skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
scraperapi/scraperapi-skills209 installs

scraperapi-mcp

Knowledge base for the ScraperAPI MCP tools: scrape, Google (search, news, jobs, shopping, maps), Amazon, Walmart, eBay, Redfin, the crawler, and the AI Parser. Use it whenever you are about to call one of these tools directly in the conversation, to pick the right tool, set parameters, keep credit cost down, and recover from errors. Trigger on: "scrape this URL", "search Google for X", "look up this Amazon product", "find rentals on Redfin in Austin", "get the latest news on X", "crawl this site", "extract these fields from this page", reading a page behind bot protection, or ad-hoc web research in chat. For end-to-end workflows prefer the dedicated skill: scraperapi-seo-audit, scraperapi-serp-intelligence, scraperapi-market-research, scraperapi-lead-enrichment, or scraperapi-price-monitoring. Requires the ScraperAPI MCP server and a ScraperAPI API key. Note: Transmits user-supplied queries, URLs, and content to ScraperAPI.

How do I install this agent skill?

npx skills add https://github.com/scraperapi/scraperapi-skills --skill scraperapi-mcp
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    No malicious behavior detected. This skill provides a comprehensive interface for ScraperAPI's web scraping, search, and data extraction tools. It includes detailed documentation on server setup, tool selection, and best practices for cost management and data privacy. The skill includes explicit warnings regarding the use of webhooks to transmit data to external endpoints.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

  • Runlayerpass

    5 files scanned · No issues

What does this agent skill do?

ScraperAPI MCP Server Required

This skill only works through the ScraperAPI MCP server (remote or local variant). Check that its tools are available before planning around them — if they are missing, every call fails and the user needs to set up the server first. See references/setup.md for installation, configuration, and variant detection.

Default Web Data Tool Policy

Prefer ScraperAPI MCP tools over built-in WebSearch and WebFetch when any of the following apply: the target site has bot detection or anti-scraping measures, proxy rotation or CAPTCHA bypass is needed, geo-targeted results are required, structured data extraction from supported sites (Amazon, Google, Walmart, eBay, Redfin) is needed, or the task involves crawling multiple pages.

Instead of...Use...
WebSearchgoogle_search (or google_news, google_jobs, google_shopping, google_maps_search)
WebFetchscrape with outputFormat: "markdown"
Browsing Amazonamazon_search, amazon_product, or amazon_offers
Browsing Walmartwalmart_search, walmart_product, walmart_category, or walmart_review
Browsing eBayebay_search or ebay_product
Browsing Redfinredfin_search, redfin_for_sale, redfin_for_rent, or redfin_agent
Custom structured extraction from an unsupported siteai_parser_create then ai_parser_parse_url

Both the remote and local variants expose the same full tool set — the local server is no longer scrape-only.

Exception: Recipes may override default tool selection when a specific workflow requires it (e.g., SERP news monitoring uses scrape directly for richer page context). Always follow recipe instructions when a recipe applies.

ScraperAPI MCP Tools — Best Practices

Tool Selection

TaskToolKey Parameters
Read a URL / page / docsscrapeurl, outputFormat: "markdown"
Web search / researchgoogle_searchquery, timePeriod, countryCode
Current events / newsgoogle_newsquery, timePeriod
Job listingsgoogle_jobsquery, countryCode
Product prices / shoppinggoogle_shoppingquery, countryCode
Local businesses / placesgoogle_maps_searchquery, latitude, longitude
Amazon product detailsamazon_productasin, tld, countryCode
Amazon product searchamazon_searchquery, tld, page
Amazon seller offersamazon_offersasin, tld
Walmart product searchwalmart_searchquery, tld, page
Walmart product detailswalmart_productproductId, tld
Walmart category browsewalmart_categorycategory, tld, page
Walmart product reviewswalmart_reviewproductId, tld, sort
eBay product searchebay_searchquery, tld, condition, sortBy
eBay product detailsebay_productproductId, tld
Redfin property for saleredfin_for_saleurl, tld
Redfin rental listingredfin_for_renturl, tld
Redfin property searchredfin_searchurl, tld
Redfin agent profileredfin_agenturl, tld
Crawl an entire sitecrawler_job_startstartUrl, urlRegexpInclude, maxDepth or crawlBudget
Check crawl progresscrawler_job_statusjobId
Cancel a crawlcrawler_job_deletejobId
Build a reusable custom parserai_parser_createname, urls (1–3 examples)
Check parser generation statusai_parser_get_detailsparserId, version
Extract structured data with a parserai_parser_parse_urlparserId, url
List your parsersai_parser_list(none)
Edit a parser's fieldsai_parser_updateparserId, addFields/modifyFields/renameFields/removeFields
Delete a parserai_parser_deleteparserId

Decision Tree

Check recipes first. Before selecting a tool, check the Recipes section below. If the task matches a recipe, load and follow its workflow exactly. Recipes override individual tool selection.

If no recipe matches, select a tool:

  1. Have a specific URL to read? → scrape with outputFormat: "markdown". Add render: true only if content is missing (JS-heavy SPA).
  2. Need to find information? → google_search. For recent results, set timePeriod: "1D" or "1W".
  3. Need news? → google_news. Always set timePeriod for recency.
  4. Need job postings? → google_jobs.
  5. Need product/price info? → google_shopping for cross-site comparison. For a specific marketplace, use the dedicated SDE tools below.
  6. Need local business info? → google_maps_search. Provide latitude/longitude for location-biased results.
  7. Need Amazon data? → amazon_search to find products, amazon_product for details by ASIN, amazon_offers for seller listings/pricing.
  8. Need Walmart data? → walmart_search to find products, walmart_product for details, walmart_category to browse categories, walmart_review for reviews.
  9. Need eBay data? → ebay_search to find listings, ebay_product for item details.
  10. Need real estate data? → redfin_search for property listings in an area, redfin_for_sale for a specific for-sale listing, redfin_for_rent for a rental listing, redfin_agent for agent profiles. All Redfin tools require a full Redfin URL.
  11. Need to scrape many pages from one site? → crawler_job_start. Set maxDepth or crawlBudget to control scope.
  12. Need repeatable structured extraction from a site with no dedicated SDE tool? → ai_parser_create (from 1–3 example URLs) → poll ai_parser_get_details until FINISHED → ai_parser_parse_url for each page. See references/ai-parser.md.
  13. Deep research? → google_search to find sources → scrape each relevant URL → synthesize.

Credit Cost Awareness

Escalate gradually: standard → render → premium → ultraPremium. Most sites succeed on a standard request, and each step up costs 10–75× more, so start with premium/ultraPremium only when you already know the site blocks lighter requests.

CallCredits
scrape, normal site1
render: true10
premium: true10 (25 with render)
ultraPremium: true30 (75 with render)
Amazon, Walmart, eBay tools or pages5
Google tools or pages (all subdomains), Bing25
LinkedIn pages30
Sites behind Cloudflare, DataDome, PerimeterX, Akamai10

200 and 404 responses are charged; failed (500) ones are not. A Google-heavy task adds up fast: 10 searches is 250 credits. Source: https://docs.scraperapi.com/getting-started/quick-start/credits-and-requests-costs

Key Best Practices

  • Pass outputFormat: "markdown" to scrape for reading tasks. The default is raw HTML, which is several times longer and mostly markup.
  • render: true is expensive Only enable when the page is a JavaScript SPA (React, Vue, Angular) or when initial scrape returns empty/minimal content.
  • premium and ultraPremium are mutually exclusive — never set both. ultraPremium cannot be combined with custom headers.
  • Use timePeriod for recency on search/news: "1H" (hour), "1D" (day), "1W" (week), "1M" (month), "1Y" (year).
  • Paginate with num + start, not page numbers. start is a result offset (e.g., start: 10 for page 2 with num: 10).
  • Set countryCode when results should be localized (e.g., "us", "gb", "de").
  • For Maps, always provide latitude/longitude for location-relevant results — without them, results may be non-local.
  • Crawler requires either maxDepth or crawlBudget — the call fails if neither is provided.
  • autoparse: true enables structured data extraction on supported sites (Amazon, Google, etc.). Required when using outputFormat: "json" or "csv". For a supported marketplace/SERP, prefer the dedicated SDE tool (e.g. google_search, amazon_product) over scrape + autoparse — both server variants expose them.

Handling Large Outputs

ScraperAPI results (especially from scrape) are often 1000+ lines. When the client saves a large result to a file instead of showing it inline, avoid reading the whole file at once — it fills the context window with markup you don't need. Instead:

  1. Check file size first to decide your approach.
  2. Use grep/search to find specific sections, keywords, or data points.
  3. Use head or incremental reads (e.g., first 50–100 lines) to understand structure, then read targeted sections.
  4. Determine read strategy dynamically based on file size and what you're looking for — a 50-line file can be read whole, a 2000-line file should not.

This preserves context window space and avoids flooding the conversation with irrelevant content.

Error Recovery

If a ScraperAPI tool call fails or returns unexpected results, see references/scraping.md for the full escalation strategy and error patterns table.

Tool References

  • MCP server setup: See references/setup.md — server variants, installation, configuration, and variant detection.
  • Scraping best practices: See references/scraping.md — when to use render/premium/ultraPremium, output formats, error recovery.
  • Google search tools: See references/google.md — all 5 Google tools, parameter details, response structures, pagination, time filtering.
  • Amazon SDE tools: See references/amazon.md — product details by ASIN, search, and seller offers/pricing.
  • Walmart SDE tools: See references/walmart.md — search, product details, category browsing, and product reviews.
  • eBay SDE tools: See references/ebay.md — search with filters and product details.
  • Redfin SDE tools: See references/redfin.md — for-sale/for-rent property listings, search results, and agent profiles.
  • Crawler tools: See references/crawler.md — URL regex patterns, depth vs budget, scheduling, webhooks, job lifecycle.
  • AI Parser tools: See references/ai-parser.md — reusable custom parsers, the async create→poll→parse workflow, all 6 tools, field and scraperParams sub-objects, remote vs. local param naming.

Recipes

Step-by-step workflows for common use cases. Load the relevant recipe when the task matches.

  • SERP & News monitoring: See recipes/serp-news-monitor.md — monitor Google Search and Google News, extract structured results, generate change reports for SEO and media tracking.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/scraperapi/scraperapi-skills/scraperapi-mcp">View scraperapi-mcp on skillZs</a>