Les meilleurs serveurs MCP pour le web scraping (2026)

Voici les 30 serveurs MCP open source les plus populaires pour le web scraping, classés par étoiles GitHub. Chacun renvoie vers une page avec les détails du dépôt, la configuration d’installation lorsqu’elle existe et des serveurs similaires.

Fetch (official) Official – Web content fetching and conversion for efficient LLM usage.
gpt-researcher ★30100 – An autonomous agent that conducts deep research on any data using any LLM providers
Douyin_TikTok_Download_API ★20642 – 🚀 抖音、TikTok 数据采集与无水印视频下载 API，自托管，支持 MCP 调用与 Docker 一键部署。| Self-hosted TikTok & Douyin scraper and no-watermark video do
apify-mcp-server ★11279 – The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, o
firecrawl-mcp-server ★7607 – 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
wigolo ★5476 – The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0
exa-mcp-server ★5131 – Exa MCP for web search and web crawling!
design-extract ★4237 – Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for
linkedin-mcp-server ★3875 – Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, an
invisible_playwright_mcp ★2750 – Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Pyt
brightdata-mcp ★2677 – A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
Tavily MCP ★2431 – Official Tavily MCP server: real-time web search, extract, map and crawl. Remote server with OAuth or API-key authentica
webclaw ★2379 – Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API
stealth-browser-mcp ★2226 – Stealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extra
slack-mcp-server ★1866 – The most powerful MCP Slack Server with no permission requirements, Apps support, GovSlack, DMs, Group DMs and smart his
crw ★1131 – Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents.
x-reader ★968 – Universal content reader MCP Server for 10+ platforms
google-search ★623 – A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local a
XActions ★594 – ⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No
pullmd ★487 – Self-hosted URL- and file-to-Markdown service for humans and AI agents - web pages, documents, images, audio, YouTube. P
graphlit-mcp-server ★378 – Model Context Protocol (MCP) Server for Graphlit Platform
rust-docs-mcp-server ★299 – 🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddin
PyScrappy ★261 – Adaptive Python web scraping toolkit + MCP server for AI agents. Self-healing selectors that survive site changes, TLS-f
Uni-CLI ★235 – One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local tools, and
amazon-scraper-v2 ★220 – Agent-ready Amazon Scraper API: real-time product details (batch ASIN), offers & stock, reviews, search, best sellers, d
x-twitter-scraper ★213 – X (Twitter) scraper API & Twitter MCP server to scrape tweets, profiles & followers. Not affiliated with X Corp.
agent-control ★181 – 🚀 High-performance AI Agent Control Plane, Task Orchestration & Model Context Protocol (MCP) Platform
agentql-mcp ★181 – Model Context Protocol server that integrates AgentQL's data extraction capabilities.
charlotte ★181 – Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps
searxNcrawl ★167 – MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Questions fréquentes

Qu’est-ce qu’un serveur MCP pour le web scraping ?

Un serveur MCP (Model Context Protocol) relie des assistants IA comme Claude, Cursor ou GitHub Copilot dans VS Code à des outils et des données externes. Les serveurs de cette page sont consacrés à le web scraping.

Comment ce classement est-il établi ?

D’après les étoiles GitHub et l’activité récente, à partir des données publiques des dépôts mises à jour le 15 octobre 2026.

Comment en installer un ?

La plupart s’ajoutent au fichier de configuration MCP de votre client sous forme de commande npx, uvx ou Docker. Nos guides pour Claude Desktop, Cursor et VS Code détaillent chaque étape.

Guides associés

La lettre MCP hebdomadaire – les nouveaux serveurs MCP et les tendances dans votre boîte mail.