Hacker News Reader

Comment by billconan | Hacker News Reader

> LLMs know how to call cli-tool --help, which means you don’t have to spend many tokens describing how to use them—the model can figure it out later when it needs to.

I do not understand this. cli-tool --help outputs still occupies tokens right?

View on HN

Absolutely, but it occupies them later and only when needed. This is what I think they're driving at here.

but why can't I do the same with mcp? I just create a help() function that returns the help info?

Most people still don't understand MCP properly and think it's about adding 50 tools to every call. Proper MCP servers and clients implement tools/listChanged

you can; i've seen people put mcp access behind another mcp. I'm not sure how much success they got from it though

That hypothetical might be fine, but MCPs do much more than that and their catalogs can be enormous. Here are some popular MCPs and the amount of context they eat before you've done anything with them:

  • Linear: 23 tools (~12,935 tokens)
  • JetBrains: 20 tools (~12,252 tokens)
  • Playwright: 21 tools (~9,804 tokens)

Github: 39 tools, 30K. I had to disable it.

Does anybody have a good SKILLS.md file we can study?

Absolutely! I now have Claude Code using `gh` and haven't missed the MCP. (If there are better CLI alternatives, I'd love to hear about them.)

This is like MCPs on demand. I've switched a few MCP servers to just scripts because they were taking like 20% of the context just by being there. Now, I can ask the model to use X script, which it reads and uses only if needed.

Reply on news.ycombinator.com