81–90 of 266 posts
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)
MCPs cost nothing in CC now with Tool Search.
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…
Yes, please do and ping me when it's done lol. Did you make it into an agent skill?
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…
MCP is very much not dead. centralized remote MCP servers are incredibly useful. also bespoke CLIs still require guidance for models to use effectively, so it's clear that token efficiency is still an issue regardless.
MCP's remaining moats I think are:
- No-install product integrations (just paste in mcp config into app)
- Non-developer end users / no shell needed (no terminal)
- Multi-tenant auth (many users, dynamic OAuth)
- Security sandboxing (restrict what agents can do), credential sandboxing (agents never see secrets)
- Compliance/audit (structured logs, schema enforcement)?
If you're a developer building for developers though, CLI seems to be a clear winner right
Earlier quoted context omitted.
Yes, please do and ping me when it's done lol. Did you make it into an agent skill?
Exactly, it is an agent skill that interacts pressing buttons and stuff with a webpage capturing and documenting all the API requests the page makes using Playwright's request / response interception methods. It creates and strongly typed well documented API at the end.
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…
Very cool. I do something like this but with Playwright. It used to be a real token hog though, and got expensive fast. So much so that I built a wrapper to dump results to disk first then let the agent query instead. https://uisnap.dev/ Will check this out to see if they’ve solved the token burn problem.
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…
Earlier quoted context omitted.
Would this hypothetically be able to download arbitrary videos from youtube without the constant yt-dlp arms race?
Don’t know how this could be more stable than ytdlp. When issues come up they’re fixed really quickly.
Here is what actually fixed it: https://github.com/yt-dlp/ejs/pull/53/changes
yt-dlp is relatively stable, but still occasionally breaks for long periods. I get the sense YouTube is becoming increasingly adversarial to yt-dlp as well.
I don't know the details, but it doesn't seem like yt-dlp is running the entire YouTube JS+DOM environment. Something like a real headless browser seems like it would break less often, but be much heavier weight. And Youtube might have all sorts of other mitigations against this approach.
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…