Web Scraping

Standalone web-research MCP server: DuckDuckGo search + headless Camoufox page scrape/crawl (zero Firecrawl)

MCP server for reading webpages and web search

Firecrawl-backed web fetch MCP server with browser cookie support

Resilient web-fetch MCP server: 3-tier escalation (curl_cffi -> Patchright -> nodriver) that fails honestly, with article-extraction mode and automatic content-type handling (HTML/JSON/PDF/image).

MCP server for web search and content extraction using SearxNG

Lightweight MCP server for web scraping, search, and crawling — local-first with optional Firecrawl fallback

220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python.

A Universal MCP Application: universal_mcp_scraper

A Universal MCP Application: universal_mcp_firecrawl

MCP server for UnblockAPI — captcha solving, browser rendering, temp email, SMS verification, screenshots, and web search for AI agents

Read-only X/Twitter MCP: posts, threads, replies, search via twscrape. No API key.

Official MCP Server for Thordata - Give your AI Agents real-time web scraping superpowers.

MCP server for web fetching with Tavily (primary) and Firecrawl (fallback), plus Tavily search.

Model Context Protocol server for Taiwan law history and article scraping from Legislative Yuan database

Official Python client for Spider MCP web scraping API

104 tools for X/Twitter automation — direct GraphQL/REST API, no browser, no API keys, free.

Context-aware web fetching MCP server that respects token limits

Sitemap MCP is a Model Context Protocol (MCP) server for fetching, parsing, analyzing, and visualizing website sitemaps

MCP server for intelligent web content extraction using single-file and trafilatura

MCP server for Sessemi — scrape anti-bot protected sites from AI agents