amazon_offer_listing
Get all seller offers for an Amazon product with structured pricing, fulfillment, and Buy Box data.
LABSCO SUMMARY
ZIP-code geo-targeting on the raw Amazon fetch is the detail that matters, because Amazon's prices and availability are location-dependent.
Scraping Amazon without controlling location produces numbers that are true somewhere and wrong for the customer you care about — availability, delivery estimates and sometimes price all move with the postcode. Exposing that control is the difference between usable data and plausible data. The offer-listing tool is the other one worth calling out, since the buy-box price is one seller's and the full offer list is what actually tells you the market. proxy_mode_config generating configuration without executing is a small courtesy that avoids paying for a request just to learn the parameter format.
What it is
A Scrape.do client covering three modes: direct scraping with structured extractors for Google and Amazon, an async job API for volume, and a proxy-mode configuration generator.
What you get
- scrape_url returns Markdown or raw output, so a page can arrive in a form a model reads rather than as HTML to parse.
- google_search returns structured SERP data with localisation support rather than a scraped results page.
- Amazon covered at four levels — product detail, all seller offers with pricing and fulfilment, search and category pages, and raw HTML with ZIP-code geo-targeting for the cases the structured extractors do not cover.
- The async API is a full job system: create, list with pagination, read job and task detail, cancel, and read account concurrency limits.
- proxy_mode_config generates the configuration and parameter strings without executing anything, so the setup can be produced without spending a request.
Requirements
SCRAPE_DO_TOKEN. Requests are metered, and the async account tool reports the concurrency you are entitled to.
Setup effort
One command plus a key — claude mcp add-json scrape-do --scope user '{ "type": "stdio", "command": "npx", "args": ["-y", "scrape-do-mcp"], "env": { "SCRAPE_DO_TOKEN": "YOUR_TOKEN_HERE" } }', then supply credentials
USE CASES
01
Getting a page into a form a model can read
Scrape it as Markdown rather than raw HTML, so the content arrives without the markup.
02
Reading search results as data
Pull the structured SERP with localisation rather than parsing a results page.
03
Working out the real price of a product
Read the full offer listing rather than the buy box, and set the ZIP code so availability and pricing reflect the location you care about.
04
Running something too large for one call
Create the async job, follow its tasks, and check your concurrency allowance before scaling it up.
05
Setting up proxy mode
Generate the configuration and parameter strings without spending a request to discover the format.
13 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
amazon_product
Get structured Amazon product detail data with the official Scrape.do Amazon PDP API.
amazon_raw_html
Get raw HTML from any Amazon URL with ZIP-code geo-targeting.
amazon_search
Search Amazon or scrape Amazon category-style result pages with structured product listings.
async_cancel_job
Cancel a Scrape.do Async API job.
async_create_job
Create a Scrape.do Async API job for batch/background scraping.
async_get_account
Get Scrape.do Async API account/concurrency information.
async_get_job
Get Scrape.do Async API job details by job ID.
async_get_task
Get Scrape.do Async API task details by job ID and task ID.
async_list_jobs
List Scrape.do Async API jobs with pagination.
google_search
Search Google with Scrape.do's structured SERP API. Supports localization, google_domain, UULE/location targeting, filters, pagination, and optional raw HTML.
proxy_mode_config
Generate Scrape.do Proxy Mode configuration and parameter strings without exposing your configured token.
scrape_url
Scrape a webpage with the official Scrape.do API. Supports Markdown/raw output, JS rendering, screenshots, browser interactions, geo-targeting, header forwarding, session persistence, and ReturnJSON features.
BEFORE YOU INSTALL
What to know first
Tools you get
13 tools when we connected. Only async_cancel_job changes anything, by stopping a job you started. scrape_url defaults to raw output.
Requires
- npx on PATH
- SCRAPE_DO_TOKEN in your environment
CONTEXT COST
Moderate Standing cost
Rated by the size of the 13 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Claude Code
TERMINAL
claude mcp add-json scrape-do --scope user '{
"type": "stdio",
"command": "npx",
"args": ["-y", "scrape-do-mcp"],
"env": {
"SCRAPE_DO_TOKEN": "<YOUR_SCRAPE_DO_TOKEN>"
}
}'MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"scrape-do": {
"command": "npx",
"args": [
"-y",
"scrape-do-mcp"
],
"env": {
"SCRAPE_DO_TOKEN": "<YOUR_SCRAPE_DO_TOKEN>"
}
}
}
}
