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.
Clone the repository
git clone https://github.com/executeautomation/mcp-playwright.git
Build the code First run npm install
npm install
Then run build and link
npm run build
npm link
Here's the Claude Desktop configuration to use the Playwright server:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@executeautomation/playwright-mcp-server"]
}
}
}
-
playwright_navigate
- Navigate to any URL in the browser
- Input:
url
(string)
-
playwright_screenshot
- Capture screenshots of the entire page or specific elements
- Inputs:
name
(string, required): Name for the screenshotselector
(string, optional): CSS selector for element to screenshotwidth
(number, optional, default: 800): Screenshot widthheight
(number, optional, default: 600): Screenshot height
-
playwright_click
- Click elements on the page
- Input:
selector
(string): CSS selector for element to click
-
playwright_hover
- Hover elements on the page
- Input:
selector
(string): CSS selector for element to hover
-
playwright_fill
- Fill out input fields
- Inputs:
selector
(string): CSS selector for input fieldvalue
(string): Value to fill
-
playwright_select
- Select an element with SELECT tag
- Inputs:
selector
(string): CSS selector for element to selectvalue
(string): Value to select
-
playwright_evaluate
- Execute JavaScript in the browser console
- Input:
script
(string): JavaScript code to execute
The server provides access to two types of resources:
-
Console Logs (
console://logs
)- Browser console output in text format
- Includes all console messages from the browser
-
Screenshots (
screenshot://<name>
)- PNG images of captured screenshots
- Accessible via the screenshot name specified during capture
- Browser automation
- Console log monitoring
- Screenshot capabilities
- JavaScript execution
- Basic web interaction (navigation, clicking, form filling)