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. Visus @visus-mcp/visus-mcpSecurity-first web access. Sanitizes pages, blocks injection, redacts PII. Now with PDF/JSON/SVG.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  2. Web Scraper @ryudi84/web-scraperMCP server for web scraping: URLs, links, metadata, CSS extraction.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  3. Web Tools @mlawsonking/web-tools-mcp10 no-LLM web tools: URL to Markdown, metadata, JSON-LD, MX, scrape, RSS, DNS, RDAP, SSL, HTTP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  4. LionScraper MCP + CLI + HTTP API (Python) @dowant/lionscraper-pythonLionScraper Python: MCP stdio + CLI + HTTP API bridging AI to LionScraper browser extension.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  5. Nexusfeed LTL @nexusfeed/nexusfeed-ltlReal-time LTL fuel surcharge rates for 10 US carriers with verifiable provenance.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  6. Proxy Veil @goldentrii/proxy-veilResidential proxy MCP server for AI agents — geo-targeting, sticky sessions, anti-bot bypass.28% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  7. Ecommerce Intel @themineworks/ecommerce-intel-mcpProduct intel: Amazon, AliExpress, Shopify, TikTok Shop, ads and search interest.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  8. APICK Web @apick/webDomain/IP, web capture, Google search/maps, YouTube, Instagram, TikTok, X and Amazon data jobs14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  9. Boolsai Scan @boolsai/scanLive tech-stack scan of any public site — vendors, account IDs, scripts, JSON-LD. 2 tools.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  10. Sluicer @gi0tto/sluicerThe data a web page declares, with where each value came from. No model, no API key.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  11. Telegram Channel Scraper - Posts, Media & Buttons | No Login @anshumanatrey/telegram-channel-scraperTelegram Channel Scraper - No Login, $0.30 per 1K Posts14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  12. CapMonster Patchright Captcha Solver @capmonstercloud/capmonster-mcp-patchright-captcha-solverBrowser automation MCP for solving captchas with CapMonster Cloud via Patchright.35% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  13. Apify @pipeworx-io/apifyApify MCP — run web-scraping Actors and fetch their dataset results.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  14. SEO & GEO @ortamarco/seo-geo-mcp-serverAudit a page's SEO and its readiness for AI answer engines: meta, schema, robots, sitemaps, AI bots.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  15. AnyAPI @getanyapi-com/anyapiHundreds of scraping & data APIs through one key. USD pay-per-request, normalized schemas, failover.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  16. CuddlyNest @mafedelahoz/cuddlynest-mcpSearch CuddlyNest hotels and read rooms, prices, availability and cancellation policies5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  17. scrapewright @ozymandias-owens-2/scrapewrightGive it a URL, get structured rows. A model writes the parser once; replays are free.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  18. Wayback Machine @ux-xd/wayback-machineWayback Machine for agents: closest archived copy of a URL with its text, and full capture history7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  19. Substrate Browser @manuelinuxkr/substrate-browserToken-first headless browser for AIs. Extracts a tiny semantic graph, cutting HTML bloat by 95%.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  20. file2markdown @file2markdown/file2markdownConvert docs and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scans, URLs. Batch of 10.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  21. MyWebSearch @wtznicy/my-websearchMyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  22. Safe Fetch @sanoy24/safe-fetchMCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  23. Parsee @parsee/parseeЦены, наличие, отзывы и СПП с Ozon и Wildberries — на компьютере продавца9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  24. mcp.vanshul.com MCP @vanshulgoyal101/mcpRead any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.