# Playwright > Official Microsoft browser automation across Chromium, Firefox, and WebKit. [Canonical HTML page](https://top-mcps.com/mcp/playwright) · [server.json](https://top-mcps.com/mcp/playwright.json) · [methodology](https://top-mcps.com/about/methodology) ## Install ### Claude Desktop — `claude_desktop_config.json` Paste under mcpServers. Fully quit and reopen Claude after editing. ```json { "mcpServers": { "playwright": { "command": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } } ``` ### Claude Code — `CLI or .mcp.json` Run from your repo. Commit .mcp.json to share with your team. ```shell claude mcp add playwright -- npx -y @playwright/mcp@latest ``` ### Cursor — `.cursor/mcp.json` Global path: ~/.cursor/mcp.json. Reload window after editing. ```json { "mcpServers": { "playwright": { "command": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } } ``` ### VS Code — `.vscode/mcp.json` VS Code uses the "servers" key (not "mcpServers"). ```jsonc { "servers": { "playwright": { "command": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } } ``` ### Windsurf — `~/.codeium/windsurf/mcp_config.json` Open via Cascade → hammer icon → Configure. ```json { "mcpServers": { "playwright": { "command": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } } ``` ### Cline — `cline_mcp_settings.json` Open via the Cline sidebar → MCP Servers → Edit. ```json { "mcpServers": { "playwright": { "command": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } } ``` ### Continue — `~/.continue/config.json` Continue uses modelContextProtocolServers with a transport block. ```json { "experimental": { "modelContextProtocolServers": [ { "transport": { "type": "stdio", "command": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } ] } } ``` ### Codex CLI — `~/.codex/config.toml` Codex uses TOML. Each server is a [mcp_servers.] subtable. ```shell # ~/.codex/config.toml [mcp_servers.playwright] command = "npx" args = [ "-y", "@playwright/mcp@latest", ] ``` ### Zed — `~/.config/zed/settings.json` Zed calls them "context_servers". Settings live-reload on save. ```jsonc { "context_servers": { "playwright": { "command": { "path": "npx", "args": [ "-y", "@playwright/mcp@latest" ] } } } } ``` ### ChatGPT — `ChatGPT → Apps directory` Playwright doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build. ```none ``` ## At a glance - **Maintainer:** Microsoft - **Transport:** stdio - **Auth model:** None - **Required secrets:** None - **Supported clients:** Claude, Cursor, VS Code, Any MCP-compatible client - **License:** Apache-2.0 - **Language:** TypeScript - **Latest version:** latest - **Last verified:** 2026-05-26 - **GitHub stars:** 33,036 (fetched 2026-05-26T10:50:22.804Z) - **Score:** 94/100 (rubric 2026-04 — see https://top-mcps.com/about/methodology) - **Source:** https://github.com/microsoft/playwright-mcp ## Tools & permissions | Tool | Description | Args | Side effects | |------|-------------|------|--------------| | `browser_navigate` | Navigate to a URL. | `url: string` | network | | `browser_click` | Click an element. | `selector: string` | exec | | `browser_type` | Type text into an input. | `selector: string, text: string` | exec | | `browser_screenshot` | Take a screenshot. | `name: string, fullPage?: boolean` | read | | `browser_evaluate` | Run JavaScript in the page context. | `script: string` | exec | ## Security & scope - **Access scope:** exec - **Sandbox:** Spawns a real browser process under the user account. Has full network access; can execute arbitrary JS on pages it visits. - **Gotchas:** - Three browser engines downloaded on first run (~400 MB total) unless pinned. - Downloads and uploads default to the user home directory. - Auto-wait can mask broken pages — combine with explicit assertions. ## Quick answer **What it does.** Exposes Playwright's automation surface as MCP tools: navigate, click, type, screenshot, evaluate JavaScript, and assert on page state across three real browser engines. **Best for:** - Cross-browser testing - Auto-wait selector reliability - Real Firefox or WebKit - Trace-based debugging - Headed and headless flows **Not for:** - Static-HTML scraping - Bare-metal speed at scale - Resource-constrained environments ## Description The Playwright MCP wraps Microsoft's cross-browser automation framework. Drive Chromium, Firefox, or WebKit headlessly or headed, navigate pages, fill forms, capture screenshots, and run end-to-end assertions with first-class auto-wait so flaky selectors disappear. ## Why it matters Playwright is the most-installed cross-browser test framework in the JavaScript ecosystem. The MCP version means agents can drive the same browsers your QA team already trusts. ## Key features - Chromium, Firefox, WebKit - Auto-wait stability - Trace viewer - Network interception - Multi-tab contexts - Official Microsoft maintenance ## FAQ ### Does it work with all three browsers out of the box? Yes — `npx playwright install` runs the first time the MCP launches and downloads bundled builds of Chromium, Firefox, and WebKit. Pin a single engine with `BROWSER=firefox` if you want to save disk. ### How does it compare to Puppeteer for an agent? Playwright auto-waits for elements to be actionable before clicking, which removes the most common source of agent flake. Puppeteer is fine for Chromium-only flows, but Playwright is the safer default if you are starting fresh. ### Can it record and replay browser sessions? Yes. Playwright traces capture every action, network request, and DOM snapshot. The MCP exposes a trace mode that the agent can hand back to you as a single archive for post-hoc inspection. ## Changelog - **2026-05-26** — Refreshed install snippets and fact sheet; verified for 2026. - **2025-02-15** — Initial directory listing.