{"uid":"cap_H_u072iUTXGHurejRIkVc","slug":"papacasper-structured-data-extract-dbc7666b","name":"PapaCasper Structured Data Extract","description":"A hosted MCP server exposing utility tools any AI agent can call over HTTP — page-to-markdown, SEO audits, robots/sitemap checks, and more.","url":"https://papacasper.com/mcp/pay/structured_data_extract","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"The URL to extract from"},"attr":{"type":"string","description":"Optional HTML attribute to extract instead of text content (e.g. 'href', 'src', 'content'). Applies to all selector fields in this call."},"selectors":{"type":"object","description":"Optional map of field name -> CSS selector (e.g. { price: '.product-price', headline: 'h1' }). Each field returns an array of matched, whitespace-normalized text values in document order."}}},"responseSchema":{"type":"object"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_sP6gnPodFWrfq2vGrQavX","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured data from a webpage using CSS selectors, returning matched text content or HTML attributes for each named field","exampleAgentPrompt":"Can you extract the product name, price, and availability from https://shop.example.com/product/123 — grab the price from '.product-price', the name from 'h1.product-title', and availability from '.stock-status'?","exampleUseCases":[{"title":"E-commerce price monitoring","prompt":"Pull the current price and sale badge from https://www.bestbuy.com/site/apple-macbook-pro/123456.p — use '.priceView-customer-price span' for price and '.sale-flag' for any promotional label."},{"title":"News article headline scraping","prompt":"Extract the main headline and author name from https://www.nytimes.com/2024/01/15/tech/ai-article.html using 'h1' for the headline and '.byline-author' for the author."},{"title":"Bulk link harvesting from a page","prompt":"Get all the href attributes from every anchor tag on https://docs.python.org/3/library/index.html — use 'a' as the selector and set the attribute to 'href' so I get all the link URLs."}],"resultDescription":"A JSON object where each key corresponds to a named field from the selectors map, and each value is an array of whitespace-normalized text strings (or attribute values if attr is specified) matched in document order from the target page.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error or empty result","CSS selector matches no elements — returns empty array for that field","Invalid or malformed URL — returns validation error","Page requires JavaScript rendering — static HTML-only extraction may miss dynamically loaded content","Rate limiting or bot protection on target URL — may return empty or blocked response","Payment failure via x402 protocol — request is rejected before processing"],"whenToPreferThis":"Choose this endpoint when you need to extract specific named fields from a webpage using CSS selectors, especially when you know the page structure and want structured key-value output rather than full markdown conversion. It is ideal for scraping product pages, news articles, or any page with predictable HTML structure. Prefer alternatives like the page-to-markdown endpoint when you need the full readable content of a page rather than targeted field extraction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:36:32.625Z","isFirstParty":false}