MCP-Server-Playwright
The MCP-Server-Playwright enables browser automation for interacting with and extracting data from web pages through Playwright. With this server, you can:
Navigate to URLs: Load any web page by specifying its URL
Interact with elements: Click, hover, fill form fields, and select dropdown options using CSS selectors or text content
Capture screenshots: Take screenshots of entire pages or specific elements
Execute JavaScript: Run arbitrary code within the browser context
Monitor console logs: Access and retrieve browser console output
Perform comprehensive automation: Complete complex sequences of interactions in a real browser environment
Allows execution of JavaScript in the browser environment via the browser_evaluate tool
Supports macOS as a compatible operating system with specific configuration paths
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP-Server-Playwright take a screenshot of the homepage and show me the console logs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Table of Contents
Related MCP server: Playwright MCP Server for Security
Features
π Full browser automation capabilities
πΈ Screenshot capture of entire pages or specific elements
π±οΈ Comprehensive web interaction (navigation, clicking, form filling)
π Console log monitoring
π§ JavaScript execution in browser context
Installation
Installing via Smithery
To install MCP Server Playwright for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claudeYou can install the package using either npx or mcp-get:
Using npx:
npx @automatalabs/mcp-server-playwright installThis command will:
Check your operating system compatibility (Windows/macOS)
Create or update the Claude configuration file
Configure the Playwright server integration
The configuration file will be automatically created/updated at:
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Using mcp-get:
npx @michaellatman/mcp-get@latest install @automatalabs/mcp-server-playwrightConfiguration
The installation process will automatically add the following configuration to your Claude config file:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@automatalabs/mcp-server-playwright"]
}
}
}Using with Cursor
You can also use MCP Server Playwright with Cursor, an AI-powered code editor. To enable browser automation in Cursor via MCP:
Install Playwright browsers (if not already):
npx playwright installInstall MCP Server Playwright for Cursor using Smithery:
npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client cursorConfiguration file setup:
If you do not use Claude, the configuration file (claude_desktop_config.json) may not be created automatically.On Windows, create a folder named
Claudein%APPDATA%(usuallyC:\Users\<YourName>\AppData\Roaming\Claude).Inside that folder, create a file named
claude_desktop_config.jsonwith the following content:
{ "serverPort": 3456 }Follow the remaining steps in the Installation section above to complete the setup.
Now, you can use all the browser automation tools provided by MCP Server Playwright directly from Cursorβs AI features, such as web navigation, screenshot capture, and JavaScript execution.
Note: Make sure you have Node.js installed and
npxavailable in your system PATH.
Components
Tools
browser_navigate
Navigate to any URL in the browser
{
"url": "https://stealthbrowser.cloud"
}browser_screenshot
Capture screenshots of the entire page or specific elements
{
"name": "screenshot-name", // required
"selector": "#element-id", // optional
"fullPage": true // optional, default: false
}browser_click
Click elements on the page using CSS selector
{
"selector": "#button-id"
}browser_click_text
Click elements on the page by their text content
{
"text": "Click me"
}browser_hover
Hover over elements on the page using CSS selector
{
"selector": "#menu-item"
}browser_hover_text
Hover over elements on the page by their text content
{
"text": "Hover me"
}browser_fill
Fill out input fields
{
"selector": "#input-field",
"value": "Hello World"
}browser_select
Select an option in a SELECT element using CSS selector
{
"selector": "#dropdown",
"value": "option-value"
}browser_select_text
Select an option in a SELECT element by its text content
{
"text": "Choose me",
"value": "option-value"
}browser_evaluate
Execute JavaScript in the browser console
{
"script": "document.title"
}Resources
Console Logs (
console://logs)Access browser console output in text format
Includes all console messages from the browser
Screenshots (
screenshot://<n>)Access PNG images of captured screenshots
Referenced by the name specified during capture
License
This project is licensed under the MIT License - see the LICENSE file for details.
Available Tools
10 toolsbrowser_clickB
Click an element on the page using CSS selector
Inputs: selector (required).
browser_click_textB
Click an element on the page by its text content
Inputs: text (required).
browser_evaluateC
Execute JavaScript in the browser console
Inputs: script (required).
browser_fillB
Fill out an input field
Inputs: selector (required), value (required).
browser_hoverA
Hover an element on the page using CSS selector
Inputs: selector (required).
browser_hover_textB
Hover an element on the page by its text content
Inputs: text (required).
browser_screenshotB
Take a screenshot of the current page or a specific element
Inputs: name (required), selector, fullPage.
browser_selectC
Select an element on the page with Select tag using CSS selector
Inputs: selector (required), value (required).
browser_select_textC
Select an element on the page with Select tag by its text content
Inputs: text (required), value (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose. Pairwise similar tools like click and click_text are differentiated by CSS selector vs text content, making ambiguity minimal.
All tools follow a consistent 'browser_verb' pattern, with optional '_text' suffix for text-based selectors. Snake_case is used uniformly.
10 tools is an appropriate number for browser automation, covering essential actions without being overwhelming. The scope is well-defined.
The set covers core browser interactions (navigation, click, fill, select, hover, evaluate, screenshot). Missing operations like waiting, scrolling, or keyboard input are minor gaps.
Maintenance
Related MCP Connectors
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to iβ¦
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables LLMs to perform web browsing tasks, take screenshots, and execute JavaScript using Puppeteer for browser automation.41MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to perform browser automation tasks including web scraping, taking screenshots, and executing JavaScript using Playwright. It facilitates real-time interaction with web pages and the generation of automated test code.23 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to drive a real browser for web scraping, page interaction, screenshots, JavaScript execution, automated test generation, and responsive device emulation through natural language tool calls.13,875 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to control a browser through tools for web automation, including navigation, typing, clicking, and taking screenshots.Apache 2.0