Hacker News

I feel like I don't fully understand mcp. I've done research on it but I definitely couldn't explain it. I get lost on the fact that to my knowledge it's a server with API endpoints that are well defined into a json schema then sent the to LLM and the LLM parses that and decides which endpoints to hit (I'm aware some llms use smart calling now so they load the tool name and description but nothing else until it's called). How exactly are you doing the process of stopping the LLM from using web search after it hits a certain endpoint in your MCP server? Or is this referring strictly to when you own the whole workflow where you can then deny websearch capabilities on the next LLM step?

It is a weird trend. I see the appeal of Skills over MCP when you are just a solo dev doing your work. MCP is incredibly useful in an organization context when you need to add controls and process. Both are useful. I feel like the anti-MCP push is coming from people who don't need to work in a large org.

Skills are just prompts, so policy doesn't apply there. MCP isn't giving you any special policy control there, it's just a capability border. You could do the same thing with a service mesh or any other capability compartmentalization technique.

The only value in MCP is that it's intended "for agents" and it has traction.

> Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills.

I have been keeping an eye on MCP context usage with Claude Code's /context command.

When I ran it a couple months ago, supabase used 13.2k tokens all the time, with the search_docs tool using 8k! So, I disabled that tool in my config.

I just ran /context now, and when not being used it uses only ~300 tokens.

I have a question. Does anyone know a good way to benchmark actual MCP context usage in Claude Code now? I just tried a few different things and none of them worked.

Towards the end of the article, they do write about some things that MCP does better.

Tool search pretty much completely negates the MCP context window argument.

I agree, and it's context-dependent when to use what (the author mentions use cases for other solutions). I'm glad there are multiple solutions to choose from.

MCPs are handy in their place. Agents calling CLI locally is much more efficient.

This matches my experience building in-house MCP servers. The mechanism I prefer on load is something like a quick FTS5 with BM25 ranking lookup to find what it needs, and then serve those. I think a lot of these things are implemented pretty naively - for instance, we ran into the huge context problem with Jira, so we just built our own Jira MCP interface that doesn't have all the bloat. If the agent finds it needs something it doesnt have, it can ask again.

The real issue isn't MCP, it's these fucking bots posting here every day.

claude code solved this about a month ago

This is becoming a solved problem with tool search; MCP is back.

More likely: "Can you believe they were actually trying to use LLMs for this?"

10 years from now: "The next big thing: HENG - Human Engineers! These make mistakes, but when they do, they can just learn from it and move on and never make it again! It's like magic! Almost as smart as GPT-63.3-Fast-Xtra-Ultra-Google23-v2-Mem-Quantum"

10 years from now: “what’s a context window?”

I am kind of already at that point. For all the complaining about context windows being stuffed with MCPs, I am curious what they are up to and how many MCPs they have that this is a problem.

"That was back when models were so slow and weighty they had to use cloud based versions. Now the same LLM power is available in my microwave"

“640K ought to be enough for anybody”

> modern MCP clients do smart tool search that obviates the entire "I am sending the full list of tools back and forth" mode of operation

How, "Dynamic Tool Discovery"? Has this been codified anywhere? I've only see somewhat hacky implementations of this idea

https://github.com/modelcontextprotocol/modelcontextprotocol...

Or are you talking about the pressure being on the client/harnesses as in,

https://platform.claude.com/docs/en/agents-and-tools/tool-us...

This is a fair trade-off and the post should probably be more explicit about it. You're right that progressive disclosure trades latency for cost and context space. For some workloads that's the wrong trade.

The amortization point is interesting too. If you're running a support agent that calls the same 5 tools thousands of times a day, paying the schema cost once and caching it makes total sense. The post covers this in the "tightly scoped, high-frequency tools" section but your framing of it as a caching problem is cleaner.

On the footnote: guilty as charged, partially. The ~80 token prompt is a minimal bootstrap, not a full schema. It tells the agent how to discover, not what to call. But yeah, the moment you start expanding that prompt with specific flags and patterns, you're drifting toward a hand-rolled tool definition. The difference is where you stop. 80 tokens of "here's how to explore" is different from 10,000 tokens of "here's everything you might ever need." But the line between the two is blurrier than the post implies. Fair point.

Can you explain how to take advantage. Is there any specific info from anthropic with regards to context window size and not having to care about MCP?

Fair point on tool search. Claude Code and Codex do have it.

But tool search is solving the symptom, not the cause. You still pay the per-tool token cost for every tool the search returns. And you've added a search step (with its own latency and token cost) before every tool call.

With a CLI, the agent runs `--help` and gets 50-200 tokens of exactly what it needs. No search index, no ranking, no middleware. The binary is the registry.

Tool search makes MCP workable. CLIs make the search unnecessary.

Great tool, however we went to a dedicated CLI client (think gh, aws, stripe) in Go.

Those bigger windows come with lovely surcharges on compute, latency, and prompt complexity, so "just wait for more tokens" is a nice fantasy that melts the moment someone has to pay the bill. If your use case is tiny or your budget is infinite, fine, but for everyone else the "make the window bigger" crowd sounds like they're budgeting by credit card. Quality still falls off near the edge.

Context windows getting bigger doesn't make the economics go away. Tokens still cost money. 50K tokens of schemas at 1M context is the same dollar cost as 50K tokens at 200K context, you just have more room left over.

The pattern with every resource expansion is the same: usage scales to fill it. Bigger windows mean more integrations connected, not leaner ones. Progressive disclosure is cheaper at any window size.