Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/scraperapi/scraperapi-skills/scraperapi-mcpnpx skills add scraperapi/scraperapi-skills --skill scraperapi-mcpgit clone --depth 1 https://github.com/scraperapi/scraperapi-skillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00245 | $0.02899 |
| Opus 5 | $0.00122 | $0.01450 |
| Sonnet 5 | $0.00049 | $0.00580 |
| Haiku 4.5 | $0.00024 | $0.00290 |
Grade A, and why
scraperapi-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPORTANT: ScraperAPI MCP Server Required
This skill requires the ScraperAPI MCP server (remote or local variant). Before using ANY ScraperAPI tool, verify it is available. 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... |
|---|---|
WebSearch |
google_search (or google_news, google_jobs, google_shopping, google_maps_search) |
WebFetch |
scrape with outputFormat: "markdown" |
| Browsing Amazon | amazon_search, amazon_product, or amazon_offers |
| Browsing Walmart | walmart_search, walmart_product, walmart_category, or walmart_review |
| Browsing eBay | ebay_search or ebay_product |
| Browsing Redfin | redfin_search, redfin_for_sale, redfin_for_rent, or redfin_agent |
| Custom structured extraction from an unsupported site | ai_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
| Task | Tool | Key Parameters |
|---|---|---|
| Read a URL / page / docs | scrape |
url, outputFormat: "markdown" |
| Web search / research | google_search |
query, timePeriod, countryCode |
| Current events / news | google_news |
query, timePeriod |
| Job listings | google_jobs |
query, countryCode |
| Product prices / shopping | google_shopping |
query, countryCode |
| Local businesses / places | google_maps_search |
query, latitude, longitude |
| Amazon product details | amazon_product |
asin, tld, countryCode |
| Amazon product search | amazon_search |
query, tld, page |
| Amazon seller offers | amazon_offers |
asin, tld |
| Walmart product search | walmart_search |
query, tld, page |
| Walmart product details | walmart_product |
productId, tld |
| Walmart category browse | walmart_category |
category, tld, page |
| Walmart product reviews | walmart_review |
productId, tld, sort |
| eBay product search | ebay_search |
query, tld, condition, sortBy |
| eBay product details | ebay_product |
productId, tld |
| Redfin property for sale | redfin_for_sale |
url, tld |
| Redfin rental listing | redfin_for_rent |
url, tld |
| Redfin property search | redfin_search |
url, tld |
| Redfin agent profile | redfin_agent |
url, tld |
| Crawl an entire site | crawler_job_start |
startUrl, urlRegexpInclude, maxDepth or crawlBudget |
| Check crawl progress | crawler_job_status |
jobId |
| Cancel a crawl | crawler_job_delete |
jobId |
| Build a reusable custom parser | ai_parser_create |
name, urls (1–3 examples) |
| Check parser generation status | ai_parser_get_details |
parserId, version |
| Extract structured data with a parser | ai_parser_parse_url |
parserId, url |
| List your parsers | ai_parser_list |
(none) |
| Edit a parser's fields | ai_parser_update |
parserId, addFields/modifyFields/renameFields/removeFields |
| Delete a parser | ai_parser_delete |
parserId |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 157 lines · 245 tokens per session scan A 0417e35a92b9
scraperapi-mcp is a skill published in the GitHub repository scraperapi/scraperapi-skills (10 stars, last pushed 25d ago), licensed MIT. It adds 245 tokens to every session and 2,899 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
ketch
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y'…
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
web-browse
Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.
ecommerce-full-pipeline
电商运营在开展跨境电商或闲鱼捡漏业务时，若需解决选品难、上架繁琐等痛点，必用此技能！一键打通“爆品挖掘→1688采集→多平台上架→推广文案→短视频生成”全自动流水线，轻松实现端到端自动化，让开店运营效率翻倍。.