Playwright Server
Supports targeting elements on web pages using CSS selectors for operations like clicking, filling forms, taking screenshots, and extracting content
Allows execution of JavaScript code in the browser context through the playwright_evaluate tool, enabling manipulation of web page content and behavior
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 Server take a screenshot of the login button on example.com"
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-server MCP server
\A MCP server with playwright tools\
Components
Resources
The server implements a simple note storage system with:
Custom note:// URI scheme for accessing individual notes
Each note resource has a name, description and text/plain mimetype
Prompts
The server provides a single prompt:
summarize-notes: Creates summaries of all stored notes
Optional "style" argument to control detail level (brief/detailed)
Generates prompt combining all current notes with style preference
Tools
The server implements the following tools:
playwright_navigate: Navigates to a specified URL. This operation will automatically create a new session if there is no active session.Requires a
urlargument (string).
playwright_screenshot: Takes a screenshot of the current page or a specific element.Requires a
nameargument (string) for the screenshot file name.Optional
selectorargument (string) to specify a CSS selector for the element to screenshot. If no selector is provided, a full-page screenshot is taken.
playwright_click: Clicks an element on the page using a CSS selector.Requires a
selectorargument (string) to specify the CSS selector for the element to click.
playwright_fill: Fills out an input field.Requires a
selectorargument (string) to specify the CSS selector for the input field.Requires a
valueargument (string) to specify the value to fill.
playwright_evaluate: Executes JavaScript code in the browser console.Requires a
scriptargument (string) to specify the JavaScript code to execute.
playwright_click_text: Clicks an element on the page by its text content.Requires a
textargument (string) to specify the text content of the element to click.
playwright_get_text_content: Get the text content of all visiable elements.playwright_get_html_content: Get the HTML content of the page.Requires a
selectorargument (string) to specify the CSS selector for the element.
Related MCP server: Playwright MCP
Configuration
[TODO: Add configuration details specific to your implementation]
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development
Building and Publishing
To prepare the package for distribution:
Sync dependencies and update lockfile:
uv syncBuild package distributions:
uv buildThis will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
uv publishNote: You'll need to set PyPI credentials via environment variables or command flags:
Token:
--tokenorUV_PUBLISH_TOKENOr username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory C:\Users\YUNYING\Documents\project\python\mcp\playwright-server run playwright-serverUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Available Tools
8 toolsplaywright_clickC
Click an element on the page using CSS selector
Inputs: selector (required).
playwright_click_textB
Click an element on the page by its text content
Inputs: text (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_get_html_contentC
Get the HTML content of the page
Inputs: selector (required).
playwright_get_text_contentB
Get the text content of all elements
Inputs: no named parameters.
playwright_screenshotC
Take a screenshot of the current page or a specific element
Inputs: name (required), selector.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose with no ambiguity. For example, playwright_click targets elements by CSS selector while playwright_click_text uses text content, and tools like playwright_get_html_content versus playwright_get_text_content provide different types of content retrieval. The descriptions clearly differentiate the specific actions each tool performs.
All tools follow a consistent 'playwright_verb' pattern with snake_case throughout. The naming is perfectly predictable, starting with 'playwright_' followed by an action verb that accurately describes the tool's function, such as 'click', 'evaluate', 'fill', or 'navigate'.
With 8 tools, this server is well-scoped for browser automation tasks. Each tool earns its place by covering essential operations like navigation, interaction (clicking, filling), content retrieval (HTML, text), and utilities (screenshot, JavaScript execution). This count is ideal for the domain without being overwhelming or insufficient.
The toolset covers core browser automation workflows effectively, including navigation, element interaction, content extraction, and screenshots. Minor gaps exist, such as no explicit tool for waiting or handling alerts, but agents can work around these using existing tools like playwright_evaluate for JavaScript-based solutions. The surface is largely complete for the stated purpose.
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)
Related MCP Servers
- AlicenseBqualityCmaintenanceAn MCP server that retrieves web page content using Playwright headless browser, capable of extracting main content and converting to Markdown format.36,302 npm1,088MIT
- FlicenseBqualityDmaintenancePlaywright wrapper for MCP that enables LLM-powered clients to control a browser for automation tasks.101-
- AlicenseBqualityDmaintenanceA browser automation server providing Playwright capabilities for controlling web browsers, capturing screenshots, extracting content, and performing complex interactions through an MCP interface.6Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA service that provides Playwright browser automation functionality through Model Context Protocol (MCP), allowing clients to use Playwright features via SSE connections.7ISC