---
title: "Control your REAL Chrome with Chrome CDP"
excerpt: "When your AI agent launches a web browser to test your site or Chrome extensions, its context is completely empty. Every time you have to start from scratch: re-authenticate on every site, deal with CAPTCHAs because the browser is detected as automated, etc. Result: unusable for your real workflows. Chrome-cdp fixes that in one line: your agent slips into your Chrome, sees what you see, acts where you work."
author: "Cédric TOURNIER"
author_url: "https://mysaas.blog/en/@Amorem"
published_at: 2026-03-15
locale: en
tags: #skills #chrome #playwright #mcp
source: "https://mysaas.blog/en/@Amorem/control-your-real-chrome-with-chrome-cdp"
site: https://mysaas.blog
---

# Control your REAL Chrome with Chrome CDP

## The problem

I lost several hours banging my head against Playwright automation. It's become rare to be blocked on a technical issue in the age of AI.

I wanted Claude to access the DOM of the Twitter feed page to identify HTML patterns and test modifications in real time.

Simple in theory.

![Playwright MCP](https://assets.mysaas.blog/posts/2026-03-21/0883c81f-f9f9-4d63-baad-1484c8f04197.png)It quickly turns into a nightmare. From a technical standpoint, Playwright starts from a fresh, isolated browser (in automation mode) on every execution.

So I have to log back into Twitter, which obviously detects that the browser is in test/automation mode and blocks me.

## The (belated) solution

I was out of ideas and, above all, out of patience when I saw a Twitter post announcing that Chrome had just released **version 146**, and from there a solution that could simplify everything: **chrome-cdp**.

As we've seen, most browser automation tools launch an isolated, empty browser every time.** **Not chrome-cdp — **it connects directly to your running Chrome**: your open tabs, your logged-in sessions, your current page state. Nothing to reinstall, nothing to reconfigure.

CDP is the native interface that allows you to control Chrome from its lower layers.

![CDP protocol](https://assets.mysaas.blog/posts/2026-03-21/ef60c5cd-edca-4dd4-93ef-4b5a256584df.png)The chrome-cdp skill then uses it to pass simple commands to an agent. Which, incidentally, is much less context-expensive than using an MCP.

**chrome-cdp** maintains a persistent daemon per tab: the modal only appears **once**, and it reliably handles **100+ tabs** where Puppeteer-based tools regularly time out.

## 

## Installation in 4 steps

### 1) Update Chrome to version 146

![Chrome 146](https://assets.mysaas.blog/posts/2026-03-15/00262a59-516a-40fa-a069-1c99d106c383.png)

### 2) Enable remote debugging

```
chrome://inspect/#remote-debugging
```

Enable the toggle. That's it.

![Enable remote debugging in Chrome](https://assets.mysaas.blog/posts/2026-03-15/457626de-f536-4f48-9595-213ce4e07b1e.png)

### 3) Fetch the skill and install it

```
npx skills add https://github.com/pasky/chrome-cdp-skill --skill chrome-cdp
```

![skills.sh](https://assets.mysaas.blog/posts/2026-03-15/cf59eafb-89a7-44f5-af6f-44f706cf817b.png)

### 4) Enjoy 🎉

Your agent can now list your tabs, take screenshots, read the DOM, click, type text, evaluate JavaScript — all within **your real Chrome**, without leaving your workflow.

![Claude is happy](https://assets.mysaas.blog/posts/2026-03-15/e4c715b1-0f18-4e26-ad0d-4580c65ee959.png)

## Sources

- [Chrome DevTools Protocol](https://chromedevtools.github.io/devtools-protocol/)
- [Your Browser Has a Remote Control — And Nobody Told You](https://dev.to/timtech4u/your-browser-has-a-remote-control-and-nobody-told-you-5e97)
- [pasky/chrome-cdp-skill](https://github.com/pasky/chrome-cdp-skill)