crawlbase_structured
ActiveTool of Crawlbase
Scrape a page into clean structured JSON using a named Crawlbase scraper — skip HTML parsing entirely. Common scraper names: "amazon-product-details", "amazon-serp", "google-serp", "facebook-page", "facebook-profile", "instagram-profile", "instagram-post", "linkedin-profile", "linkedin-company", "tiktok-profile", "ebay-product", "walmart-product-details", "github-repository", "generic-extractor". Full catalog: https://crawlbase.com/docs/scrapers/ — social-media scrapers (Facebook/Instagram/LinkedIn) work best with your JavaScript token. Example: crawlbase_structured({ url: "https://www.amazon.com/dp/1098145356", scraper: "amazon-product-details", _apiKey: "your-crawlbase-token" })
Parameters schema
{
"type": "object",
"required": [
"url",
"scraper",
"_apiKey"
],
"properties": {
"url": {
"type": "string",
"description": "The absolute URL of the page to scrape, e.g. \"https://www.google.com/search?q=coffee\" for google-serp."
},
"_apiKey": {
"type": "string",
"description": "Your Crawlbase token (JavaScript token recommended for social-media scrapers). Free tier at https://crawlbase.com"
},
"country": {
"type": "string",
"description": "Two-letter ISO country code to route through, e.g. \"US\", \"DE\". Matters for localized storefronts and SERPs."
},
"scraper": {
"type": "string",
"description": "The Crawlbase scraper name to apply, e.g. \"amazon-product-details\", \"google-serp\", \"linkedin-profile\". Catalog: https://crawlbase.com/docs/scrapers/"
}
}
}No endpoints wrapped at confidence ≥ 0.50.
Parent server
Crawlbase
https://github.com/pipeworx-io/mcp-crawlbase
2/7 registries