README.md
Cloud-based browser automation for LLMs
BrowserCat MCP Server
A Model Context Protocol server that provides browser automation capabilities using BrowserCat's cloud browser service. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment without needing to install browsers locally.
Components
Tools
- browsercat_navigate
- Navigate to any URL in the browser
- Input:
url(string)
- browsercat_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
- browsercat_click
- Click elements on the page
- Input:
selector(string): CSS selector for element to click
- browsercat_hover
- Hover elements on the page
- Input:
selector(string): CSS selector for element to hover
- browsercat_fill
- Fill out input fields
- Inputs:
selector(string): CSS selector for input fieldvalue(string): Value to fill
- browsercat_select
- Select an option from a dropdown menu
- Inputs:
selector(string): CSS selector for select elementvalue(string): Value to select
- browsercat_evaluate
- Execute JavaScript in the browser console
- Input:
script(string): JavaScript code to execute
Resources
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
Key Features
- Cloud-based browser automation
- No local browser installation required
- Console log monitoring
- Screenshot capabilities
- JavaScript execution
- Basic web interaction (navigation, clicking, form filling)
Configuration to use BrowserCat MCP Server
Environment Variables
The BrowserCat MCP server requires the following environment variable:
BROWSERCAT_API_KEY: Your BrowserCat API key (required). You can get one for free at https://browsercat.xyz/mcp.
NPX Configuration
{
"mcpServers": {
"browsercat": {
"command": "npx",
"args": ["-y", "@browsercatco/mcp-server"],
"env": {
"BROWSERCAT_API_KEY": "your-api-key-here"
}
}
}
}
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Tools (7)
browsercat_navigateNavigate to any URL in the browserbrowsercat_screenshotCapture screenshots of the entire page or specific elementsbrowsercat_clickClick elements on the pagebrowsercat_hoverHover elements on the pagebrowsercat_fillFill out input fieldsbrowsercat_selectSelect an option from a dropdown menubrowsercat_evaluateExecute JavaScript in the browser consoleEnvironment Variables
BROWSERCAT_API_KEYrequiredYour BrowserCat API keyConfiguration
claude_desktop_config.json
{"mcpServers": {"browsercat": {"command": "npx", "args": ["-y", "@browsercatco/mcp-server"], "env": {"BROWSERCAT_API_KEY": "your-api-key-here"}}}}Try it
→Navigate to https://example.com and take a full-page screenshot named 'homepage'.
→Fill out the search input field with selector '#search-box' with the value 'MCP servers' and click the submit button.
→Execute JavaScript to extract all link URLs from the current page.
→Hover over the navigation menu element with selector '.nav-menu' and capture a screenshot of the result.