
Playwright MCP
The Playwright MCP is a powerful MCP server that gives an AI agent control over a web browser. This server enables LLMs to interact with web pages.
On this page
About Playwright MCP
Playwright MCP
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.
Key Features
- Fast and lightweight. Uses Playwright's accessibility tree, not pixel-based input.
- LLM-friendly. No vision models needed, operates purely on structured data.
- Deterministic tool application. Avoids ambiguity common with screenshot-based approaches.
Requirements
- Node.js 18 or newer
- VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client
Getting started
First, install the Playwright MCP server with your client.
Standard config works in most of the tools:
{ "mcpServers": { "playwright": { "command": "npx", "args": [ "@playwright/mcp@latest" ] } } } Are you the owner of Playwright MCP?
Claim this listing to update it, get a Verified badge and reach more QA teams.
Playwright MCP alternatives

Shiplight AI
NewAI-powered E2E testing platform that automatically generates, runs, and maintains tests. Shiplight helps teams catch bugs early without flaky tests or manual maintenance.
Paid (with free trial)
Pie
NewPie is an agentic testing platform for web, iOS and Android apps. It tests your pull requests like a real user.
Paid (no free trial)Test Collab is AI-powered test management with QA Copilot that generates test cases from screenshots or requirements—and converts plain-English tests into executable automation code. Review and approve proposals, then track results with full evidence on every run.
Paid (with free trial)BroserStack MCP allows you to manage test cases, execute manual or automated tests, debug issues, and even fix code—directly within tools like Cursor, Claude, or any MCP-enabled client, using plain English.
Open-source
Testsy
NewTestsy runs plain-language QA tests in a real Chrome browser and on iPhone, iPad and Android, and returns a pass or fail verdict with video proof and a fix prompt. QA teams run it from CI, the CLI or the API; AI coding agents call it over MCP. Get your first 10 tests free, no card needed.
Paid (with free trial)
Rill
NewRill helps developers and QA teams record browser flows, investigate bugs, and review AI-agent work with replayable video and captured console and network details. Record a Chrome tab or your coding agent, or describe a task for Rill to run in a hosted browser.
Freemium


