Agentic Browser runs on your own machine — the client starts it, so there is no endpoint to ping. 337 installs a week from npm. Last commit 23 Oct 2026.
Give any AI agent your real Chrome: text perception, visible cursor, ~4x fewer tokens.
What the code does
We read the source, 2 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.
postinstall: node scripts/postinstall.js
const lock = ['SingletonLock', 'lockfile', 'SingletonSocket'].find(f => fs.existsSync(path.join(profile, f)));
const r = spawnSync(cand, ['-version'], { stdio: 'ignore', windowsHide: true });
const env = Object.fromEntries(Object.entries(process.env)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 agentic-browser -- npx -y agentic-browser-mcp{
"mcpServers": {
"agentic-browser": {
"command": "npx",
"args": [
"-y",
"agentic-browser-mcp"
]
}
}
}[mcp_servers.agentic-browser]
command = "npx"
args = ["-y", "agentic-browser-mcp"]{
"mcpServers": {
"agentic-browser": {
"command": "npx",
"args": [
"-y",
"agentic-browser-mcp"
]
}
}
}{
"servers": {
"agentic-browser": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentic-browser-mcp"
]
}
}
}Alternatives to Agentic Browser
same job, measured the same wayDrive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.
Drive your real, logged-in Chrome/Edge from AI agents over CDP. Faster. Sharper.
Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.
Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
Give browser tasks to TabRunner, an agent in your own Chrome that uses your logins.
Design engine for AI agents: images at every size, no Chrome, 2× fewer tokens
Stealth browser automation for AI agents — real Chrome, N parallel persistent logged-in sessions.
Agentic Browser — questions
Answers built from our own checks of this server.