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. DocImprint MCP @docimprint/apiAI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. Ciro Cesar Maciel — Free Tools @ciromaciel/toolsFree, no sign-in: favicons, web to Markdown, CSV to chart, text to speech, time zones, passwords.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. smry Product @smry/smry-productRead public sources and manage a smry library, feeds, notes, highlights, files, and page monitors.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. APEX web reader @apexfaucet/apex-webA real browser for your agent: a page to clean text for $0.009, a 25-page site for $0.14. x402.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. Page Scanner @sbd530/page-scannerCapture a web page from your own Chrome as a PDF whose text is still text.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  6. Search @anon2052/search-mcpWeb search and clean-text fetch MCP server (Tavily-powered, SSRF-guarded).8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. read_url @pradooskee/read-urlOne public web page as clean markdown, with title, language and a SHA-256. Obeys robots.txt.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. Jobpost @kaneky/jobpostRead the job posting from any career page: title, employer, dates, salary. Paid per call, x402.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. Pagemd @kaneky/pagemdRead any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. Styx @thetempleofdoom/styxTor gateway for AI agents: fetch URLs and rotate circuits through Tor, Bitcoin-settled.25% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. ProjectThunder @projectthunder/siteERP and B2B ecommerce rollout research: ERP fit, migration plans, site scans, ERP partner directory.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Contrie @contrie/contrieExtract structured data from a web page, read it as markdown, verify values against the source.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  13. CaptureOneAI Web Perception @captureoneai/web-perceptionGive agents eyes on any web page: structured context, and changes explained in plain language.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  14. Structured Data Check @dawaxwx/structured-data-checkStructured data validator in one call: extracts JSON-LD, microdata and RDFa from a URL or raw HTM...4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. Agent Utilities Hosted @agent-utilities/agent-utilitiesFree agent tools: SEO snapshots, sitemap refresh, Wikipedia collections and saved-page MCP guides.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. Ace Website MCP @ace-bl/site-mcpSearch and read public Ace pages with source URLs.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. BL Sports Website MCP @michaelbarber/site-mcpSearch and read public BL Sports pages with source URLs.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. AARF Utility Network @qolapps/aarf-utility-networkPaid AI utilities for web comparison, code checks, document extraction, security, and research.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  19. Baizhi Cloud Agent Toolkit @ct-jaryn/baizhi-agent-toolkitWeb search, page extraction, visual tools and developer utilities through Baizhi Cloud.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  20. beyourspace data APIs @beyourspace/data-apisPay-per-call data tools via x402: Spanish/EU open data, extraction, URL to Markdown, CSV to JSON.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  21. Wild Orange Charters Website MCP @wildorangecharters/site-mcpSearch and read public Wild Orange Charters pages with source URLs.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. Sunset Website MCP @sunsetmixing/site-mcpSearch and read public Sunset pages with source URLs.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. Mags Tack Website MCP @magstackonline/site-mcpSearch and read public Mags Tack pages with source URLs.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  24. Gulf Coast Wellness & Recovery Spa Website MCP @gcwars/site-mcpSearch and read public Gulf Coast Wellness & Recovery Spa pages with source URLs.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.