@browsercloud/mcp-server-cloudbrowser-playwright
v1.0.2
Published
MCP server for browser automation using cloudbrowser
Readme
Cloud browser MCP Server
Test
- Run
npm installto install the necessary dependencies, then runnpm run buildto getdist/index.js. - Run
npm run inspectorto start the server.
Get Started
Run
npm installto install the necessary dependencies, then runnpm run buildto getdist/index.js.Set up your Claude Desktop configuration to use the server.
{
"mcpServers": {
"cloudbrowser": {
"command": "node",
"args": ["path/to/mcp-server-cloudbrowser/cloudbrowser_playwright/dist/index.js"],
"env": {
"API_KEY": "<YOUR_BROWSERBASE_API_KEY>"
},
"transportType": "stdio"
}
}
}Restart your Claude Desktop app and you should see the tools available clicking the 🔨 icon.
Start using the tools! Below is an image of Claude closing a browser session.
Using npm
{
"mcpServers": {
"cloudbrowser": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"@browsercloud/mcp-server-cloudbrowser-playwright"
],
"env": {
"API_KEY": "<YOUR_BROWSERBASE_API_KEY>"
},
"transportType": "stdio"
}
}
}Tools
Browserbase API
cloudbrowser_navigate
- Navigate to any URL in the browser
- Input:
url(string)
cloudbrowser_evaluate
- Execute JavaScript in the browser console
- Input:
script(string): JavaScript code to execute
cloudbrowser_get_current_url
- Retrieve the current URL of the browser page
cloudbrowser_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
cloudbrowser_click
- Click elements on the page
- Input:
selector(string): CSS selector for element to click
cloudbrowser_fill
- Fill out input fields
- Inputs:
selector(string): CSS selector for input fieldvalue(string): Value to fill
cloudbrowser_get_text
- Extract all content from the current page
- Input:
selector(string, optional): CSS selector to get content from specific elements
Resources
The server provides access to two types of resources:
- Screenshots (
screenshot://<name>)- PNG images of captured screenshots
- Accessible via the screenshot name specified during capture
