MCP Server Playwright is a powerful Model Context Protocol server that allows large language models to interact with web browsers through Playwright. It enables LLMs to navigate websites, take screenshots, fill forms, and execute JavaScript in a real browser environment - essentially giving AI models the ability to use the web like a human.
The simplest way to install MCP Server Playwright for Claude Desktop is via Smithery:
npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude
You can also install using npx directly:
npx @automatalabs/mcp-server-playwright install
This automated installation process will:
The configuration file will be placed at:
%APPDATA%\Claude\claude_desktop_config.json
~/Library/Application Support/Claude/claude_desktop_config.json
Alternative installation using mcp-get:
npx @michaellatman/mcp-get@latest install @automatalabs/mcp-server-playwright
During installation, the following configuration is automatically added to your Claude config file:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@automatalabs/mcp-server-playwright"]
}
}
}
Navigate to any URL:
{
"url": "https://stealthbrowser.cloud"
}
Click elements using CSS selectors:
{
"selector": "#button-id"
}
Click elements by their text content:
{
"text": "Click me"
}
Hover over elements using CSS selectors:
{
"selector": "#menu-item"
}
Hover over elements by their text content:
{
"text": "Hover me"
}
Fill input fields with text:
{
"selector": "#input-field",
"value": "Hello World"
}
Select an option in a dropdown using CSS selector:
{
"selector": "#dropdown",
"value": "option-value"
}
Select an option in a dropdown by its text content:
{
"text": "Choose me",
"value": "option-value"
}
Capture entire pages or specific elements:
{
"name": "screenshot-name", // required
"selector": "#element-id", // optional
"fullPage": true // optional, default: false
}
Run JavaScript code in the browser context:
{
"script": "document.title"
}
Access browser console output through console://logs
which provides all console messages from the browser in text format.
Access captured screenshots through screenshot://<name>
where <name>
is the name specified during capture. These are available as PNG images.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.