Web Scraping API

Name: Web Scraping API
Author: zeeb0tt

@zeeb0tt

リポジトリ

Web Scraping API について

概要はまだありません

#web-scraping #api #ai-agents

基本情報

カテゴリ

ブラウザ自動化

トランスポート

stdio

公開者

zeeb0tt

投稿者

Anthony Ziebell

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "web-scraping-api-by-instantapi-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://web-scraping-api-by-instantapi-ai.help-052.workers.dev/sse",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

ツール

Extract structured data from any webpage with one call: provide the URL and a mock JSON object as the fields parameter, using natural-language placeholder values to describe the data you want (not selectors or HTML details). Examples Basic Usage Scenario: User wants to extract the pricing plans from the Apify pricing page. ``` "url": "https://apify.com/pricing", "fields": { "plans": [ { "name": "", "monthly_price": "", "prepaid_usage": "", "compute_units": "", "actor_ram": "", "max_concurrent_users": "", "rented_actors": "" } ] } ``` Sample response: ``` { "plans": [ { "name": "Free", "monthly_price": "$0", "prepaid_usage": "$5", "compute_units": "$0.4/CU", "actor_ram": "8 GB", "max_concurrent_users": "25", "rented_actors": "Limited" }, ... ] } ``` Advanced Usage Scenario: User wants to extract the product details from the Amazon product page. You can specify not only which fields to extract, but also embed constraints and instructions for each field: ``` "url": "https://www.amazon.com.au/MSI-PRO-MP341CQW-UltraWide-Compatible/dp/B09Y19TRQ2", "fields": { "monitor_name": "< The product name of the monitor. >", "brand": "< The brand or manufacturer name. >", "display_size_in_inches": "< Numeric only. >", "resolution": "< Example format: 1920x1080. >", "panel_type": "< Type of panel. >", "refresh_rate_hz": "< Numeric only. >", "aspect_ratio": "< Example format: 16:9. >", "ports": "< A comma-delimited list of available ports (e.g., HDMI, DisplayPort, etc.). >", "features": "< Key selling points or capabilities, comma-delimited (e.g., LED, Full HD, etc.). >", "price": "< Numeric price (integer or float). >", "price_currency": "< Price currency (3 character alphabetic ISO 4217). >", "review_count": "< Total number of customer reviews, numeric only. >", "average_rating": "< Float or numeric star rating (e.g., 4.3). >", "review_summary": "< A 50 words or less summary of all the written customer feedback. >" } ``` Sample response: ``` { "monitor_name": "MSI PRO MP341CQW 34" UltraWide Business Monitor", "brand": "MSI", "display_size_in_inches": 34, "resolution": "3440x1440", "panel_type": "VA", "refresh_rate_hz": 100, "aspect_ratio": "21:9", "ports": "2xHDMI, DisplayPort", "features": "1500R Curved, Frameless, 1ms, Tilt Compatible, HDR Ready, Built-in Speakers, VESA, 3 Year Warranty", "price": 339, "price_currency": "AUD", "review_count": 391, "average_rating": 4.5, "review_summary": "The MSI PRO MP341CQW offers excellent image quality with a high refresh rate and curved design, making it ideal for both work and gaming. Users appreciate its vibrant colors and ergonomic features." } ```

Extract all links on a webpage that match a specific description with one call: Provide the URL and a natural-language description of the kinds of links to extract. Example Usage Scenario: User wants to extract individual product URLs from an Ikea product listing page. ``` "url": "https://www.ikea.com/au/en/cat/quilt-cover-sets-10680/?page=3", "description": "individual product urls" ``` Sample response: ``` { "links": [ "https://www.ikea.com/au/en/p/strandlummer-duvet-cover-and-pillowcase-multicolour-floral-pattern-00579802/", "https://www.ikea.com/au/en/p/gullnattljus-duvet-cover-and-2-pillowcases-white-floral-pattern-60600075/", ... ] } ```

Extract "Next Page" links from a paginated web page with one call: Provide the URL only. Example Usage Scenario: User wants to extract the "next page" links from a paginated Ikea product listing result. ``` "url": "https://www.ikea.com/au/en/cat/quilt-cover-sets-10680/" ``` Sample response: ``` { "next": [ "https://www.ikea.com/au/en/cat/quilt-cover-sets-10680/?page=2#products-page-2", ... ] } ```

Extract relevant Google search result URLs with one call: Provide the Google domain, search query, and page number of the results. Example Usage Scenario: User wants to extract the first page of search result URLs for the search query "white sofas" on the www.google.com domain. ``` "google_domain": "www.google.com", "query": "white sofas", "page": 1 ``` Sample response: ``` { "search": [ "https://www.ashleyfurniture.com/p/maitelynn_sofa/4820238.html?google_pla=true&utm_source=google&utm_medium=unpaidShopping&region_id=564100", "https://www.livingspaces.com/pdp-isabella-sand-97-inch-sofa-320111?utm_test=spotlight&region_id=808080", ... ] } ```

概要

What is Web Scraping API?

This MCP server integrates InstantAPI.ai's web scraping API into AI agent workflows. It allows autonomous scraping of web pages, extracting links, paginating, and searching without manual HTML selectors or logic. Designed for developers building AI agents that need to gather web data from multiple pages.

How to use Web Scraping API?

Add the provided configuration to your MCP settings, using the command npx -y mcp-remote https://web-scraping-api-by-instantapi-ai.help-052.workers.dev/sse with an Authorization header set via the AUTH_HEADER environment variable