Plugs the Amazon Scraper API into Claude Desktop, Cursor, or any MCP client, giving your model four tools: single product lookups by ASIN or URL, keyword search with filters, async batch scraping for up to 1,000 ASINs, and batch status polling. Returns structured JSON with price, rating, availability, variants, and specs across 20 marketplaces. Sidesteps Amazon's robot checks and residential IP requirements by routing through a commercial scraping service. Useful when you need live product data for price comparisons, catalog updates, or multi-prompt shopping research where the model picks ASINs dynamically. Offers 1,000 free requests on signup, then $0.50 per thousand.
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.
"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.
| Tool | What it does | Typical use |
|---|---|---|
amazon_product | Fetch one product by ASIN or URL | "get price + rating for B09HN3Q81F" |
amazon_search | Keyword search with sort/filter | "top 10 cast iron skillets under $50" |
amazon_batch_create | Queue up to 1000 ASINs for async scrape | "scrape all 500 products in my catalog, webhook me when done" |
amazon_batch_status | 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.
| Metric | Value |
|---|---|
| Median latency (product, US) | ~2.6 s |
| P95 latency | ~6 s |
| Price / 1,000 requests | $0.50 flat |
| Marketplaces | 20+ |
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.
Settings → MCP → Add server:
npx -y amazon-scraper-api-mcpASA_API_KEY=asa_live_...claude mcp add amazon-scraper -- npx -y amazon-scraper-api-mcp
# then set ASA_API_KEY in the environment Claude Code runs in
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.
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:
Errors are surfaced to the model as tool errors with a code field and a hint. The model then decides whether to retry or abandon the sub-task. You don't have to write error-handling logic yourself.
Common codes: INVALID_API_KEY, INSUFFICIENT_CREDITS, RATE_LIMITED, target_unreachable, amazon-robot-or-human, extraction_failed, SERVICE_OVERLOADED. Full table: amazonscraperapi.com/docs/errors.
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.
MIT
ASA_API_KEY*secretAmazon Scraper API key. Get 1000 free requests (no credit card) at https://app.amazonscraperapi.com
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp