How to install nodriver — Chrome browser automation in Gemini CLI

Gemini CLI was replaced by Antigravity CLI in June 2026. On an enterprise licence or paid API key you can still install nodriver — Chrome browser automation by running "gemini mcp add nodriver-chrome-browser-automation uvx nodriver-mcp", then type /mcp to check it.

Built from the published package · server updated 5 days ago

Run the install command

In a terminal, run:

gemini mcp add nodriver-chrome-browser-automation uvx nodriver-mcp

2
Check it
Inside Gemini CLI, type /mcp to list servers and tools.

MCP servers run with your permissions. If nodriver — Chrome browser automation needs an API key, add it under env in the config. Check its README.

Install nodriver — Chrome browser automation in another app

Claude Code Claude Desktop Cursor VS Code Windsurf Codex Antigravity CLI ChatGPT

Similar servers

browser-use browser-use

100

Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.

AAA Local and remote 119k

Actionbook actionbook

Let your AI agent operate any website through a real, logged-in browser session.

AAA Remote 1.6k

Robin: AI-Powered Dark Web OSINTapurvsinghgautam

Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.

AAA Local 7.6k

Questions

Does nodriver — Chrome browser automation work in Gemini CLI?

Yes. Gemini CLI supports local and remote mcp servers, extensions (legacy), and nodriver — Chrome browser automation installs with the steps above.

nodriver — Chrome browser automation does not show up in Gemini CLI. What now?

Restart Gemini CLI fully, check the JSON is valid, and make sure uv (for uvx) is installed. See common MCP errors and fixes.

Is nodriver — Chrome browser automation safe?

It scores 54 of 100. Review the code before you install it, and only give it the access it needs. Grades and details.