Home › Browser Automation & Scraping › nodriver — Chrome browser automation
nodriver — Chrome browser automation
Chrome automation via nodriver: 70 tools, isolated browsers, profiles and configurable startup.
Topics: Browser Automation
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (pypi 2.6.1)
uvx nodriver-mcp
Or add to your MCP client config:
{
"mcpServers": {
"nodriver-mcp-server": {
"command": "uvx",
"args": [
"nodriver-mcp"
]
}
}
}
NODRIVER_HEADLESS— Run Chrome headless (true/false). Default false.NODRIVER_USER_DATA_DIR— Explicit persistent Chrome profile directory. Default: an ephemeral temp profile, auto-deleted per session.NODRIVER_BROWSER_PATH— Path to the Chrome/Chromium executable. Auto-detected when unset.NODRIVER_PROXY— Proxy server address passed to Chrome as --proxy-server.
Related servers
browser
Headless browser for AI and web automation with a built-in MCP server.
playwright-mcp
Playwright Tools for MCP
SeleniumBase MCP
Stealthy browser automation, testing, and web-scraping via CDP Mode.
Firecrawl MCP Server
Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
browsermcp/mcp
Automate your local Chrome browser.
mcp-playwright
Browser automation and web scraping using Playwright.
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry