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…
Gemini 3.1 Pro through Gemini CLI always tries to write files with cat instead of using the write_file tool, it's awful at tool use.
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!
> What other alternatives exist in place of MCP? Arbitrary code via curl/sdks to call a remote endpoint? cli? for example aws cli. It's a full interface to aws API. Why would you need mcp for that? and if you have any doubts, agents use it with a great effect even without any relevant skill. "aws help" is fully discoverable.
yes, but clis thus need self-service commands to provide guidance, and their responses need to be optimized for consumption by agents. in a sense, this is the same sort of context tax that MCP servers incur. so in my view cli and MCP are complementary tools; one is not strictly superior over the other.
> yes, but clis thus need self-service commands to provide guidance, and their responses need to be optimized for consumption by agents.
MCP vs Agent Skills:
MCPs once configured cost you tokens even when they are not used.
Unlike MCPs, skills use progressive disclosure. The AI agent does not load up the entire context, if the skill is not being used.
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 use chrome devtools MCP to the same end - it works great for me. Interested in what advantages you see in using Playwright over chrome devtools?
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 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 also do this. My primary use case is for reproducing page layout and styling at any given tree in the dom. So, capturing various states of a component etc. I also use it to automatically retrieve page responsiveness behavior in complex web apps. It uses playwright to adjust the width and monitor entire trees for exact changes which it writes structured data that includes the complete cascade of styles relevant with…
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…
FYI: Gemini Cli is used internally at Google. It's actually more popular than Antigravity. Google uses MCP services internally for code search (since everything is in a mono-repo you don't want to waste time grepping billions of files), accessing docs and bugs, and also accessing project specific RAG databases for expertise grounding. Source - I know people at Google.
Have you tried it? It's like working with an idiot savant. It's absolutely brilliant, but goes off the rails constantly, spewing out CoT when it shouldn't be, getting into weird loops, spewing gibberish or repeated phrases. But when it does actually work, it's brilliant. But the issues make it unusable for dev at any level - and completely untrustworthy. Contrasted with CC or Codex CLI it's night and day. The latter two are incredibly reliable, rock solid, and crazy productive, and becoming exponentially more so by the week.
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 also do this. My primary use case is for reproducing page layout and styling at any given tree in the dom. So, capturing various states of a component etc. I also use it to automatically retrieve page responsiveness behavior in complex web apps. It uses playwright to adjust the width and monitor entire trees for exact changes which it writes structured data that includes the complete cascade of styles relevant with…
> My first reaction to seeing this FP was why are people still releasing MCPs?
MCPs are more difficult to use. You need to use an agent to use the tools, can't do it manually easily. I wonder if some people see that friction as a feature.