The 15 most popular browser & web MCP servers out of 378, with a security level for each.
| # | Name | Popularity | Security |
|---|---|---|---|
| 1 | servers Web content fetching and processing for AI consumption. | 91.3k ★ | Low risk |
| 2 | UI-TARS-desktop Browser automation using Puppeteer, supporting local and remote browser connections. | 39.3k ★ | Low risk |
| 3 | Playwright Playwright browser automation: interact with web pages through structured accessibility snapshots. | 38.3k ★ | Low risk |
| 4 | browser Headless browser for AI and web automation with a built-in MCP server. | 36.6k ★ | Low risk |
| 5 | SeleniumBase Browser automation, testing and bot-detection bypass using SeleniumBase CDP Mode with Chromium, including clic | 13.1k ★ | Low risk |
| 6 | Firecrawl Firecrawl web scraping: search, scrape, crawl, map and extract structured data, with live browser interaction | 7.6k ★ | Low risk |
| 7 | Browser MCP Automate your local Chrome browser. | 7.2k ★ | Low risk |
| 8 | mcp-playwright Browser automation and web scraping using Playwright. | 5.7k ★ | Low risk |
| 9 | wigolo Local web search, fetching, crawling, extraction and research, with multi-engine search, local ML reranking, a | 5.5k ★ | Low risk |
| 10 | exa-mcp-server Real-time web search using the Exa AI Search API. | 5.1k ★ | Low risk |
| 11 | arxiv-mcp-server Search arXiv papers, read original LaTeX sections, get BibTeX from arXiv metadata and set topic watches, with | 3.2k ★ | Low risk |
| 12 | trieve Crawl, embed, chunk, search and retrieve information from datasets through Trieve. | 2.7k ★ | Low risk |
| 13 | brightdata-mcp Discover, extract and interact with the web via Bright Data, one interface for automated access to the public | 2.7k ★ | Review before installing |
| 14 | open-webSearch Multi-engine web search across Bing, Baidu, DuckDuckGo, Brave, Exa and CSDN. | 1.9k ★ | Low risk |
| 15 | duckduckgo-mcp-server Web search using DuckDuckGo, with content fetching and parsing. | 1.5k ★ | Low risk |