B4n1Web runs on your own machine — the client starts it, so there is no endpoint to ping. 100 installs a week from npm. Last commit 27 Oct 2026.
Ultra-lightweight browser engine for AI agents. 33 MCP tools, 4 SDKs, cross-platform.
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
ProcessBuilder pb = new ProcessBuilder(cmd);
const version = execSync(`${binaryPath} --version`, { timeout: 5000 }).toString().trim();
const bundled = path.join(__dirname, '..', 'bin', binName);
subprocess.run(["chmod", "+x", str(binary_path)], check=True)
import select
deadline = time.monotonic() + self.timeout
$proc = proc_open($cmd, $spec, $pipes);
StartInfo = new ProcessStartInfo("chmod", $"+x {tempBinary}")
Open3.popen3(*argv, pgroup: true) do |pin, pout, perr, wait_thr|
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add b4n1web -- uvx b4n1-web
{
"mcpServers": {
"b4n1web": {
"command": "uvx",
"args": [
"b4n1-web"
]
}
}
}
[mcp_servers.b4n1web]
command = "uvx"
args = ["b4n1-web"]
{
"mcpServers": {
"b4n1web": {
"command": "uvx",
"args": [
"b4n1-web"
]
}
}
}
{
"servers": {
"b4n1web": {
"type": "stdio",
"command": "uvx",
"args": [
"b4n1-web"
]
}
}
}
Code-aware browser testing agent — 14 Playwright tools for AI code editors via MCP
Self-hosted stealth browser for AI agents: Firefox engine + Rust MCP runtime.
Local browser automation for AI agents: real-browser fetch, capture, smoke tests, cross-engine QA.
Local browser automation for AI agents: real-browser fetch, capture, smoke tests, cross-engine QA.
Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.
MCP server for Safari DevTools — browser debugging and automation for AI coding agents
Selenium MCP server for AI agents — 41 browser automation tools with snapshots and sessions.
OpenRouter for browser agents. One MCP to route browser tasks across 250+ runners.
Answers built from our own checks of this server.