Weboperator runs on your own machine — the client starts it, so there is no endpoint to ping. 45 installs a week from npm. Last commit 24 Oct 2026.
Hands your live Chrome tab to any MCP client — snapshot, navigate, click, type, extract.
We read the source, 23 h 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.
const child = spawn(type === 'clipboard.read' ? '/usr/bin/pbpaste' : '/usr/bin/pbcopy', [], { stdio: ['pipe', 'pipe', 'ignore'] });
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 weboperator -- npx -y weboperator-mcp
{
"mcpServers": {
"weboperator": {
"command": "npx",
"args": [
"-y",
"weboperator-mcp"
]
}
}
}
[mcp_servers.weboperator]
command = "npx"
args = ["-y", "weboperator-mcp"]
{
"mcpServers": {
"weboperator": {
"command": "npx",
"args": [
"-y",
"weboperator-mcp"
]
}
}
}
{
"servers": {
"weboperator": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"weboperator-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
WEBOPERATOR_BRIDGE_PORT (Port of the local WebOperator bridge HTTP API), WEBOPERATOR_AGENT_SOCKET (Unix socket path the bridge listens on), WEBOPERATOR_API_TOKEN (Shared token required by the bridge when unauthenticated access is disabled).
Give AI agents full control over live browsers and apps to navigate, click, extract, and automate.
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot.
AI browser automation - navigate, click, type, extract content, and run autonomous web tasks
AI browser automation. Write async Python to navigate, click, type, and extract data.
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Automate a browser with accessibility snapshots: navigate, click, type, fill and wait.
Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
Drive your real, logged-in Chrome (many profiles, parallel tabs) from any MCP client. Local only.
Answers built from our own checks of this server.