Playwright MCP
OFFICIAL SERVERMicrosoft's Playwright server for driving Chrome, Firefox, WebKit or Edge from an MCP client
MCP servers that drive a real browser or fetch pages for an assistant: navigate, click, fill forms, take screenshots and read what a page shows.
60 servers, page 1 of 2.
Search capabilities in this directory
Microsoft's Playwright server for driving Chrome, Firefox, WebKit or Edge from an MCP client
Lets an assistant control and inspect a live Chrome browser: automate pages, debug, trace performance.
Local MCP server that drives a Chrome or Chromium browser step by step, with an agent fallback
Lets an assistant scrape pages over HTTP or a real browser, pick elements by CSS selector and take screenshots
Web search, scraping, crawling and research-paper search through Firecrawl, hosted or run with npx.
Find and run Apify Store scrapers and crawlers, and manage Actors, runs and data on the Apify platform
Lets an assistant search the web, read pages as markdown and run Exa research agents.
Web search, unblocked page scraping, pre-built scrapers and a remote browser, run through Bright Data
Tavily's web search, page extraction, site crawling and research API, offered as MCP tools
A separate desktop Chromium browser that AI agents drive through a local MCP endpoint, signed in as you
macOS screen capture, UI inspection and native click-and-type automation exposed over MCP
Web search and page reading through a SearXNG metasearch instance you run or trust
Mozilla's server for driving and debugging Firefox: browse, fill forms, read console, network, profiler
Keyless web search, page fetching, crawling and extraction that run on your own machine
Microsoft's MCP wrapper for MarkItDown: turn files, web pages and data URIs into Markdown
Lets an assistant scrape pages to Markdown, search the web and extract structured data through Crawl4AI Cloud
Debug and reverse-engineer a web page's JavaScript in a visible Chrome, with breakpoints and network capture
Local MCP server that reads and operates desktop app windows on macOS, Linux and Windows
Linux desktop control over MCP: accessibility trees, screenshots, clicks and typing on Wayland and X11
Reverse-engineering workbench for web pages, JavaScript bundles, WASM, native processes and APKs
MCP endpoint of a self-hosted Magic Cloud instance: your APIs, SQL, files, tasks and a headless browser
Run, debug and manage web and mobile tests on BrowserStack's real-device cloud from an assistant
Local web fetch, keyless multi-engine search, site crawl and screenshots in one Rust binary
SEO data from your own Search Console, GA4, Bing and site crawls, hosted or run locally over MCP
Fetches web pages and returns them as HTML, Markdown, plain text, JSON, article text or YouTube transcripts
Dark web OSINT over Tor: query onion search engines, read .onion pages and save reports
Streams console, network, screenshots and Lighthouse audits from your own Chrome tabs to an MCP client
Runs a headless Chromium task from a goal and a start URL, steered by TypeSafe's Jev model
Checks whether a coding agent's change works by driving your running web or desktop app
Read, post and engage on X/Twitter with your own session cookie, without an X API key