mcp_web_search
Provides web search capabilities via DuckDuckGo HTML search, returning titles, URLs, and snippets.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp_web_search search for MCP server best practices"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp_web_search
MCP-сервер для веб-поиска, получения контента и скрапинга страниц. Работает через Model Context Protocol — подключается к Claude Desktop и другим MCP-совместимым клиентам.
Возможности
Инструмент | Описание |
| Поиск через DuckDuckGo HTML (без API-ключа). Возвращает заголовки, URL и сниппеты |
| Загрузка страницы и извлечение текстового содержимого. Опционально — список ссылок |
| Скрапинг через Playwright для динамических/JS-сайтов. Поддержка скриншотов |
| Открытие страницы в headless-браузере: заголовок, HTTP-статус, превью контента |
Защита от блокировок
Случайные User-Agent, Accept-Language, Sec-Ch-Ua и другие заголовки
Случайные задержки между запросами
Разные профили браузера при каждом запуске Playwright
Related MCP server: MCP MyZ Search
Установка
git clone <repo-url> mcp_web_search
cd mcp_web_search
npm install
npm run buildДля Playwright необходимо установить Chromium:
npx playwright install chromiumИспользование
Ручной запуск
npm run build # Сборка TypeScript → dist/
npm start # Запуск через stdiodev-режим (без сборки)
npm run devПодключение к Claude Desktop
Добавь в claude_desktop_config.json:
{
"mcpServers": {
"mcp_web_search": {
"command": "node",
"args": ["/путь/к/mcp_web_search/dist/index.js"]
}
}
}Инструменты
web_search
Поиск через DuckDuckGo HTML. Не требует API-ключа.
{ "query": "TypeScript MCP server", "maxResults": 10 }web_fetch
Загрузка страницы и извлечение текста. Быстрее, чем web_scrape, но без поддержки JavaScript.
{ "url": "https://example.com", "withLinks": true, "maxContentLength": 5000 }web_scrape
Полноценный браузерный скрапинг через Playwright Chromium. Для сайтов, которые рендерят контент на клиенте (React, Vue и т.д.).
{
"url": "https://example.com",
"waitForSelector": ".article-body",
"timeout": 30000,
"maxContentLength": 15000,
"takeScreenshot": false
}open_url
Лёгкое открытие страницы — возвращает заголовок, HTTP-статус и краткое превью.
{ "url": "https://example.com", "timeout": 15000 }Стек
TypeScript (ES2022, ESM)
@modelcontextprotocol/sdk — MCP-сервер
Playwright — headless-браузер для динамических страниц
Cheerio — парсинг HTML
Zod — валидация параметров
Скрипты
Команда | Описание |
| Компиляция TypeScript |
| Запуск скомпилированного сервера |
| Запуск через tsx (без компиляции) |
Лицензия
ISC
Available Tools
4 toolsopen_urlB
Open a URL in a headless browser and return the page title, HTTP status, and a short content preview.
Inputs: url (required), waitForSelector, timeout.
web_fetchB
Fetch a URL and return its parsed HTML content as text, optionally with extracted links.
Inputs: url (required), withLinks, maxContentLength.
web_scrapeA
Use Playwright (browser) to load a page with JavaScript support and extract content. Best for dynamic/SPA sites.
Inputs: url (required), waitForSelector, timeout, maxContentLength, +1 more.
web_searchB
Search the web and return results with titles, URLs, and snippets.
Inputs: query (required), maxResults.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Tools are mostly distinct: web_search for search results, web_fetch for static content, web_scrape for dynamic pages, open_url for a quick preview. However, open_url and web_fetch have overlapping functionality (both fetch a URL), which could cause slight confusion if descriptions are not carefully read.
Three tools use the 'web_' prefix (web_fetch, web_scrape, web_search), but open_url breaks the pattern. Verbs are inconsistent (open, fetch, scrape, search). A uniform naming convention like 'web_search', 'web_fetch', 'web_scrape', 'web_preview' would be clearer.
Four tools is an appropriate number for a web search MCP server. Each tool serves a distinct purpose (search, static fetch, dynamic scrape, quick preview), and no tool feels unnecessary. The count is well-scoped.
The tool surface covers the main workflows: searching the web, retrieving content from static pages, and handling dynamic pages. A minor gap is the lack of a dedicated tool for metadata extraction or advanced search filtering, but the core functionality is complete for typical usage.
Maintenance
Related MCP Connectors
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables web searching through DuckDuckGo and fetching content from webpages. Provides search capabilities with configurable result limits and webpage content extraction for AI assistants.-
- AlicenseNot gradedqualityFmaintenanceEnables web search across Bing, DuckDuckGo, and Google using Playwright automation, with tools for retrieving search results and extracting page text content.12 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables web searching through Google, DuckDuckGo, and Bing using a headless Chrome browser, returning structured results with titles, URLs, and snippets. Also supports fetching and extracting text content from any webpage.16MIT
- AlicenseNot gradedqualityDmaintenanceEnables web search using Bing and DuckDuckGo combined, and fetching readable content from web pages, with no API key required.9 npm2MIT