MCP Playwright

v1.0.12Browser Automationstable

🚀 Active Fork of executeautomation/mcp-playwright This repository is an actively maintained continuation of the original MCP Playwright server: >👉 https://github.com/executeautomation/mcp-playwright A Model Context Protocol server that provides brows

playwrightautomationAIClaude MCPfilesystem
Share:
5,530
Stars
0
Downloads
0
Weekly
0/5

What is MCP Playwright?

MCP Playwright is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🚀 active fork of executeautomation/mcp-playwright this repository is an actively maintained continuation of the original mcp playwright server: >👉 https://github.com/executeautomation/mcp-playwright...

🚀 Active Fork of executeautomation/mcp-playwright This repository is an actively maintained continuation of the original MCP Playwright server: >👉 https://github.com/executeautomation/mcp-playwright A Model Context Protocol server that provides brows

This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🚀 Active Fork of executeautomation/mcp-playwright This repos

Use Cases

Automate browser interactions and testing
Execute web automation tasks
LicenseMIT License
Languagetypescript
Versionv1.0.12
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @executeautomation/playwright-mcp-server

Manual Installation

npx -y @executeautomation/playwright-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Playwright

MCP Playwright is a Model Context Protocol server that gives AI assistants full browser automation capabilities through Playwright, supporting real browser interactions including screenshots, JavaScript execution, form filling, navigation, and device emulation across 143 device profiles. It is an actively maintained fork of the original executeautomation/mcp-playwright server and installs browser binaries automatically on first use. QA engineers, developers, and AI agents use it to automate end-to-end testing, scrape web data, and interact with web applications through natural language without writing Playwright test scripts manually.

Prerequisites

  • Node.js 18+ and npm/npx installed
  • An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
  • Sufficient disk space for browser binaries (Chromium, Firefox, or WebKit — downloaded automatically)
1

Install the Playwright MCP server globally

Install the package globally via npm so it is available as a command for your MCP client. Alternatively, npx will download it on demand.

npm install -g @executeautomation/playwright-mcp-server
2

Add the server to Claude Desktop configuration

Edit your Claude Desktop config file at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) to add the Playwright server.

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["-y", "@executeautomation/playwright-mcp-server"]
    }
  }
}
3

Restart Claude Desktop

Fully quit and restart Claude Desktop to load the new MCP server. On macOS use Cmd+Q, not just closing the window.

4

Test browser automation with a screenshot

Ask your AI assistant to navigate to a URL and take a screenshot. Playwright will automatically download the required browser binary on first run.

5

Optional: run in HTTP mode for network access

To expose the Playwright MCP server over the network (e.g., for remote agents), use the HTTP transport configuration instead of stdio.

{
  "mcpServers": {
    "playwright": {
      "url": "http://localhost:8931/mcp",
      "type": "http"
    }
  }
}

MCP Playwright Examples

Client configuration

Standard Claude Desktop configuration for the Playwright MCP server using stdio transport (recommended for local use).

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["-y", "@executeautomation/playwright-mcp-server"]
    }
  }
}

Prompts to try

Use natural language to automate browsers, scrape pages, test applications, and emulate devices.

- "Navigate to https://example.com and take a screenshot"
- "Go to the login page at myapp.com, fill in the username and password fields, and click Sign In"
- "Emulate an iPhone 13 and take a screenshot of https://myapp.com to check the mobile layout"
- "Scrape all product names and prices from the first page of https://shop.example.com"
- "Run a JavaScript snippet on the current page to get all link hrefs"

Troubleshooting MCP Playwright

Browser binary download fails or times out on first run

Run 'npx @executeautomation/playwright-mcp-server' manually from the terminal to trigger the browser download with visible progress output. Ensure you have a stable internet connection and sufficient disk space (approximately 300MB per browser).

HTTP mode fails with 'type field is required' error

The 'type': 'http' field is required in the MCP config when using HTTP transport — it is not optional. Ensure your config includes both 'url' and 'type': 'http' fields in the server entry.

Screenshots return blank images or pages don't load

Some pages block headless browsers. Try adding a wait step before taking the screenshot, or switch the browser engine by specifying --browser=firefox in the args array in your MCP config.

Frequently Asked Questions about MCP Playwright

What is MCP Playwright?

MCP Playwright is a Model Context Protocol (MCP) server that 🚀 active fork of executeautomation/mcp-playwright this repository is an actively maintained continuation of the original mcp playwright server: >👉 https://github.com/executeautomation/mcp-playwright a model context protocol server that provides brows It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Playwright?

Install via npm with the command: npx -y @executeautomation/playwright-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with MCP Playwright?

MCP Playwright works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Playwright free to use?

Yes, MCP Playwright is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Browser Automation MCP Servers

Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-playwright": { "command": "npx", "args": ["-y", "@executeautomation/playwright-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Playwright?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides