Uses Microsoft Playwright to drive real Chromium, Firefox, and WebKit browsers for automation, accessibility testing, and UI verification. Agents can click, type, navigate, take screenshots, and extract content from dynamic web pages. Suitable for end-to-end testing and web scraping workflows.
Use cases
- QA agent runs end-to-end tests that log in, fill forms, and verify results
- Accessibility auditor agent checks pages for WCAG compliance issues
- Data extraction agent navigates JavaScript-heavy pages to scrape dynamic content
- Visual regression agent captures screenshots and compares against baselines
- Form automation agent fills and submits web forms in bulk for batch data entry testing
Key features
- Claude Desktop
- Cursor
- Codex
Frequently Asked Questions
- What browsers does Playwright MCP support?
- Chromium, Firefox, and WebKit are all supported. The server auto-installs browser binaries. You can specify which browser to use in the configuration.
- Can it run headless like Puppeteer?
- Yes, Playwright runs headless by default. You can configure headed mode for debugging or screenshot purposes where visible browsers are needed.
- How does it handle pages that require login?
- Agents can use storage state to authenticate once and reuse sessions. Playwright also supports cookie injection and session storage manipulation.
Related
Related
3 Indexed items
Browserbase MCP
Provides cloud-hosted browser sessions for AI agents to navigate websites, interact with DOM elements, fill forms, and execute scripted flows. Eliminates the need to run local Chrome profiles or handle browser automation infrastructure. Agents can perform complex web tasks remotely through a managed browser fleet.
Filesystem MCP
Exposes local file system operations to AI agents with configurable path permissions and sandboxed access controls. Agents can read, write, and search files within explicitly allowed directories. Designed as a reference implementation demonstrating MCP resource patterns and secure file access.
Cloudflare MCP
Bridges AI agents to Cloudflare Workers, KV storage, R2 object storage, and D1 databases for edge deployment inspection and management. Agents can check Workers status, inspect KV namespaces, query D1 databases, and monitor R2 buckets directly from the coding environment.