microsoft/playwright-mcp
Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
Ads
Overview
Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
Capabilities
- Navigate and inspect pages
Have your assistant visit URLs and read structured accessibility snapshots to understand page content and state.
- Interact with page elements
Direct the assistant to click, type, and perform browser actions on elements found via the accessibility tree.
- Run autonomous browser workflows
Keep a persistent browser context for long-running tasks that iterate over page structure.
- Control session persistence
Use `--isolated` or a persistent `--user-data-dir` profile to manage whether login state and storage survive between runs.
- Generate Playwright code
Enable `--codegen` to capture interactions as code in TypeScript, Python, Java, or C#.
- Connect to an existing browser
Use the browser extension to operate on your logged-in tabs and current browser state.
Installation
npx -y @playwright/mcp@latest
Configuration
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"-y",
"@playwright/mcp@latest"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Supported clients
- Cursor
- Claude Desktop
- VS Code
Tags
- automation
- testing
- chromium
- browser-automation
- testing-qa
- web-scraping
- awesome-list
Used for
Related MCP servers
Browser Automation
frsorrentino/chrome-bridge
MCP server + Chrome extension that drive the user's real, logged-in Chrome over a local WebSocket. 59 token-efficient web-dev tools: compact element refs instead of screenshots, server-side table filtering, visual regression, accessibility/SEO/security audits, network mocking. Also runs on ChromeOS/Crostini.
Browser Automation
SanggonBoy/PyreCrawl
Web browsing superpowers for AI agents: 13 MCP tools (scrape, extract, crawl, map, search, academic papers, batch, research, monitor, session). 3-tier auto-fallback ladder with free Cloudflare bypass, no API keys. Self-hosted Firecrawl alternative.
Browser Automation
ilien-dev/svipall
Local-first web reading with a tier ladder that escalates from plain HTTP to a real browser when a page pushes back. Pages as clean Markdown, whole-site crawls, keyless search, repeated page structure induced into rows, and a REST API. Attempts supported captchas on your own machine with optional local ONNX models, and parks the rest in a human dashboard. Labels blocked and low-quality pages instead of handing back a challenge screen as content. No API keys, no paid solvers, no telemetry.
Browser Automation
zzzjy765/ottersnap-mcp
Glint Render (by Moyu) — web rendering & evidence API for AI agents: screenshots, PDFs, OG images, monitoring, extraction and tamper-evident evidence. Free tier included. `npx -y ottersnap-mcp`
Browser Automation
maccydee/cute-web-scraper
Web scraping with four escalating fetch tiers (httpx, TLS impersonation, Playwright, stealth) that only escalate on a detected block. Returns clean markdown, or saves large scrapes into SQLite tables you query with read-only SQL to keep them out of the context window. 24 tools covering crawls, products, contacts, PDFs and change tracking. MIT, no API key.
Browser Automation
auspy/supasidebar-mcp
Access and organize your open browser tabs, bookmarks, and recently opened links across every macOS browser from your AI client. Powered by the free SupaSidebar app.
Browser Automation
Retio-ai/pagemap
Compresses ~100K-token HTML into 2-5K-token structured maps while preserving every actionable element. AI agents can read and interact with any web page at 97% fewer tokens.
Browser Automation
ScrapeUnblocker/scrapeunblocker-mcp
Fetch any web page's HTML (or AI-parsed JSON, or Google results) through the ScrapeUnblocker anti-bot API (Cloudflare, DataDome, PerimeterX, Akamai, Shape), using your own API key. Three tools: `fetch_html`, `fetch_parsed`, `google_search`. Install: `npx -y scrapeunblocker-mcp`.