81–90 of 348 posts
— written by ai
The post misses the mark on why a stateless protocol like MCP actually makes sense today. Most modern devs aren’t spinning up custom servers or fiddling with sticky sessions—they’re using serverless platforms like AWS Lambda or Cloudflare Workers because they’re cheaper, easier to scale, and less of a headache to manage. MCP’s statelessness fits right into that model and makes life simpler, not harder. Sure, if you’r…
The protocol is absolute mess both for clients and servers. The whole thing could have been avoided if they picked any sane bidirectional transport, even websocket.
Tldr; it's json array passed to llms. Swagger would have sufficed. How and why youcome up with the array shouldn't matter. We shouldn't need 10000 redundant servers.
In the same way that crypto folks speedran "why we have finance regulations and standards", LLM folks are now speedrunning "how to build software paradigms". The concept they're trying to accomplish (expose possibly remote functions to a caller in an interrogable manner) has plenty of existing examples in DLLs, gRPC, SOAP, IDL, dCOM, etc, but they don't seem to have learned from any of them, let alone be aware that t…
Or like the early Python ecosystem, mistakes will become ossified at the bottom layers of the stack, as people rapidly build higher level tools that depend on them.
Except unlike early Python, the AI ecosystem community has no excuse, BECAUSE THERE ARE ALREADY HISTORICAL EXAMPLES OF THE EXACT MISTAKES THEY'RE MAKING.
Agreed with basically the entire article. Also happy to hear that someone else was as bewildered as me when they visited the MCP site and they found nothing of substance. RFCs can be a pain to read, but they're much better than 'please just use our SDK library'.
Agree... this is an important blog. People need to press pause on MCP in terms of adoption...it was simply not designed with a solid enough technical foundation that would make it suitable to be an industry standard. People are hyped about it, kind of like they were for LangChain and many other projects, but people are going to gradually (after diving into implementations) that it's not actually what they were lookin…
Earlier quoted context omitted.
> I somewhat agree with author’s comments, but also want to note that the protocol is in the extremely early stages of development, and it will likely evolve a lot over the next year. And that's why it's so important to spec with humility. When you make mistakes early in protocol design, you live with them FOREVER. Do you really want to live with a SSE Rube Goldberg machine forever? Who the hell does? Do you think yo…
Just focusing on worst-case scenarios tends to spread more FUD than move things forward. If you have specific proposals for how the protocol could be designed differently, I’m sure the community would love to hear them – https://github.com/orgs/modelcontextprotocol/discussions
At the least, MCP needs to clarify things like "SHOULD rate limit" in more precise terms. Imagine someone who is NOT YOU, someone who doesn't go to your offsites, someone who doesn't give a fuck about your CoC, implementing your spec TO THE LETTER in a way you didn't anticipate. You going to sit there and complain that you obviously didn't intend to do the things that weird but compliant server is doing? You don't have a recourse.
The recent MCP annotations work is especially garbage. What the fuck is "read only"? What's "destructive"? With respect to what? And hoo boy, "open world". What the fuck? You expect people to read your mind?
What would be the point of creating GH issues to discuss these problems? The kind of mind that writes things like this isn't the kind of mind that will understand why they need fixing.
Absolutely terrible, no clear spec, absolute useless errors and/or just broken behaviour without telling what’s wrong. Reference implementations and frameworks are not working either, so only reverse engineering + trial & error until it runs, yaaay.
Feels like the early 2000 over and over again, trying to make something work.
[1]: https://modelcontextprotocol.io/specification/draft/basic/au...
https://github.com/modelcontextprotocol/modelcontextprotocol...
MCP as a spec is really promising; a universal way to connect LLMs to tools. But in practice you hit a lot of edge cases really quickly. To name a few; auth, streaming of tool responses, custom instructions per tool, verifying tool authenticity (is the server I'm using trustworthy?). It's still not entirely clear (*for remote servers*) to me what you can do with MCP that you can't do with just a REST API, the latter being a much more straightforward integration path.
If other vendors do adopt MCP (OpenAI and Gemini have promised to) the problem they're going to run into very quickly is that they want to do things (provide UI elements, interaction layers) that go beyond the MCP spec. And a huge amount of MCP server integrations will just be lackluster at best; perhaps I'm wrong -- but if I'm { OpenAI, Anthropic, Google } I don't want a consumer installing Bob's Homegrown Stripe Integration from a link they found on 10 Best MCP Integrations, sharing their secret key, and getting (A) a broken experience that doesn't match the brand or worse yet, (B) credentials stolen.