NeoBrowser: AI drives your real Chrome, logged in and stealthy
NeoBrowser: An MCP server that drives real Chrome with your logged-in sessions
NeoBrowser is an MCP server that lets AI models drive your real Chrome browser with your actual logged-in sessions. It passes bot detection with a genuine fingerprint, moves the mouse like a human, and detects bot walls (CAPTCHAs, rate limits) to hand control back. With 43 tools, a single static Rust binary, and no runtime dependencies, it offers real multi-tab browsing, semantic element finding, and multi-source search. It's honest about limitations: interactive challenges may still appear, but its warm real profile and wall detection make it dependable.
It doesn't pretend to be invisible: when a site throws an interactive challenge (reCAPTCHA, Turnstile) NeoBrowser detects it and hands control back with a real-session or human path — that honesty is what makes it dependable.
- nater5000
>It doesn't pretend to be invisible: when a site throws an interactive challenge (reCAPTCHA, Turnstile) NeoBrowser detects it and hands control back with a real-session or human path — that honesty is what makes it dependable.
Maybe it's just me, but if you can't be bothered to clean up your vibecoded README, I'm going to assume I'd be better off just vibecoding my own version of this solution.
- Icingdeath
When I need an coding agent to interact with an existing session I just use
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-profile-stable and tell it
- dongkeren
I am wondering how it solves the security issues:
I saw opt-in, file permissions and SSRF in README, but I do not see:
domain allowlist;
human approval before submiting/deleting;
persistent audit record after operations;
how to revoke a previously granted access;
The prompt injection may also induce the agent to perform write operations.
Reuse the real user-login session also delegate the user's full authority to the agent, which obviously has potential security issues.
The point is, the more real authority the agent has, the more important the responsibility the agent must take, which I think should be designed in from the beginning.
- dbbk
Doesn't Claude already do this?
- andreidbr
I've been using the Chrome CDP skill for Claude Code with great success for test automation purposes (locator detection, troubleshooting mobile layout, and so on). I found it here on HN: https://github.com/pasky/chrome-cdp-skill
I remember seeing another Chromium-based "MCP-focused" browser at that point in time, but I can't remember what it was called.