221–230 of 266 posts
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…
Earlier quoted context omitted.
Tbh I find self-documenting CLIs (e.g. with a `--help` flag, and printing correct usage examples when LLMs make things up) plus a skill that's auto invoked to be pretty reliable. CLIs can do OAuth dances too just fine. 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, dynam…
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?
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…
Did you compare playwright with mcp? Why one over another?
I use MCP usually, because I heard it’s less detectable than playwright, and more robust against design changes, but I didn’t compare/test myself
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 love how HN is loving this idea when it's the exact same thing Anthropic and OpenAi (and every other llm maker) did. It's God's gift to them when it lets them bypass ads and dl copyrighted material. But it's Satan's curse on humanity when the Zuck does it to train his llm and dl copyrighted material.
Where's the contradiction?
However, it will not fill forms, etc. But it can be combined with agent-browser to get the best of both worlds: https://swival.dev/pages/web-browsing.html
Earlier quoted context omitted.
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…
its mostly because MCPs handle auth in a standardised way and give you a framework you can layer things like auth, etc on top of. Without it youre stuck with the basic http firewall, etc which is extremely dangerous and this is maybe the 1 opportunity we have to do this.
80% of MCPs are thin wrappers over APIs . Yes they stink.
A well written remote OAuth MCP need not stink. Tons of advantages starting with strong security baked in.
I like Cloudflare Code Mode as an MCP pattern. Two tools, search and execute.
1M Opus 4.6 also reduces the penalties of MCP’s context approach. Along with tool search etc.