Playwright MCP Server
The Playwright MCP Server is a browser automation tool that enables programmatic interaction with web pages. With this server, you can:
Navigate to URLs: Browse to specific web addresses
Take Screenshots: Capture images of pages or specific elements
Click Elements: Interact with page elements using CSS selectors
Fill Input Fields: Enter text into forms
Select Options: Choose items from dropdown menus
Hover Elements: Trigger hover events on specific elements
Execute JavaScript: Run custom JS code in the browser console
Perform HTTP Requests: Make GET, POST, PUT, PATCH, and DELETE requests
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., "@Playwright MCP Server take a screenshot of the GitHub homepage"
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.
Playwright MCP Server
A Model Context Protocol server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.
Screenshot

Related MCP server: Playwright MCP Server
Documentation | API reference
Installation
You can install the package using either npm, mcp-get, or Smithery:
Using npm:
npm install -g @executeautomation/playwright-mcp-serverUsing mcp-get:
npx @michaellatman/mcp-get@latest install @executeautomation/playwright-mcp-serverUsing Smithery
To install Playwright MCP for Claude Desktop automatically via Smithery:
npx @smithery/cli install @executeautomation/playwright-mcp-server --client claudeConfiguration to use Playwright Server
Here's the Claude Desktop configuration to use the Playwright server:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@executeautomation/playwright-mcp-server"]
}
}
}Available Tools
12 toolsplaywright_clickC
Click an element on the page
Inputs: selector (required).
playwright_deleteC
Perform an HTTP DELETE request
Inputs: url (required).
playwright_evaluateC
Execute JavaScript in the browser console
Inputs: script (required).
playwright_fillC
fill out an input field
Inputs: selector (required), value (required).
playwright_getC
Perform an HTTP GET request
Inputs: url (required).
playwright_hoverC
Hover an element on the page
Inputs: selector (required).
playwright_patchC
Perform an HTTP PATCH request
Inputs: url (required), value (required).
playwright_postC
Perform an HTTP POST request
Inputs: url (required), value (required).
playwright_putC
Perform an HTTP PUT request
Inputs: url (required), value (required).
playwright_screenshotC
Take a screenshot of the current page or a specific element
Inputs: name (required), downloadsDir, height, savePng, +3 more.
playwright_selectC
Select an element on the page with Select tag
Inputs: selector (required), value (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 12 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools cleanly separate into three categories: HTTP methods (GET, POST, PUT, PATCH, DELETE), browser interaction (click, fill, hover, navigate, screenshot, select), and JavaScript execution (evaluate). There is no overlap between these functional areas.
All tools follow a perfect 'playwright_verb' naming pattern with consistent snake_case throughout. The verb choices are precise and descriptive (click, fill, hover, navigate, evaluate, screenshot, select, get, post, put, patch, delete), creating a highly predictable and readable naming convention.
12 tools is well-scoped for a Playwright automation server. The count provides comprehensive coverage of core browser automation and HTTP testing capabilities without being overwhelming. Each tool clearly earns its place in the toolkit.
The tool surface is nearly complete for browser automation and HTTP testing. It covers navigation, interaction, JavaScript execution, screenshots, and full HTTP method support. Minor gaps might include waiting/retry mechanisms or file upload/download operations, but core workflows are well covered.
Related MCP Connectors
Playwright browser automation ā navigate, click, fill forms, extract, screenshot ā 17 agent tools.
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to iā¦
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.19Apache 2.0
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, scrape web content, and execute JavaScript in real browser environments.3115,256 npmMIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, scrape web content, and execute JavaScript in a real browser environment.3215,256 npmMIT
- AlicenseAqualityDmaintenanceA server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or vision models.221Apache 2.0