Browser Automation for AI Assistants
Control Chrome directly through JSON-RPC and MCP for seamless AI-driven browser automation
Control Chrome directly through JSON-RPC and MCP for seamless AI-driven browser automation
Designed specifically for AI assistants with token-efficient responses and structured data extraction.
Option to run in windowed mode for users to see AI actions in real-time with screenshot capabilities.
Stealth features to navigate modern websites without being detected as an automated system.
Support for user profiles to maintain login sessions and cookies between runs.
Execute multiple browser operations in a single request for efficient automation.
Extract only relevant elements and attributes from pages for focused data processing.
# Install globally
npm install -g mcp-chrome-control
# Or use without installation via npx
npx mcp-chrome-control// Add to your .mcp.json file:
{
"chrome": {
"type": "stdio",
"command": "npx",
"args": ["mcp-chrome-control"],
"env": {}
}
}import { ChromeControlClient } from 'mcp-chrome-control/client';
async function runDemo() {
const client = new ChromeControlClient();
await client.start();
// Create a browser (visible to user)
const browserId = await client.createBrowser({
headless: false
});
// Navigate and interact
await client.navigate('https://example.com', browserId);
await client.screenshot(browserId, {
path: 'screenshot.png'
});
// Clean up
await client.closeBrowser(browserId);
await client.stop();
}Comprehensive guides, API reference, and tutorials for using Chrome Control.
View DocumentationBrowse example scripts for common automation tasks and AI integrations.
View ExamplesDetailed reference of all available tools, methods, and parameters.
View API ReferenceStart using Chrome Control today to enable your AI assistants to interact with the web.
Get Started