Добавить сервер
webscraping-ai/webscraping-ai-mcp-server
  1. Каталог MCP
  2. webscraping-ai/webscraping-ai-mcp-server

webscraping-ai/webscraping-ai-mcp-server

от webscraping-ai
MCP сервер для веб-скрапинга через WebScraping.AI — извлекает текст, HTML и структурированные данные, задаёт вопросы по содержимому страниц. Поддерживает JavaScript-рендеринг, CSS-селекторы, выбор прокси и эмуляцию устройств. Идеален для интеграции с LLM при сборе информации с сайтов.

WebScraping.AI MCP Server

A Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI for web data extraction capabilities.

Features

  • Question answering about web page content
  • Structured data extraction from web pages
  • HTML content retrieval with JavaScript rendering
  • Plain text extraction from web pages
  • CSS selector-based content extraction
  • Multiple proxy types (datacenter, residential, stealth) with country selection
  • JavaScript rendering using headless Chrome/Chromium
  • Concurrent request management with rate limiting
  • Custom JavaScript execution on target pages
  • Device emulation (desktop, mobile, tablet)
  • Account usage monitoring
  • Content sandboxing option - Wraps scraped content with security boundaries to help protect against prompt injection

Installation

Running with npx
env WEBSCRAPING_AI_API_KEY=your_api_key npx -y webscraping-ai-mcp
Manual Installation
# Clone the repository
git clone https://github.com/webscraping-ai/webscraping-ai-mcp-server.git
cd webscraping-ai-mcp-server

# Install dependencies
npm install

# Run
npm start
Инструменты были проиндексированы:
webscraping_ai_account
Параметры

Без параметров.

webscraping_ai_fields
Параметры
  • countryenum

    Country of the proxy to use (US by default).

  • custom_proxystring

    Your own proxy URL in "http://user:password@host:port" format.

  • deviceenum

    Type of device emulation.

  • error_on_404boolean

    Return error on 404 HTTP status on the target page (false by default).

  • error_on_redirectboolean

    Return error on redirect on the target page (false by default).

  • fieldsobjectобязательный

    Dictionary of field names with instructions for extraction.

  • jsboolean

    Execute on-page JavaScript using a headless browser (true by default).

  • js_scriptstring

    Custom JavaScript code to execute on the target page.

  • js_timeoutnumber

    Maximum JavaScript rendering time in ms (2000 by default).

  • proxyenum

    Type of proxy: datacenter, residential, or stealth (residential by default). Use residential if the site restricts datacenter traffic, or stealth for the most heavily protected sites with advanced anti-bot detection. Residential and stealth requests cost more than datacenter — see the pricing page.

  • timeoutnumber

    Maximum web page retrieval time in ms (15000 by default, maximum is 30000).

  • urlstringобязательный

    URL of the target page.

  • wait_forstring

    CSS selector to wait for before returning the page content.

webscraping_ai_html
Параметры
  • countryenum

    Country of the proxy to use (US by default).

  • custom_proxystring

    Your own proxy URL in "http://user:password@host:port" format.

  • deviceenum

    Type of device emulation.

  • error_on_404boolean

    Return error on 404 HTTP status on the target page (false by default).

  • error_on_redirectboolean

    Return error on redirect on the target page (false by default).

  • formatenum

    Response format (json or text).

  • jsboolean

    Execute on-page JavaScript using a headless browser (true by default).

  • js_scriptstring

    Custom JavaScript code to execute on the target page.

  • js_timeoutnumber

    Maximum JavaScript rendering time in ms (2000 by default).

  • proxyenum

    Type of proxy: datacenter, residential, or stealth (residential by default). Use residential if the site restricts datacenter traffic, or stealth for the most heavily protected sites with advanced anti-bot detection. Residential and stealth requests cost more than datacenter — see the pricing page.

  • return_script_resultboolean

    Return result of the custom JavaScript code execution.

  • timeoutnumber

    Maximum web page retrieval time in ms (15000 by default, maximum is 30000).

  • urlstringобязательный

    URL of the target page.

  • wait_forstring

    CSS selector to wait for before returning the page content.

webscraping_ai_question
Параметры
  • countryenum

    Country of the proxy to use (US by default).

  • custom_proxystring

    Your own proxy URL in "http://user:password@host:port" format.

  • deviceenum

    Type of device emulation.

  • error_on_404boolean

    Return error on 404 HTTP status on the target page (false by default).

  • error_on_redirectboolean

    Return error on redirect on the target page (false by default).

  • jsboolean

    Execute on-page JavaScript using a headless browser (true by default).

  • js_scriptstring

    Custom JavaScript code to execute on the target page.

  • js_timeoutnumber

    Maximum JavaScript rendering time in ms (2000 by default).

  • proxyenum

    Type of proxy: datacenter, residential, or stealth (residential by default). Use residential if the site restricts datacenter traffic, or stealth for the most heavily protected sites with advanced anti-bot detection. Residential and stealth requests cost more than datacenter — see the pricing page.

  • questionstringобязательный

    Question or instructions to ask the LLM model about the target page.

  • timeoutnumber

    Maximum web page retrieval time in ms (15000 by default, maximum is 30000).

  • urlstringобязательный

    URL of the target page.

  • wait_forstring

    CSS selector to wait for before returning the page content.

webscraping_ai_selected
Параметры
  • countryenum

    Country of the proxy to use (US by default).

  • custom_proxystring

    Your own proxy URL in "http://user:password@host:port" format.

  • deviceenum

    Type of device emulation.

  • error_on_404boolean

    Return error on 404 HTTP status on the target page (false by default).

  • error_on_redirectboolean

    Return error on redirect on the target page (false by default).

  • formatenum

    Response format (json or text).

  • jsboolean

    Execute on-page JavaScript using a headless browser (true by default).

  • js_scriptstring

    Custom JavaScript code to execute on the target page.

  • js_timeoutnumber

    Maximum JavaScript rendering time in ms (2000 by default).

  • proxyenum

    Type of proxy: datacenter, residential, or stealth (residential by default). Use residential if the site restricts datacenter traffic, or stealth for the most heavily protected sites with advanced anti-bot detection. Residential and stealth requests cost more than datacenter — see the pricing page.

  • selectorstringобязательный

    CSS selector to extract content for.

  • timeoutnumber

    Maximum web page retrieval time in ms (15000 by default, maximum is 30000).

  • urlstringобязательный

    URL of the target page.

  • wait_forstring

    CSS selector to wait for before returning the page content.

webscraping_ai_selected_multiple
Параметры
  • countryenum

    Country of the proxy to use (US by default).

  • custom_proxystring

    Your own proxy URL in "http://user:password@host:port" format.

  • deviceenum

    Type of device emulation.

  • error_on_404boolean

    Return error on 404 HTTP status on the target page (false by default).

  • error_on_redirectboolean

    Return error on redirect on the target page (false by default).

  • jsboolean

    Execute on-page JavaScript using a headless browser (true by default).

  • js_scriptstring

    Custom JavaScript code to execute on the target page.

  • js_timeoutnumber

    Maximum JavaScript rendering time in ms (2000 by default).

  • proxyenum

    Type of proxy: datacenter, residential, or stealth (residential by default). Use residential if the site restricts datacenter traffic, or stealth for the most heavily protected sites with advanced anti-bot detection. Residential and stealth requests cost more than datacenter — see the pricing page.

  • selectorsstring[]обязательный

    Array of CSS selectors to extract content for.

  • timeoutnumber

    Maximum web page retrieval time in ms (15000 by default, maximum is 30000).

  • urlstringобязательный

    URL of the target page.

  • wait_forstring

    CSS selector to wait for before returning the page content.

webscraping_ai_text
Параметры
  • countryenum

    Country of the proxy to use (US by default).

  • custom_proxystring

    Your own proxy URL in "http://user:password@host:port" format.

  • deviceenum

    Type of device emulation.

  • error_on_404boolean

    Return error on 404 HTTP status on the target page (false by default).

  • error_on_redirectboolean

    Return error on redirect on the target page (false by default).

  • jsboolean

    Execute on-page JavaScript using a headless browser (true by default).

  • js_scriptstring

    Custom JavaScript code to execute on the target page.

  • js_timeoutnumber

    Maximum JavaScript rendering time in ms (2000 by default).

  • proxyenum

    Type of proxy: datacenter, residential, or stealth (residential by default). Use residential if the site restricts datacenter traffic, or stealth for the most heavily protected sites with advanced anti-bot detection. Residential and stealth requests cost more than datacenter — see the pricing page.

  • return_linksboolean

    Return links from the page body text.

  • text_formatenum

    Format of the text response.

  • timeoutnumber

    Maximum web page retrieval time in ms (15000 by default, maximum is 30000).

  • urlstringобязательный

    URL of the target page.

  • wait_forstring

    CSS selector to wait for before returning the page content.

Похожие MCP-сервера

Browserbase MCP

Browserbase MCP

официальный

MCP сервер облачной автоматизации браузера Browserbase. Позволяет AI-агентам навигировать по сайтам, извлекать данные и выполнять действия. Полезен для RPA и веб-скрапинга. Доступен self-hosted и hosted.

TypeScript⭐ 3404
just-every/mcp-screenshot-website-fast

just-every/mcp-screenshot-website-fast

Быстрый MCP-сервер для скриншотов веб-страниц, оптимизированный под Claude Vision. Автоматически разбивает полные страницы на тайлы 1072x1072. Поддерживает скринкасты, захват CSS-селекторов и настр...

TypeScript⭐ 109
scraperapi/scraperapi-mcp

scraperapi/scraperapi-mcp

MCP сервер для интеграции с ScraperAPI, позволяющий LLM-агентам легко выполнять веб-скрапинг. Поддерживает рендеринг JavaScript, геотаргетинг и обход блокировок. Полезен разработчикам, работающим с...

Python⭐ 5
jae-jae/fetcher-mcp

jae-jae/fetcher-mcp

MCP сервер для извлечения веб-контента через Playwright. Работает с динамическими сайтами, поддерживает JavaScript, умное выделение текста и пакетную загрузку. Идеален для сбора данных и разработки.

TypeScript⭐ 1084
executeautomation/playwright-mcp-server

executeautomation/playwright-mcp-server

Сервер для браузерной автоматизации на Playwright. Используется AI-агентами для открытия страниц, скриншотов, веб-скрапинга и выполнения JavaScript в реальном браузере. Отлично подходит для тестиро...

TypeScript⭐ 5644
mzxrai/mcp-webresearch

mzxrai/mcp-webresearch

MCP-сервер для веб-исследований, подключающий Claude к интернету: поиск в Google, извлечение содержимого страниц, создание скриншотов и трекинг сессии. Полезен, чтобы получать актуальную информацию...

JavaScript⭐ 300
© Каталог MCP, 2026. Все права защищены.
Проект не аффилирован с Anthropic и любыми упомянутыми продуктами.
Все названия и торговые марки принадлежат их владельцам.
Контакты для связи: hi@mcp-katalog.ru

Лука Никитин