from Hacker News

MCP explained without hype or fluff

by captn3m0 on 5/22/25, 3:39 PM with 70 comments

  • by thembones on 5/22/25, 5:03 PM

    Good point about the M x N problem reduction, but this glosses over a critical limitation. While MCP does turn integration complexity from M x N to M + N for the protocol layer, authentication and authorization remain stubbornly M x N problems.

    Each MCP server still needs to handle auth differently depending on what it's connecting to. A GitHub MCP server needs GitHub tokens, a database server needs database credentials, an email server needs SMTP auth, etc. The client application now has to manage and securely store N different credential types instead of implementing N different integrations.

    So yes, the protocol complexity is reduced, but the real operational headache (managing secrets, handling token refresh, dealing with different auth flows) just gets moved around rather than solved. In some ways this might actually be worse since you now have N different processes that each need their own credential management instead of one application handling it all.

    This doesn't make MCP useless, but the "M x N to M + N" framing undersells how much complexity remains in the parts that actually matter for production deployments.

  • by hansmayer on 5/22/25, 4:37 PM

    The overload of GenAI related postings on here almost makes me look with nostalgy at the period when most of the posts were about some SQLite optimisation/use-case/weird trick....

  • by scubbo on 5/22/25, 4:37 PM

    I keep waiting for someone to break character and admit that this is all an extended trolling campaign. People are actually connecting these autocompletes to APIs and giving credentials to take impactful external actions? Y'all are _insanely_ trusting.

  • by nythroaway048 on 5/22/25, 3:59 PM

    Can we not just point LLMs at OpenAPI documents and achieve the same result? All of the example functions in the article look like very very basic REST endpoints.

  • by m3kw9 on 5/22/25, 4:01 PM

    Why is there so much explaining to do for MCPs? There seem to be something seriously wrong with the way Anthropic is marketing it. It looks like the entire world is confused as to what it is.

  • by Zaheer on 5/22/25, 4:38 PM

    I found myself trying to explain MCP the other day. The simplest way I could put it for another developer:

    MCP is a standardized set of API endpoints that makes it easier for LLM's to discover and operate with all the other regular APIs you have.

  • by mannyv on 5/22/25, 4:34 PM

    It's cgi-bin for AI.

  • by dvt on 5/22/25, 7:58 PM

    MCP is bloated AI hype that basically solves nothing (the Langchain of 2025!). Typical tooling on top of tooling and the quintessential case of a problem looking for a solution. It's absolute garbage from just about any standpoint: architectural, security, elegance, etc. But my main point is that it solves nothing and there's nothing novel here. It's APIs talking to APIs that talk to other APIs. Wow, groundbreaking!

    I genuinely believe that there will be (and potentially already are) use-cases when it comes to AI agents, but we really to step back and re-think the whole thing. In the middle of writing a blog post about this, but I really do think genAI is a dead-end and that no one really wants to chill out for a second and solve the hard stuff:

        - Needle in a haystack accuracy
    - Function calling (and currying/chaining) reliability
    - Non-chat UI paradigm (the chat-box UI is a dead-end)
    - Context culling (ignoring non-relevant elements)
    - Data retrieval given huge contexts (RAG is just not good enough)
    - Robotics
    - Semantic inference
    Like, I get it, it's hard to come up with new ways of solving some of these (or bringing them up from ~50% to 90% accuracy), but no one's going to use an AI agent when it confidently fakes data, it doesn't remember important stuff, or you gotta sit there and tweak a prompt for 30 minutes.

  • by beernet on 5/22/25, 5:31 PM

    MCP is as revolutionary as JSON.

    Still, funny to see numerous hyped GenAI start-ups with bad monetary traction jump on the bandwagon and proclaim MCP as the latest revolution (after RAG, Agents, you name it)...All of these are simply tools which add zero value by themselves. Looking forward to the VC wake up calls.

  • by bootsmann on 5/22/25, 4:23 PM

    Has anyone found good resources about dealing with authentication in MCP, especially about managing the oauth tokens locally?

  • by huhkerrf on 5/22/25, 4:22 PM

    I feel like there's something wrong with me for not understanding the big leap with MCP and the proponents aren't helping.

    I saw a tweet stream that said something like "if you think MCP is the same as REST, you're not thinking big enough" followed by a bunch of marketing speak that gave off LinkedIn web3 influencer vibes. I saw a blog post that says MCP is better because it bridges multiple protocols. Okay, and?

    I really want to get this, but I don't know how to square "LLMs are hyper intelligent" with "LLMs can't figure out OpenAPI documentation."

  • by thekodols on 5/22/25, 4:09 PM

    I know it’s in active discussion on GH, but I wish clients would solve (non-text) UIs from MCP servers rather soon. It would 10x the power of these chat extensions.

  • by mrtksn on 5/22/25, 6:33 PM

    How so humans need to know about all this? Isn’t it the exact use case where the machines write all the code as it is machine to machine protocol and some of the machine involved are supposed to be phd level programmers.

    The MCP or something similar should exist but it should be handled %100 by AI so the people can do the stuff that is important and human related.

    It rubs me the wrong way seeing people trying to understand this and if you take it on face value it appears that now AI can do the code but MCP is so hard that it needs a human who studied that so they can talk.

    Is this piece of JSON really the last frontier of programming?

  • by leoc on 5/22/25, 6:23 PM

  • by rglover on 5/22/25, 7:22 PM

    Initially I took MCP to be some crazy new thing, but once I dug into it, it's really just a soft-standard for connecting a database, API, or other data source (e.g., a list of functions that can be called) to a vector database and then returning a response in a standardized JSON format.

    It's basically RAG with a bit of sugar on top. What spooks me is how few people hyping MCP seem to understand that.