ratings and image URLs, with sort_by, pages and start_page controlling the sweep.
- Volume without waiting on it: amazon_batch_create queues up to 1000 ASINs or search queries against either endpoint and returns a batch id, with an optional webhook_url for the callback.
- Progress you can poll: amazon_batch_status reports how far an async batch has got and returns its results.
Requirements
An API key for the service in ASA_API_KEY, and — if you want the callback rather than polling — a webhook_url the service can reach.
Setup effort
One command plus a key — npx -y amazon-scraper-api-mcp, then supply credentials
USE CASES
01
Checking what a competitor's listing actually says today
One call returns the product as fields — price, variations, reviews, the category ladder and images — for the marketplace and language you name.
02
Seeing where a product really ranks for a keyword
The search results come back ranked, with organic and sponsored positions separated, so a page of results becomes a row per listing.
03
Refreshing a catalogue too large to sit and wait for
Queue the ASINs or the queries as one job, then either poll it or let the callback tell you when the results are ready.
4 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
amazon_batch_status
Poll an async batch job for progress + results.
amazon_product
Fetch structured data for a single Amazon product by ASIN. Returns ~55 fields including title, price, variations, reviews, category ladder, images.
amazon_search
Run an Amazon keyword search. Returns ranked product listings with organic/sponsored positions, prices, ratings, and image URLs.
BEFORE YOU INSTALL
What to know first
Tools you get
4 tools when we connected. All four read: fetch a product, run a search, queue a batch of up to 1,000 ASINs, and check that batch. Nothing writes to Amazon.
Requires
- npx on PATH
- ASA_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y amazon-scraper-api-mcpMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"amazon-scraper": {
"command": "npx",
"args": [
"-y",
"amazon-scraper-api-mcp"
],
"env": {
"ASA_API_KEY": "<YOUR_ASA_API_KEY>"
}
}
}
}Claude Code
CLAUDE CODE · TERMINAL
claude mcp add amazon-scraper -- npx -y amazon-scraper-api-mcp
