Full-page browser screenshots, from the command line or from your own code, with the pixels, the text, and the HTML all handed back together.
Brosh mcp server connects Brosh to AI assistants that speak the Model Context Protocol. Full-page browser screenshots, from the command line or from your own code, with the pixels, the text, and the HTML all handed back together.
Full-page browser screenshots, from the command line or from your own code, with the pixels, the text, and the HTML all handed back together.
The server is distributed via PyPI as brosh, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Browser automation servers are the ones people reach for when a site has no API — the assistant drives a real page instead of guessing at endpoints. Brosh sits in that group. Worth comparing against the other browser automation servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
{
"mcpServers": {
"brosh": {
"command": "uvx",
"args": ["brosh"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.