How do I get an API key?
Sign up at [app.amazonscraperapi.com](https://app.amazonscraperapi.com). You receive 1,000 free requests on signup, no credit card required.
@ChocoData-com
Basic information
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.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"amazon-scraper": {
"command": "npx",
"args": [
"-y",
"amazon-scraper-api-mcp"
],
"env": {
"ASA_API_KEY": "asa_live_..."
}
}
}
}Fetch structured data for a single Amazon product by ASIN. Returns ~55 fields including title, price, variations, reviews, category ladder, images.
Run an Amazon keyword search. Returns ranked product listings with organic/sponsored positions, prices, ratings, and image URLs.
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.
Poll an async batch job for progress + results.
Amazon Scraper Api is an MCP (Model Context Protocol) server for the Amazon Scraper API. It connects AI assistants like Claude Desktop, Cursor, and Claude Code to live Amazon product data, enabling the model to fetch product details and search results via tool calls.
Install the package with npx -y amazon-scraper-api-mcp and set the ASA_API_KEY environment variable. Add it to your MCP-compatible client’s configuration (e.g., claude_desktop_config.json for Claude Desktop or the MCP settings in Cursor). The server exposes tools like amazon_product, amazon_search, amazon_batch_create, and amazon_batch_status.
amazon_product)amazon_search)Sign up at [app.amazonscraperapi.com](https://app.amazonscraperapi.com). You receive 1,000 free requests on signup, no credit card required.
It exposes four tools: `amazon_product` (fetch one product), `amazon_search` (keyword search with sort/filter), `amazon_batch_create` (queue up to 1000 ASINs), and `amazon_batch_status` (poll batch progress).
Unlike generic browser-based tools that get blocked by Amazon’s robot checks, this server routes calls through Amazon Scraper API, which uses escalating proxy tiers, CAPTCHA retries, and residential IPs to return clean structured data.
Median latency for a product lookup in the US is about 2.6 seconds; P95 latency is about 6 seconds. Pricing is $0.50 per 1,000 requests across all marketplaces.
Yes. Use `amazon_batch_create` to queue up to 1000 ASINs for asynchronous scraping with optional webhook delivery. Monitor progress with `amazon_batch_status`.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
Comments