Playwright MCP
Control a browser for automation and web scraping tasks using Playwright.
playwright-mcp
Playwright wrapper for MCP (Model Context Protocol). This server enables LLM-powered clients to control a browser for automation tasks.
Components
Resources
The server exposes resources for accessing browser screenshots:
- Screenshot resource URI:
screenshot://{page_id} - Screenshot resources are automatically available for all open pages
Prompts
The server provides a prompt to help clients interpret web pages:
interpret-page: Analyzes the current web page content and structure- Optional
page_idargument to select which page to interpret - Optional
focusargument to focus on specific aspects (full, forms, navigation, text) - Returns both text analysis and a screenshot of the page
- Optional
Tools
The server implements a comprehensive set of browser automation tools:
-
Browser navigation
navigate: Go to a specific URLnew_page: Create a new browser page with a specific IDswitch_page: Switch to a different browser pageget_pages: List all available browser pages
-
Page interaction
click: Click on an element using CSS selectortype: Type text into an input elementwait_for_selector: Wait for an element to appear on the page
-
Content extraction
get_text: Get text content from an elementget_page_content: Get the entire page HTMLtake_screenshot: Capture visual state of the page or element
Configuration
Install Dependencies
uv add playwright
playwright install chromium
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration
"mcpServers": {
"playwright-mcp": {
"command": "uv",
"args": [
"--directory",
"/Users/shannon/Workspace/artivus/playwright-mcp",
"run",
"playwright-mcp"
]
}
}
Published Servers Configuration
"mcpServers": {
"playwright-mcp": {
"command": "uvx",
"args": [
"playwright-mcp"
]
}
}
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or 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 /Users/shannon/Workspace/artivus/playwright-mcp run playwright-mcp
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
相关服务器
Bright Data
赞助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Redbook Search & Comment Tool
An automated tool to search notes, analyze content, and post AI-generated comments on Xiaohongshu (Redbook) using Playwright.
CarDeals-MCP
A Model Context Protocol (MCP) service that indexes and queries car-deal contexts - fast, flexible search for vehicle listings and marketplace data.
Web Scout
An MCP server for web search and content extraction using DuckDuckGo.
MCP LLMS.txt Explorer
Explore and analyze websites that have implemented the llms.txt standard.
Read URL MCP
Extracts web content from a URL and converts it to clean Markdown format.
ScrapeBadger
Access Twitter/X data including user profiles, tweets, followers, trends, lists, and communities via the ScrapeBadger API.
Xiaohongshu Search & Comment
An automated tool to search notes, retrieve content, and post comments on Xiaohongshu (RedBook) using Playwright.
SABIS MCP Server
Access academic grades from the Sakarya University SABIS system via automated web scraping.
MCP Browser Console Capture Service
A browser automation service for capturing console output, useful for tasks like public sentiment analysis.
Jina Reader
Fetch the content of a remote URL as Markdown with Jina Reader.