mcpbeat Sign in

Browz MCP Server

answering

Browz is answering right now. Last checked 15 min ago.

The most secure anti-detect browser, for people and AI agents: drive isolated browser profiles

Uptime history 17 hours of history
17 hours agonow
100.0%
Uptime 24h
62 of 62 checks
—
Tools
hidden behind auth
1016 ms
Response time
average over 24h
OAuth sign-in
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Browz every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.

run in your terminal
claude mcp add browz --transport http https://mcp.gobrowz.com/mcp
Settings → Connectors → Add custom connector, then paste this address
https://mcp.gobrowz.com/mcp
~/.codex/config.toml
[mcp_servers.browz]
url = "https://mcp.gobrowz.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "browz": {
      "url": "https://mcp.gobrowz.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "browz": {
      "type": "http",
      "url": "https://mcp.gobrowz.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.

Endpoints

URLTransportStateLatencyChecked
https://mcp.gobrowz.com/mcp streamable-http sign-in 1065 ms 15 min ago

Alternatives to Browz

same job, measured the same way
Argus
by pochtmanr

Drive Argus anti-detect browser profiles: isolated identities with their own fingerprint and proxy.

local only
NextCore Browser
by homestaynextcore

Multi-profile browser: AI agents create, open and drive isolated signed-in profiles with own proxy

local only
ZennoBrowser MCP Server
by zennolab

MCP server for ZennoBrowser antidetect browser: manage browser profiles from AI agents

81 installs/wk local only
Nullprint
by nullprintai

Create, launch, check and drive Nullprint AI antidetect browser profiles from any MCP agent.

679 installs/wk local only
Tabfleet
by tabfleet

Launch, inspect, control, and share isolated cloud browsers for your agents.

answering
oassis — web for agents
by oassis

Read, map and crawl the web, and drive a real browser. Pay per call, no key, no signup.

14 tools answering
Veilus
by veilus

Drive Veilus browser profiles from an AI assistant: profiles, pages, scripts, schedules.

47 installs/wk local only
Devloop
by vincentvella

Browser + dev-server logs on one correlated timeline, for Claude Code and AI agents.

156 installs/wk local only

Browz — questions

Answers built from our own checks of this server.

Why is there no tool list for Browz?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is Browz working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 62 of 62 checks got a reply (100.0%), average response time 1016 ms. The bar chart above shows every period we have measured.
How do I connect Browz?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to Browz?
No API key is involved. Browz answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is Browz?
It answers our handshake in 1016 ms on average, which is faster than 5% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.