Web scraping MCP servers

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

Not here: web search.

1,762servers
1,108 remote654 localTagged by Odel's AI, which can make mistakes

Best fit

1,105 made for this, ranked by starsRemoteLocal
  1. Omnisearch @spences10/mcp-omnisearchMCP server for integrating Omnisearch with LLMs4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.352 GitHub stars.
  2. Oya Browser @oyadotai/oya-browserReal Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.349 GitHub stars.
  3. SpotifyScraper @aliakhtari78/spotifyscraperPublic Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.316 GitHub stars.
  4. Google Surf @harimxchoi/google-surf-mcpWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.291 GitHub stars.
  5. OpenBrowser AI @openbrowser/openbrowser-aiAI browser automation. Write async Python to navigate, click, type, and extract data.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.275 GitHub stars.
  6. PyScrappy @mldsveda/pyscrappyWeb-scraping toolkit with 22 tools for structured web data as JSON for AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.260 GitHub stars.
  7. Nimrod @orchis/nimrodWeb search with quality scores; web pages are read on your computer by the local server.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.256 GitHub stars.
  8. TinySearch @marcellm01/tinysearchSelf-hosted web research for MCP agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.232 GitHub stars.
  9. TinySearch @tinysuitehq/tinysearchFast discovery search and self-hosted web research for MCP agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.230 GitHub stars.
  10. Safari @achiya-automation/safari-mcpNative Safari browser automation for AI agents — 98 tools, zero Chrome overhead.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.212 GitHub stars.
  11. Kreuzcrawl @kreuzberg-dev/kreuzcrawlScrape, crawl, and map websites to Markdown or JSON via local CLI.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.184 GitHub stars.
  12. Crawlberg @xberg-io/crawlbergScrape, crawl, and map websites to Markdown or JSON via local CLI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.182 GitHub stars.
  13. Charlotte @ticktockbent/charlotteRenders web pages into structured, agent-readable representations using headless Chromium.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.181 GitHub stars.
  14. Search1API @superagents-lab/search1apiWeb search, agentic search, news, page retrieval, sitemaps, and trending topics through Search1API.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.173 GitHub stars.
  15. Scrapeless @scrapeless-ai/scrapeless-mcp-serverWeb search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.169 GitHub stars.
  16. WebReaper @alex-on-ai/webreaperAI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.150 GitHub stars.
  17. One Search @yokingma/one-search-mcpWeb search, URL discovery, scraping & extraction with agent-browser and search providers6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.144 GitHub stars.
  18. Vessel Browser @unmodeled-tyler/vessel-browserAI-native browser runtime for autonomous agents with human-in-the-loop supervision7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.136 GitHub stars.
  19. Web Scout @smithery/pinkpixel-dev-web-scout-mcpSearch the web and extract clean, readable text from webpages. Process multiple URLs at once to sp…9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.136 GitHub stars.
  20. Fitter @pxyup/fitterTurn any website or API into structured JSON with LLM-authored declarative scraping configs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.133 GitHub stars.
  21. ru-marketplace-mcp @vladimir-human/ru-marketplace-mcpRead-only MCP servers for Russian marketplaces: prices, stock, ratings, reviews, seller identity8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.130 GitHub stars.
  22. ScrapeGraph @scrapegraphai/scrapegraph-mcpAI-powered web scraping and data extraction capabilities through ScrapeGraph API5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.115 GitHub stars.
  23. Crawlie @crawlie/crawlieTechnical SEO + GEO (AI-search) site audits: hosted crawls, prioritized fixes, report diffs.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.111 GitHub stars.
  24. Free Search @sweetcornna/free-search-mcpNo-API-key web search, page fetching and document reading across many engines. Local-first.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.110 GitHub stars.