@playwright/mcp
Playwright MCP server
The Playwright MCP Server lets the AI control a real browser: open pages, click buttons, fill forms, take screenshots, and extract content. You describe the task in natural language and it drives the browser to do it.
For example, "open this page, log in, and export the order list" — the AI works through it step by step via Playwright. This is Microsoft's official server.
What it does for you
Lets your AI actually drive a real browser — click, fill forms, screenshot, and scrape JS-rendered pages, including sites behind login.
Capabilities
- Open pages, click / type / submit
- Screenshot and read rendered page content
- Handle JS-rendered dynamic sites
- Multi-step browser automation
Once installed, try asking your AI
Say this directly in Claude / Cursor or any client with this server connected
- ›“Open this product page and tell me the price and stock status”
- ›“Fill out the signup form on this site and screenshot the confirmation”
Why use it
Good for: developers and QA doing end-to-end testing, web automation, or data scraping.
Maintained by Microsoft with a very high TrustScore; full health data is shown below.
Works with these clients
- Claude Desktopnpx
- Claude Codenpx
- Cursornpx
- VS Codenpx
- Windsurfnpx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Install / Connect
claude mcp add mcp -- npx -y @playwright/mcpFollow the official README; env and args vary per server.
🛠️ Maintenance weight 30% · 70 pts
📊 Adoption weight 25% · 92 pts
✅ Usability weight 20% · 55 pts
❤️ Health & community weight 25% · 91 pts
Sources: GitHub API · npm registry · updated 2026-08-19
90-day trend
⭐ stars +0%
📦 weekly downloads +0%
Frequently Asked Questions
Does it run a real browser or headless?
Both are supported and configurable. Headless is common for automation; run headed when you want to watch what's happening while debugging.
Can it get past login walls?
It operates a browser like a human, so it can go through normal login flows — but respect the target site's terms and don't use it for abusive scraping.
Similar / alternative servers
How to choose among these
Browser servers differ mainly on local vs. cloud, and whether you need to handle login / dynamic pages.
- Operate login-gated, JS-rendered sites→Pick Playwright MCP — a real browser with the fullest interaction
- Bulk-scrape static sites to Markdown / feed a knowledge base→Pick Firecrawl — easiest for whole-site crawl and extraction
- Want scaled, cloud-hosted browsers→Pick Browserbase / Hyperbrowser — cloud sessions
playwriter
Chrome extension & CLI to let agents control your browser. Runs Playwright snipp
io.github.microsoft/playwright-mcp
Playwright Tools for MCP
io.github.hubertgajewski/playwright-report-mcp
Run Playwright tests and surface structured results for AI agents doing test fai
io.github.ShaftHQ/shaft-mcp
shaft-mcp
One email a week, 5 minutes to see what happened in the MCP ecosystem
New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.
One email a week · unsubscribe anytime · no data selling