Log inSubmit server
Playwright MCP Server logo

Playwright MCP Server

by executeautomation

Automates real browsers with Playwright for page interaction, screenshots, JavaScript execution, scraping, and test-code generation.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Playwright MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "executeautomation-playwright-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@executeautomation/playwright-mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 33 tools correctly (1mo ago).

Overview

The executeautomation/playwright-mcp-server MCP server exposes Playwright browser automation to MCP-compatible clients. It can interact with web pages, capture screenshots, execute JavaScript, scrape page content, and generate test code in a real browser environment. Browser binaries are installed automatically when needed, with optional manual installation for Chromium, Firefox, or WebKit. Reach for it when an agent needs browser-based testing, inspection, or web data collection, including device-emulation scenarios.

Use cases

  • Automate browser-based website checks
  • Scrape content from rendered web pages
  • Capture screenshots during agent workflows
  • Generate Playwright test code
  • Validate responsive layouts on device profiles

Key features

  • Playwright browser automation
  • Screenshot capture
  • JavaScript execution
  • Web scraping
  • Test-code generation
  • 143 device-emulation presets

Tools33

What Playwright MCP Server lets your agent do. Expand a tool for its parameters.

Verified live~3.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

29/29 checks healthy over the last 77d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · @executeautomation/playwright-mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars5.7kStargazers on the source repository.
npm downloads163kPackage downloads in the last 30 days.
Last commit10mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed33Callable tools this server registers over MCP.
Directory activity6 viewsConfig copies, upvotes, and views on AllMCPs.

How Playwright MCP Server works

What executeautomation/playwright-mcp-server does

The executeautomation/playwright-mcp-server MCP server gives an MCP client access to browser automation through Playwright. It operates in a real browser environment and supports page interaction, screenshots, JavaScript execution, web scraping, and test-code generation. This makes it suitable for agent-assisted website checks, extracting information from rendered pages, and investigating browser behavior.

The server also supports device emulation. Its documented device profiles include 143 presets covering iPhone, iPad, Pixel, Galaxy, and desktop browsers. A client can request a profile such as iPhone 13, iPad Pro 11, or Desktop Chrome, and can specify orientation where supported by the command. Emulation includes the device viewport, user agent, touch behavior, and device pixel ratio.

How it works

The executeautomation/playwright-mcp-server MCP server can communicate over standard input/output or HTTP. Stdio is the recommended transport for Claude Desktop and uses the package command as the MCP process. HTTP mode runs the server as a standalone service and exposes MCP endpoints, including /mcp, along with SSE, message, and health-check routes. The HTTP server uses port 8931 in the documented example, although another port can be supplied.

HTTP mode is intended for setups such as VS Code GitHub Copilot, custom MCP clients, background services, remote deployments, and multiple-client access. Clients connecting through HTTP must identify the connection type as http; omitting that setting causes the connection to fail. The server also includes monitoring on a dynamically allocated port, whose value is shown in the console.

Setup and configuration

Install the package globally with npm, run it through npx, use mcp-get or Smithery, or add it through the Claude Code and VS Code commands documented by the project. A Claude Desktop stdio configuration runs npx -y @executeautomation/playwright-mcp-server.

Browser binaries are downloaded automatically the first time a missing browser is required. Manual installation is also available with Playwright commands for all browsers or for a selected browser. In stdio mode, logs are written to ~/playwright-mcp-server.log rather than the console to preserve JSON-RPC communication.

Tools and capabilities

The executeautomation/playwright-mcp-server MCP server supports capabilities for:

  • Interacting with web pages in a browser
  • Taking screenshots
  • Executing JavaScript in the browser context
  • Scraping page content
  • Generating browser test code
  • Resizing or emulating supported device profiles

The documented resize capability accepts a device preset and can use an orientation such as landscape. This supports checking responsive layouts across mobile, tablet, and desktop profiles.

Limitations and notes

Claude Desktop currently requires stdio configuration, so HTTP mode is not the appropriate transport for that client. HTTP deployments need a client that supports the server’s HTTP or SSE configuration. Browser installation may download substantial browser binaries, and the server stores them in Playwright’s standard cache locations unless the environment changes that behavior.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Playwright MCP Server

Install it with npm, run it with npx, use mcp-get or Smithery, or add it through the documented Claude Code and VS Code commands.

Yes. Claude Desktop should use the documented stdio configuration; HTTP mode is not currently supported there.

Yes. When a required browser is missing, the server automatically downloads and installs it. You can also run Playwright’s manual installation commands.

Yes. It documents 143 device presets, including iPhone, iPad, Pixel, Galaxy, and desktop profiles, with viewport, user-agent, touch, and device-pixel-ratio emulation.

Yes. Start it as a standalone HTTP server and configure the client with the MCP URL and a required `type` value of `http`.

Related MCP servers

All in Browser Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPlaywright MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/executeautomation-playwright-mcp-server?style=directory)](https://allmcps.com/mcp/executeautomation-playwright-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/executeautomation-playwright-mcp-server"><img src="https://allmcps.com/api/badge/executeautomation-playwright-mcp-server?style=directory" alt="Playwright MCP Server on AllMCPs" /></a>