Browse Bridge is answering right now. Last checked 5 min ago. Last commit 29 Oct 2026.
Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
Today is the operative word: we check Browse Bridge every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.
claude mcp add browse-bridge --transport http https://mcp.browsebridge.com/mcp
https://mcp.browsebridge.com/mcp
[mcp_servers.browse-bridge]
url = "https://mcp.browsebridge.com/mcp"
{
"mcpServers": {
"browse-bridge": {
"url": "https://mcp.browsebridge.com/mcp"
}
}
}
{
"servers": {
"browse-bridge": {
"type": "http",
"url": "https://mcp.browsebridge.com/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.browsebridge.com/mcp | streamable-http | sign-in | 448 ms | 5 min ago |
Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
Launch, inspect, control, and share isolated cloud browsers for your agents.
Complete web tasks in the user's own Chrome via an observe-decide-act browser agent.
Use your existing Firefox and logged-in tabs, limited to tabs or groups you explicitly share.
Control existing signed-in Chrome and Edge tabs through a locally paired extension.
Let AI coding agents read pages through your real, logged-in Chrome browser.
Control a local headless Chrome browser: open pages, read titles, and take screenshots.
Let AI agents see, tap, type, scroll, screenshot and debug your Expo app on a real phone.
Answers built from our own checks of this server.