Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Enables AI assistants to control a browser for web automation tasks, including navigation, typing, clicking, and taking screenshots, deployable to Cloudflare Workers.

README.md

Cloudflare Playwright MCP Example

![Deploy to Cloudflare](https://deploy.workers.cloudflare.com/?url=https://github.com/cloudflare/playwright-mcp/tree/main/cloudflare/example)

Overview

This project demonstrates how to use Playwright with Cloudflare Workers as a Model Control Protocol (MCP) server using Cloudflare Playwright MCP.

It enables AI assistants to control a browser through a set of tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.

The server can be used with various AI platforms including Cloudflare AI Playground, Claude Desktop, and GitHub Copilot in VS Code.

Deploy

Follow these steps to set up and deploy the project:

  1. Install dependencies:
npm ci
  1. Deploy to Cloudflare Workers:
npx wrangler deploy

Use with Cloudflare AI Playground

!alt text

Cloudflare playground AI is a great way to test MCP servers using LLM models available in Workers AI.

  • Navigate to https://playground.ai.cloudflare.com/
  • Ensure model is set to llama-3.3-70b-instruct-fp8-fast
  • In MCP Servers, set URL to https://[my-mcp-url].workers.dev/sse
  • Click Connect
  • Status should update to Connected and it should list 14 available tools

You can now start to interact with the model, and it will run necessary tools to accomplish what was requested.

[!TIP] For best results, give simple instructions consisting of one single action, e. g., "Create a new todo entry", "Go to cloudflare site", "Take a screenshot"

Example of a conversation:

| Role | Message | |------|---------| | User | Go to demo.playwright.dev/todomvc | | Assistant | runs browser_navigate tool<br> The page has been navigated to https://demo.playwright.dev/todomvc/. The page title is "React • TodoMVC". The page snapshot shows the content of the page, including a heading, a textbox, and several links. | | User | Create some todo entry | | Assistant | runs browser_type tool<br> A new todo entry "Buy groceries" has been created. The page snapshot shows the updated content of the page, including the new todo entry. | | User | Nice. Now create a todo in parrot style | | Assistant | runs browser_type tool<br> A new todo entry "Polly wants a cracker" has been created in parrot style. The page snapshot shows the updated content of the page, including the new todo entry. | | User | And create another todo in yoda style | | Assistant | runs browser_type tool<br> A new todo entry "A walk, I must take" has been created in Yoda style. The page snapshot shows the updated content of the page, including the new todo entry. | | User | Take a screenshot | | Assistant | runs browser_take_screenshot tool<br> !alt text A screenshot of the current page has been taken. The screenshot is in PNG format and is 56KB in size. | | User | Now click the checkbox of the parrot todo entry | | Assistant | runs browser_clickt tool<br> The checkbox of the parrot todo entry "Polly wants a cracker" has been clicked. The page snapshot shows the updated content of the page, with the checkbox now checked. | | User | Take a screenshot | | Assistant | runs browser_take_screenshot tool<br> !alt text A screenshot of the current page has been taken. The screenshot is in PNG format and is 58KB in size. | | User | Remove completed todo entries | | Assistant | runs browser_clickt tool<br> The "Clear completed" button has been clicked. The page snapshot shows the updated content of the page, with the completed todo entry "Polly wants a cracker" removed. | | User | Take a final screenshot | | Assistant | runs browser_take_screenshot tool<br> !alt text A final screenshot of the current page has been taken. The screenshot is in PNG format and is 50KB in size. |

Use with Claude Desktop

As of now, Claude Desktop only supports local MCP servers. To use playground-mcp with Claude Desktop we make use of mcp-remote, a tool that proxies remote MCP servers and exposes them locally. Use the following configuration:

  1. Open the configuration file for Claude Desktop.
  2. Add the following JSON snippet under the mcpServers section:
{
  "mcpServers": {
    "cloudflare-playwright-mcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://[my-mcp-url].workers.dev/sse"
      ]
    }
  }
}
  1. Save the configuration file and restart Claude Desktop to apply the changes.

This setup ensures that Claude Desktop can communicate with the Cloudflare Playwright MCP server.

Here's an example of a session opening the TODO demo app, adding "buy lemons" and doing a screenshot, taking advantage of playwright-mcp tools and Browser Rendering:

!alt text

Configure in VSCode

You can install the Playwright MCP server using the VS Code CLI:

# For VS Code
code --add-mcp '{"name":"cloudflare-playwright","type":"sse","url":"https://[my-mcp-url].workers.dev/sse"}'
# For VS Code Insiders
code-insiders --add-mcp '{"name":"cloudflare-playwright","type":"sse","url":"https://[my-mcp-url].workers.dev/sse"}'

After installation, the Playwright MCP server will be available for use with your GitHub Copilot agent in VS Code.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Browser & Scraping servers.