How do I start Chrome for this server?
On macOS, run `open -a "Google Chrome" --args --remote-debugging-port=9222`. The server expects Chrome to be launched manually with the debugging port.
@ratiofu
Basic information
A simple MCP server for controlling Chrome via Puppeteer
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"puppeteer-control": {
"type": "http",
"url": "http://localhost:7742/sse"
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list directly from this server's endpoint using the button above.
This MCP server connects to a running Chrome instance through its remote debugging port using Puppeteer Core. It acts as a bridge between MCP clients (like Cursor) and Chrome, allowing programmatic control via the Model Context Protocol.
First, start Chrome with the remote debugging port enabled (e.g., --remote-debugging-port=9222). Then install dependencies with pnpm i and run the server with pnpm run start. Finally, configure Cursor to add a global MCP server pointing to http://localhost:7742/sse.
puppeteer-core (no bundled browser)On macOS, run `open -a "Google Chrome" --args --remote-debugging-port=9222`. The server expects Chrome to be launched manually with the debugging port.
The project uses `puppeteer-core` and does not install a browser. You need Node.js, pnpm, and a Chrome/Chromium installation.
In Cursor’s MCP settings, add a new global MCP server with the URL `http://localhost:7742/sse`. The server must be running locally.
The README explains that Cursor requires SSE support. The TypeScript SDK’s Streamable HTTP example is not compatible; SSE is better documented in the official MCP documentation.
Yes, you can use the MCP Inspector. With the server already running on SSE, run `pnpx @modelcontextprotocol/inspector` to explore available tools.

Parse allows your agent to access thousands of APIs instantly. You can use Parse to build an API for any action on any website and edit any previously existing API in our catalogue.
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

MCP server for managing Gologin browser profiles, proxies, fingerprints and cloud browser sessions through AI conversations
DOM-first AI browser automation for Chrome and MCP clients.
Capture screenshots of webpages as images or PDFs with Screenshot Scout.
Comments