Web scraping MCP servers

A server here extracts content or structured data from web pages.

Not here: web search.

1,765servers
1,112 remote653 localTagged by Odel's AI, which can make mistakes

Best fit

1,107 made for this, ranked by starsRemoteLocal
  1. Decodo MCP @decodo/mcp-serverEnable your AI agents to scrape and parse web content dynamically, including geo-restricted sites13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.38 GitHub stars.
  2. PageMap @retio-ai/pagemapStructured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.36 GitHub stars.
  3. Documentation Extractor @nirholas/extract-llms-docsExtract llms.txt from any docs site - Mintlify Docusaurus GitBook parser3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.34 GitHub stars.
  4. Cdpilot @mehmetnadir/cdpilotZero-dependency browser automation over raw CDP — no Puppeteer, Playwright, or Selenium.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.32 GitHub stars.
  5. Apify @mcparmory/apifyBuild, deploy, and run web scraping and automation actors in the cloud8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
  6. Agentql @mcparmory/agentqlQuery webpages and extract structured data using natural language7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
  7. DocPull @raintree-technology/docpullSync public web sources into cited context packs for AI agents, RAG, and MCP clients.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
  8. OneTool MCP @beycom/onetool-mcpOne MCP for devs incl Brave,Google,Tavily,Context7,AWS,Excalidraw,DB,GitHub,DevTools,Playwright9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.24 GitHub stars.
  9. Kitewright MCP @kitewright/mcpLightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.23 GitHub stars.
  10. Zen @sh6drack/zen-mcpMCP server for Zen Browser automation via WebDriver BiDi6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.22 GitHub stars.
  11. Octen @octen-team/octen-mcpURL to LLM-ready markdown — plus per-page category, page_structure, and query-driven highlights.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
  12. PyreCrawl @sanggonboy/pyrecrawlWeb scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
  13. Tilda @theyahia/tilda-mcpMCP server for Tilda API — projects, pages. 3 tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
  14. Wet @n24q02m-io/wetOpen-source MCP server for AI agents: web search, content extraction, and library docs.Not assessed yet.Runs on your machine, installed from PyPI.19 GitHub stars.
  15. Svipall @ilien/mcpRead any page past its anti-bot wall, crawl sites, search without an API key, solve captchas locally32% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
  16. wet @n24q02m/wetOpen-source MCP server for AI agents: web search, content extraction, and library docs.Not assessed yet.Runs on your machine, installed from PyPI.18 GitHub stars.
  17. Public Browser @silbercue/public-browserChrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
  18. Wet @n24q02m/wet-mcpOpen-source MCP server for AI agents: web search, content extraction, and library docs.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.18 GitHub stars.
  19. Browser Gateway @browser-gateway/browser-gatewayAI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
  20. MCP Retrieval @role1776/mcp-retrievalLocal Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.16 GitHub stars.
  21. unbrowser by Unchained @protostatis/unbrowserChrome-free MCP web access for agents with low-token page maps and browser escalation hints.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
  22. SEO Crawler @houtini-ai/seo-crawler-mcpCrawl and analyse websites for SEO errors using Crawlee with SQLite storage5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
  23. Scrapfly MCP @scrapfly/mcpScrape any website, extract structured data, and collect web content at scale with AI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
  24. Fiverr @kyurish/fiverr-mcp-serverSearch Fiverr gigs, sellers, pricing, and reviews. No API key required.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.14 GitHub stars.