amazon-scraper-api
This MCP server gives AI clients live, structured Amazon product and search data through tool calls.
Fetch a single Amazon product by ASIN/URL with structured fields such as title, price, rating, reviews, availability, variants, images, bullets, categories, and specs.
Run Amazon keyword searches with marketplace selection, sorting, and pagination.
Create asynchronous batch jobs for up to 1,000 ASINs or search queries, optionally with a webhook callback.
Poll batch job progress and results.
Query 20+ Amazon marketplaces and supported content languages.
Surface API/HTTP errors to the model so it can decide whether to retry or abandon.
Provides tools to search and retrieve product data from Amazon, including prices, ratings, reviews, availability, and batch scraping across multiple marketplaces.
amazon-scraper-api-mcp
MCP (Model Context Protocol) server for Amazon Scraper API. Plugs into Claude Desktop, Cursor, Claude Code, Continue, or any MCP-compatible AI client. Gives your model live Amazon product data as a first-class tool call.
What it unlocks
"Find me the highest-rated wireless earbuds under $150 on amazon.com, then check if they're cheaper on amazon.de"
That's one prompt. Without MCP, your AI can't fetch Amazon pages (Amazon blocks LLM browsing) and has zero recency for prices and stock. With this MCP server, it calls amazon_search + amazon_product directly and comes back with structured data from Amazon Scraper API.
Related MCP server: Amazon Price Tracker MCP
Tools exposed
Tool | What it does | Typical use |
| Fetch one product by ASIN or URL | "get price + rating for B09HN3Q81F" |
| Keyword search with sort and pagination (one page per call) | "top 10 cast iron skillets under $50" |
| Queue up to 1000 ASINs for async scrape | "scrape all 500 products in my catalog, webhook me when done" |
| Poll a batch's progress | "how much of batch xyz is done?" |
Each returns structured JSON: title, price, rating, reviews count, availability, buybox, variants, images, bullets, categories, spec tables.
Benchmark (live production, 2026-04)
Metric | Value |
Median latency (product, US) | ~2.6 s |
P95 latency | ~6 s |
Price / 1,000 requests | $0.50 flat |
Marketplaces | 20+ |
Claude Desktop setup
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"amazon-scraper": {
"command": "npx",
"args": ["-y", "amazon-scraper-api-mcp"],
"env": {
"ASA_API_KEY": "asa_live_..."
}
}
}
}Restart Claude Desktop. Tools appear under the MCP icon in the chat composer.
Cursor setup
Settings → MCP → Add server:
Command:
npx -y amazon-scraper-api-mcpEnv:
ASA_API_KEY=asa_live_...
Claude Code setup
claude mcp add amazon-scraper -- npx -y amazon-scraper-api-mcp
# then set ASA_API_KEY in the environment Claude Code runs inExample conversation (Claude Desktop)
You: What's the current price of AirPods Pro 3rd gen on amazon.com?
Claude: [calls
amazon_productwith ASIN B09HN3Q81F]The AirPods Pro 3rd gen are currently $199.00 on amazon.com, down from $249.00 (20% off). They have a 4.7-star rating from 58,214 reviews and are in stock, shipping from and sold by Amazon.com with Prime.
You: Compare that to the German Amazon listing.
Claude: [calls
amazon_productwithquery=B09HN3Q81F, domain=de]On amazon.de the same product is listed at 229.00 EUR. At today's exchange rate that's about $245, roughly 23% more than the US price. German listing ships from Amazon and qualifies for Prime delivery.
Why this vs. a generic "browse the web" MCP
Generic browser tools that try to load amazon.com typically get blocked (robot check) or serve a mobile-stripped page. This server routes every call through Amazon Scraper API, which:
Detects and retries robot/CAPTCHA pages through escalating proxy tiers
Returns structured JSON (typed fields), not HTML soup
Supports 20+ marketplaces with country-matched residential IPs
Handles batch (hundreds to thousands of ASINs) with webhook delivery
Error handling
Errors are surfaced to the model as tool errors whose message carries the HTTP status and the API's error code, for example HTTP 502: target_unreachable or HTTP 402: INSUFFICIENT_CREDITS. The model then decides whether to retry or abandon the sub-task. The server itself does not retry.
Common codes: INVALID_API_KEY, INSUFFICIENT_CREDITS, RATE_LIMITED, CONCURRENCY_LIMIT, product_not_found, target_unreachable (retry after 60s or more), extraction_failed, SERVICE_OVERLOADED. Full table: amazonscraperapi.com/docs/guides/errors.
Get an API key
app.amazonscraperapi.com. 1,000 free requests on signup, no credit card required. Enough to test every tool this MCP exposes plus a few dozen productive chats.
Links
Website: https://www.amazonscraperapi.com/
Pricing: https://amazonscraperapi.com/pricing
Node SDK: amazon-scraper-api-sdk · Python SDK: amazonscraperapi-sdk · Go SDK: github.com/ChocoData-com/amazon-scraper-api-sdk-go · CLI: amazon-scraper-api-cli
License
MIT
Available Tools
4 toolsamazon_batch_createA
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.
Inputs: endpoint (required), items (required), webhook_url.
amazon_batch_statusB
Poll an async batch job for progress + results.
Inputs: id (required).
amazon_productB
Fetch structured data for a single Amazon product by ASIN. Returns ~55 fields including title, price, variations, reviews, category ladder, images.
Inputs: query (required), domain, language.
amazon_searchA
Run an Amazon keyword search. Returns ranked product listings with organic/sponsored positions, prices, ratings, and image URLs.
Inputs: query (required), domain, sort_by, start_page, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: batch creation, batch status polling, single product fetch, and keyword search. No overlap between tools.
All tools use snake_case and start with 'amazon_'. Three follow verb_noun pattern ('batch_create', 'batch_status', 'search'), while 'amazon_product' is a noun implying fetch. Minor inconsistency but overall predictable.
Four tools cover the essential scraping operations: search, single product details, and async batch processing. The count is well-scoped for the server's purpose.
Covers search, single product, and batch processing. Missing dedicated review or category tools, but the product tool includes reviews. Minor gaps but core workflows are complete.
Maintenance
Related MCP Connectors
Amazon product API & MCP server: search, prices, ratings, sellers, deals, and ASIN lookup by Canopy.
Live Amazon product, review, search, deal, offer/stock and seller data across 23 marketplaces.
One MCP server for 180+ live web-data APIs returning clean JSON from sites that block scrapers.
Get recommended by Amazon's AI. Hosted MCP server for Amazon listing compliance & generation.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceThis MCP server scrapes Amazon product details and reviews, manages a local JSON database, and visualizes intelligence data through a rich dashboard.-
- AlicenseAqualityDmaintenanceMCP server for tracking Amazon product prices via camelcamelcamel.com, using headless Chromium to bypass Cloudflare protection.32ISC
- FlicenseBqualityDmaintenanceProvides tools to access real-time Amazon data, including product details, reviews, offers, influencer profiles, and deals, through a FastMCP-based server.18-
- AlicenseAqualityCmaintenanceRemote MCP server with 19 e-commerce and IP-compliance data tools — Amazon product/review/search/niche/bestseller data, AI SERP & keyword trends, local Maps POI, WIPO trademark search, and PACER patent litigation. No scraping code or proxies needed; one API key unlocks all tools.211MIT