MCP servers / sitelooper
sitelooper
active io.github.restspace/sitelooper
Record a browser flow once with a model, then compile it to a Playwright spec that needs no model.
Downloads, last 30 days
Install
Run it directly:
npx -y sitelooperOr add it to your client config (Claude Desktop claude_desktop_config.json, Cursor .cursor/mcp.json):
{
"mcpServers": {
"sitelooper": {
"command": "npx",
"args": [
"-y",
"sitelooper"
]
}
}
}Generated from the package metadata in the official MCP Registry. MCP Morning does not run or test servers; check required environment variables in the project README.
Alternatives
4
Scrapling MCP Server
254.0k/wkWeb scraping with stealth HTTP, real browsers, and Cloudflare bypass.…