- Firecrawl MCP Server @firecrawl/firecrawl-mcp-serverMCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.7,575 GitHub stars.
- Robin: AI-Powered Dark Web OSINT @apurvsinghgautam/robinDark web OSINT over Tor: search onion engines, scrape pages, report with your own model.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.7,493 GitHub stars.
- Wigolo @knockoutez/wigoloLocal-first web intelligence MCP server for AI coding agents7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5,462 GitHub stars.
- Exa @exa/exaConnect AI agents to Exa for web search, content fetching, and multi-step research.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.5,075 GitHub stars.
- Dembrandt @dembrandt/dembrandtDesign tokens from any live site: colours, type, spacing, components, drift against a baseline.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3,624 GitHub stars.
- Browserbase @browserbase/mcp-server-browserbaseMCP server for AI web browser automation using Browserbase and Stagehand5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3,405 GitHub stars.
- Browserbase @smithery/browserbasehq-mcp-browserbaseProvides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3,405 GitHub stars.
- Brightdata @brightdata/brightdata-mcpBright Data's Web MCP server enabling AI agents to search, extract & navigate the web8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2,671 GitHub stars.
- Tavily @tavily-ai/tavily-mcpMCP server for advanced web search using Tavily3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2,425 GitHub stars.
- Ui.Vision MCP @a9t9/uivision-mcpMCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2,069 GitHub stars.
- fastCRW @us/fastcrwScrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1,115 GitHub stars.
- CRW Web Scraper @us/crwOpen-source web scraper for AI agents with scrape, crawl, and map tools6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1,115 GitHub stars.
- CRW Web Scraper @fastcrw/crwOpen-source web scraper for AI agents with scrape, crawl, and map toolsNot assessed yet.Runs on your machine, installed from Docker.1,110 GitHub stars.
- anymd @sylphxai/anymdAny file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1,035 GitHub stars.
- Citra @sylphxai/citraCitra — PDF answers with page-level proof: structure, tables, OCR, and page citations.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1,030 GitHub stars.
- PDF Reader MCP @sylphxai-io/pdf-reader-mcpEvidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1,028 GitHub stars.
- OpenBrand @ethanjyx/openbrandExtract brand assets (logos, colors, backdrop images, brand name) from any website URL6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.799 GitHub stars.
- Unbrowse @unbrowse-ai/unbrowseWebsites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.784 GitHub stars.
- Fortress @tiliondev/fortressStealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.28% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.736 GitHub stars.
- DrissionPage MCP @jumodada/drissionpage-mcpLocal browser automation for MCP clients powered by DrissionPage.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.488 GitHub stars.
- Flyto Core @flytohub/flyto-coreExecution engine for AI agents. 412 modules: browser, file, Docker, data, crypto.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.483 GitHub stars.
Web scraping MCP servers
A server here extracts content or structured data from web pages.
Not here: web search.
1,108 remote654 localTagged by Odel's AI, which can make mistakes
Most popular in Web scraping
By GitHub stars, at most two per publisher- Number 1: Scrapling MCP Server@d4vinci/scraplingWeb scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.86,720 GitHub stars.
- Number 2: Skyvern@skyvern-ai/skyvernAI-powered browser automation — navigate, click, fill forms, and extract data from any website.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.23,168 GitHub stars.
- Number 3: Apify@apify/apify-mcp-serverExtract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.10,071 GitHub stars.
