Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chrome DevTools MCP (2025)

developer.chrome.com

Post reply on HN
Print view View original

241–250 of 266 posts

Re: Chrome DevTools MCP (2025)

#241

Post by staticassertion »

cheema33 wrote: post #66
mmaunder wrote: post #40

Google is so far behind agentic cli coding. Gemini CLI is awful. So bad in fact that it’s clear none of their team use it. Also MCP is very obviously dead, as any of us doing heavy agentic coding know. Why permanently sacrifice that chunk of your context window when you can just use CLI tools which are also faster and more flexible and many are already trained in. Playwright with headless Chromium or headed chrome is…

> Also MCP is very obviously dead Some people will push back on this. They are holding out hope that the recent improvements Anthropic has made in this regard have improved the context rot problem with MCP. Anthropic's changes improve things a little. But it is akin to putting lipstick on a pig. It helps, but not much. The reason MCP is dying/dead is because MCP servers, once configured, bloat up context even when th…

I'm a layman here. How is a skill any better? Aren't agent tools loaded on-demand, just as a skill would be? People are mentioning OpenAPI, but wouldn't you need to load the spec for that too?

Re: Chrome DevTools MCP (2025)

#244

Post by botanrice »

dataviz1000 wrote: post #100
dsrtslnd23 wrote: post #97

Earlier quoted context omitted.

you mean this one? https://github.com/vercel-labs/agent-browser

It is 2 months old! My excuse for not keeping up is that I'm in so deep that Claude Code can predict the stock market. I'll still publish mine and see if has any value but agent browser looks very complete. Thank you for sharing!

I'm curious, have you developed your own reasoning system for how Claude can predict the stock market? Or have you trained it on past data combined with news sources?

Re: Chrome DevTools MCP (2025)

#245

Post by botanrice »

dataviz1000 wrote: post #49
xrd wrote: post #45

Earlier quoted context omitted.

Yes, please do!

100% I'll response to this by Friday with link to Github. I use Patchright + Ghostery and I have a cleaver tool that uses web sockets to pass 1 second interval screenshots to the a dashboard and pointer / keyboard events to the server which allow interacting with websites so that a user can create authentication that is stored in the chrome user profile with all the cookies, history, local storage, ect.. in the cloud…

Would you be open to sharing your Github profile now so I could follow you? I don't check on here very often.

Re: Chrome DevTools MCP (2025)

#246

Post by mistyvales »

dataviz1000 wrote: post #43

I use Playwright to intercept all requests and responses and have Claude Code navigate to a website like YouTube and click and interact with all the elements and inputs while recording all the requests and responses associated with each interaction. Then it creates a detailed strongly typed API to interact with any website using the underlying API. Yes, I know it likely breaks everybody's terms of service but at the…

I would like to see this!

Re: Chrome DevTools MCP (2025)

#247

Post by quotemstr »

debugnik wrote: post #222
quotemstr wrote: post #107

Earlier quoted context omitted.

Imagine if, in addition to local MCP "servers", the MCP people had nurtured a structured CLI-based --help-equivalent consumable by LLMs and shell completion engines alike. Doing so, you unify "CLI" (trivial deployment; human accessibility) and MCP-style (structured and discoverable tool calling) in a single DWIM artifact. But since when has this industry done the right thing informed by wisdom and hindsight?

That structured CLI already exists: PowerShell cmdlets.

Not in any meaningful, general way on Unix systems it doesn't. Nobody uses psh outside Windows

Re: Chrome DevTools MCP (2025)

#248

Post by recroad »

galaxyLogic wrote: post #211
recroad wrote: post #152

Earlier quoted context omitted.

No, doesn't use work with server-side only apps.

It's a server-side app whose GUI is in the browser, a bit like Electron or what have you. I guess my question is does Tidewawe only work with a fixed set of known "frameworks" like React and Next, or is it a more general purpose tool for analysing an app based on its source-code and the HTML it produces for the browser?

Fixed set.

Re: Chrome DevTools MCP (2025)

#249

Post by abhikul0 »

paulirish wrote: post #47

The DevTools MCP project just recently landed a standalone CLI: https://github.com/ChromeDevTools/chrome-devtools-mcp/blob/m... Great news to all of us keenly aware of MCP's wild token costs. ;) The CLI hasn't been announced yet (sorry guys!), but it is shipping in the latest v0.20.0 release. (Disclaimer: I used to work on the DevTools team. And I still do, too)

It doesn't seem to work, tried the -u flag with the default address and it just couldn't connect to the existing chrome instance.

Re: Chrome DevTools MCP (2025)

#250

Post by sidwyn »

dataviz1000 wrote: post #43

I use Playwright to intercept all requests and responses and have Claude Code navigate to a website like YouTube and click and interact with all the elements and inputs while recording all the requests and responses associated with each interaction. Then it creates a detailed strongly typed API to interact with any website using the underlying API. Yes, I know it likely breaks everybody's terms of service but at the…

I do something similar [1] but it leverages WebMCP (see Amazon example [2]). Could probably turn it into a strongly typed API.

[1] https://github.com/sidwyn/webmcp-tool-library

[2] https://github.com/sidwyn/webmcp-tool-library/blob/main/cont...

Post reply on HN