Best Scraping and browsing MCP servers

Scanned servers (20)

Safety-scanned and ordered by adoption. If you run one of these, a review puts it in the section above.

• 1
  Ui.Vision MCP

  MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
  not reviewed
  Established
  C
• 2
  AIHawk

  AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
  not reviewed
  Established
  A
• 3
  SeleniumBase MCP

  Stealthy browser automation, testing, and web-scraping via CDP Mode.
  not reviewed
  Established
  B
• 4
  Oya Browser

  Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.
  not reviewed
  Growing
  A
• 5
  mcp

  Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
  not reviewed
  Growing
  B
• 6
  Svipall

  Read any page past its anti-bot wall, crawl sites, search without an API key, solve captchas locally
  not reviewed
  Growing
  C
• 7
  EnConvert

  Unified web ingestion for AI agents: perceive, discover, search, extract, ingest, watch, convert.
  not reviewed
  Growing
  A
• 8
  Aginx Browser

  Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
  not reviewed
  Growing
  B
• 9
  ghostlight

  Visible local browser automation in signed-in Chromium, with optional policy and audit.
  not reviewed
  Growing
  A
• 10
  ZeroDOM

  Token-optimized interaction graph for AI browser agents — 71% fewer tokens than ARIA snapshots.
  not reviewed
  Growing
  A
• 11
  zip-archive-create-extract-bomb-guard

  Create, inspect and extract zip archives offline, with traversal, symlink and zip-bomb guards.
  not reviewed
  Growing
  A
• 12
  pdf-merge-split-stamp-extract-pages

  Merge, split, extract, rotate, reorder and stamp PDF pages from your AI chat, all offline.
  not reviewed
  Growing
  A
• 13S
  saas-pricing-extractor

  Extract and structure pricing pages from any SaaS site: plans, tiers, and features.
  not reviewed
  New
  A
• 14N
  news-article-extractor

  Extract clean article text, titles, and metadata from news URLs - ready for NLP pipelines.
  not reviewed
  New
  A
• 15E
  ExtractEdge

  Any web page -> clean markdown. Firecrawl-lite, 0.001 USDC/extract (x402, Base), free demo.
  not reviewed
  New
  A
• 16W
  web-scraper

  Fetch, crawl, and browse protected pages with anti-bot handling - renders in a real browser and
  not reviewed
  New
  A
• 17S
  screenshot

  Pixel-perfect webpage screenshots rendered in a real browser, full-page or viewport, via one POST.
  not reviewed
  New
  B
• 18B
  browser-automation

  Programmatic headless browser sessions: create, interact, browse, and extract - rendered in a real
  not reviewed
  New
  B
• 19
  zip

  Create, inspect and extract zip archives offline, with traversal, symlink and zip-bomb guards.
  not reviewed
  New
  A
• 20
  pdf

  Merge, split, extract, rotate, reorder and stamp PDF pages from your AI chat, all offline.
  not reviewed
  New
  A