>here's no mechanism for progressive disclosure of parts of the tool's abilities

In fact there is: https://platform.claude.com/docs/en/agents-and-tools/tool-us...

If the special tool search tool is available, then a client would not load the descriptions of the tools in advance, but only for the ones found via the search tool. But it's not widely supported yet.

Indeed, the reconnect behavior is described in the protocol and the server will simply resume from the requested sequence id.

But hey, your fridge is now more secure because blockchain (I'm not kidding, it's in the press release)

It appears to also use a peer-to-peer solution to preventing botnets. So a botnet to prevent botnets.

I wonder if the botnets attend conferences.

I'm not fact-checking that because that's horrifying. Beyond parody. But I guess that's a trend currently.

Edit: I checked because one shouldn't be outraged without fact checking. It's true.

It’s not a million miles from the Silicon Valley smart fridge plot, as long as someone hacks them all.

Indeed, the article would have been correct one year ago.

Now, modern LLM APIs do require the tools to be described outside the prompt [1]. This negates the whole article, although one bit where he's right is that it does not matter if those tools are MCP tools or local, the call to LLM looks the same.

[1] https://platform.openai.com/docs/guides/function-calling?api...

That was in 2022, before LLMs, and they "lost" as in they had to pay back $482 USD.

Weird deflection. GPT 3, a 175 billion parameter model, came out in 2020, so it very much is not before LLMs. I guess you can say the story happened before ChatGPT by a few weeks. As for putting lost in quotation marks, I have no idea why you think the quantity of money is relevant to the outcome. No one was expecting them to file bankruptcy over this, only to follow the original agreement.

>one of the oldest Western traditions is to demonize Russia and Russian people

Would you blame them? Who cares is something good happens now in Russia while they are brutally murdering their neighbors?

Nobody cares whether Hitler was great at drawing or not.

Extend this to the next logical step: who cares about Americans while they are supporting mass murder of children, also?

>Broadly speaking, Russian historians are generally of the opinion that the Holodomor did not constitute a genocide. Among Ukrainian historians the general opinion is that it did constitute a genocide.

https://en.wikipedia.org/wiki/Holodomor_genocide_question

No support for long, streaming interactions, like a terminal

An endpoint implementing this protocol would describe the agent and its capabilities, including examples. So I guess you could index that and create a discovery service.

That sounds like it could be the play. Quick, let’s apply to YC with it.

But MCP doesn't claim to address agent to agent communication, right?

It's not so much about what you _can do_ but about the messaging and posturing, which is what drives the adoption of standards as a social phenomenon.

My team's been working on implementing MCP-agents and agents-as-tools and we consistently saw confusion from everyone we were selling this into (who were already bought in to hosting an MCP server for their API or SDK) for their agents because "that's not what it's for".

Kinda weird, but kinda simple.