Cloudflare Playwright

Provides a browser automation MCP endpoint via Cloudflare Workers for navigation, typing, clicking, and screenshots.
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

This Cloudflare Playwright MCP Server lets an AI assistant control a browser to perform web automation tasks such as navigating pages, typing, clicking, and taking screenshots. It provides a ready-made MCP endpoint that you can connect to from various MCP clients to run browser actions through Playwright.

How to use

Connect to the MCP server from your preferred MCP client (for example, Cloudflare AI Playground, Claude Desktop, or VS Code with Copilot). Use the URL that points to the server's SSE endpoint and enable the connection. Once connected, you can issue browser-related actions as tools, such as navigating to pages, typing into fields, clicking elements, and taking screenshots. For best results, keep requests simple and focused on a single action at a time.

How to install

Prerequisites you need before installation.

Install dependencies and deploy to Cloudflare Workers.

# Install dependencies
npm ci

# Deploy to Cloudflare Workers
npx wrangler deploy

Additional notes

Configure your MCP clients to use the server’s SSE URL: https://[my-mcp-url].workers.dev/sse. This enables the client to connect and discover the available browser tools.

Available tools

browser_navigate

Navigates the browser to a specified URL and returns the page title and URL.

browser_type

Types text into a focused input field or element on the page.

browser_clickt

Clicks a target element on the page, such as a button or checkbox.

browser_take_screenshot

Captures a screenshot of the current page state and returns it as an image.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational