[HN Gopher] MCP: An (Accidentally) Universal Plugin System
       ___________________________________________________________________
        
       MCP: An (Accidentally) Universal Plugin System
        
       Author : Stwerner
       Score  : 436 points
       Date   : 2025-06-28 14:22 UTC (8 hours ago)
        
 (HTM) web link (worksonmymachine.substack.com)
 (TXT) w3m dump (worksonmymachine.substack.com)
        
       | roenxi wrote:
       | ... MCP is almost literally just a JSON schema and a "yo, this
       | stuff exists" for AI. It is great to have it standardised and
       | we're all very thankful not to be using XML but there just isn't
       | that much there.
       | 
       | MCP is fulfilling the promise of AI agents being able to do their
       | own thing. None of this is unintended, unforeseen or particularly
       | dependent on the existence of MCP. It is exciting, the fact that
       | AI has this capability captures the dawn of a new era. But the
       | important thing in the picture isn't MCP - it is the power of the
       | models themselves.
        
         | layer8 wrote:
         | XML actually works better with LLMs than JSON.
        
           | zahlman wrote:
           | Why?
        
             | layer8 wrote:
             | Presumably because XML tags give better context. You have
             | closing tags, and each array element has its own tags. The
             | tag syntax is different from the value syntax, whereas in
             | JSON both labels and string values use the same syntax.
             | JSON strings are delimited by the same character ("),
             | whereas XML uses two different characters (>...<). Non-
             | string values in JSON have more variations in their
             | delimitation than values in XML.
        
       | spiritplumber wrote:
       | Yes, I'm old. Old enough to remember the MCP when he was just a
       | chess program! He started small, and he'll end small!
        
         | rlboston wrote:
         | Sounds like programming! What happened to low code/no code? I
         | AM old, retired in fact. IT has more "middleware" than the
         | library of congress and mainframes still exist. But I will dig
         | around, because I'm still curious. Carry on. LOL
        
       | jadar wrote:
       | I don't want to undermine the author's enthusiasm for the
       | universality of the MCP. But part of me can't help wondering:
       | isn't this the idea of APIs in general? Replace MCP with REST and
       | does that really change anything in the article? Or even an
       | Operating System API? POSIX, anyone? Programs? Unix pipes? Yes,
       | MCP is far simpler/universal than any of those things ended up
       | being -- but maybe the solution is to build simpler software on
       | good fundamental abstractions rather than rebuilding the
       | abstractions every time we want to do something new.
        
         | bayesianbot wrote:
         | My first thought as well. But maybe at least people wanting to
         | plug their apps to their AI forces developers to actually
         | implement the interface, unlike APIs that are mostly unheard of
         | in general population and thus not offered?
        
         | kvdveer wrote:
         | The main difference between MCP and Rest is that MCP is self
         | described from the very start. REST may have OpenAPI, but it is
         | a later addon, and we haven't quite standardised on using it.
         | The first step of exposing an MCP is describing it, for Rest is
         | is an optional step that's often omitted.
        
           | light_hue_1 wrote:
           | But you're describing it in a way that is useless to anything
           | but an LLM. It would have been much better if the description
           | language had been more formalized.
        
             | 0x696C6961 wrote:
             | The description includes an input and output json schema.
        
             | Majromax wrote:
             | > It would have been much better if the description
             | language had been more formalized.
             | 
             | To speculate about this, perhaps the informality is the
             | point. A full formal specification of something is
             | somewhere between daunting and Sisyphean, and we're more
             | likely to see supposedly formal documentation that
             | nonetheless is incomplete or contains gaps to be filled
             | with background knowledge or common sense.
             | 
             | A mandatory but informal specification in plain language
             | might be just the trick, particularly since vibe-APIing
             | encourages rapid iteration and experimentation.
        
           | Szpadel wrote:
           | isn't also SOAP self described?
        
             | souldeux wrote:
             | And gRPC with reflection, yeah?
        
               | hansonkd wrote:
               | and GQL with reflection?
        
               | notpushkin wrote:
               | JSON-LD?
        
             | gaunds wrote:
             | khsnaadirbiid Skdbiebdjv
        
             | kerng wrote:
             | When I read about MCP the first time and saw that it
             | requires a "tools/list" API reminded me of COM/DCOM/ActiveX
             | from Microsoft, it had things like QueryInterface and
             | IDispatch. And I'm sure that wasn't the first time someone
             | came up with dynamic runtime discovery of APIs a server
             | offers.
             | 
             | Interestingly, ActiveX was quite the security nightmare for
             | very similar reasons actually, and we had to deal with
             | infamous "DLL Hell". So, history repeats itself.
        
           | xg15 wrote:
           | Is it "self-described" in the sense I can get a list of
           | endpoints or methods, with a human- (or LLM-) readable
           | description for each - or does it supply actual schemata that
           | I could also use with non-AI clients?
           | 
           | (Even if only the former, it would of course be a huge step
           | forward, as I could have the LLM generate schemata. Also, at
           | least, everyone is standardizing on a base protocol now, and
           | a way to pass command names, arguments, results, etc. That's
           | already a huge step forward in contrast to arbitrary
           | Rest+JSON or even HTTP APIs)
        
             | Spivak wrote:
             | For each tool you get the human description as well as a
             | JSON schema for the parameters needed to call the function.
        
               | talos_ wrote:
               | You're getting an arbirary string back though...
        
               | jcelerier wrote:
               | how else would you describe an arbitrary tool?
        
         | spenczar5 wrote:
         | honestly, yes - but MCP includes a really simple 'reflection'
         | endpoint to list the capabilities of an API, with human
         | readable docs on methods and types. That is something that gRPC
         | and OpenAPI and friends have supported as an _optional_
         | extension for ages, but it has largely been a toy. MCP makes it
         | central and maybe that makes all the difference.
        
           | spudlyo wrote:
           | At a previous job most of our services supported gRPC
           | reflection, and exploring and tinkering with these APIs using
           | the grpc_cli tool was some of the most fun I had while
           | working there. Building and using gRPC services in golang
           | left a strong positive impression on me.
        
             | lobsterthief wrote:
             | I had the same experience working with GQL :)
        
         | Jonovono wrote:
         | MCP is not REST. In your comparison, its more that MCP is a
         | protocol for _discovering_ REST endpoints at runtime and
         | letting users configure what REST endpoints should be used at
         | runtime.
         | 
         | Say i'm building a app and I want my users to be able to play
         | spotify songs. Yea, i'll hit the spotify api. But now, say i've
         | launched my app, and I want my users to be able to play a song
         | from sonofm when they hit play. Alright, now I gotta open up
         | the code and do some if statements hard code the sonofm api and
         | ship a new version, show some update messages.
         | 
         | MCP is literally just a way to make this extensible so instead
         | of hardcoding this in, it can be configured at runtime
        
           | nikolayasdf123 wrote:
           | so... is this OpenAPI then?
        
             | lobsterthief wrote:
             | Basically, yes. But with much more enthusiasm!
        
             | doug_durham wrote:
             | OpenAPI doesn't have a baked in discoverability mechanism.
             | It isn't compatible with LLMs out of the box. It is a lower
             | level abstraction. I don't want to write a blob of code
             | that talks to an Open API service every time I want to do
             | something with an LLM.
        
           | layer8 wrote:
           | HATEOAS was supposed to be that.
           | 
           | https://en.wikipedia.org/wiki/HATEOAS
        
             | Jonovono wrote:
             | heh, there was a good convo about HATEOAS and MCP on HN
             | awhile back:
             | 
             | * https://news.ycombinator.com/item?id=43307225
             | 
             | * https://www.ondr.sh/blog/ai-web
        
             | mort96 wrote:
             | Wait was it? HATEOAS is all about hypermedia, which means
             | there must be a human in the loop being presented the
             | rendered hypermedia. MCP seems like it's meant to be for
             | machine<->machine communication, not human<->machine
        
               | layer8 wrote:
               | I agree that HATEOAS never made sense without a human in
               | the loop, although I also have never seen it be described
               | as such. IMO that's an important reason why it never
               | gained useful traction.
               | 
               | There is a confused history where Roy Fielding described
               | REST, then people applied some of that to JSON HTTP APIs,
               | designating those as REST APIs, then Roy Fielding said
               | "no you have to do HATEOAS to achieve what I meant by
               | REST", then some people tried to make their REST APIs
               | conform to HATEOAS, all the while that change was of no
               | use to REST clients.
               | 
               | But now with AI it actually can make sense, because the
               | AI is able to dynamically interpret the hypermedia
               | content similar to a human.
        
               | NomDePlum wrote:
               | My understanding was that the discoverable part of
               | HATEAOS was meant for machine to machine. Actually all of
               | REST is machine to machine except in very trivial
               | situations.
               | 
               | Not sure I'm understanding your point in hypermedia means
               | there is human in the loop. Can you expand?
        
               | renerick wrote:
               | H in HATEOAS stands for "hypermedia". Hypermedia is a
               | type of document that includes hypermedia controls, which
               | are presented by the hypermedia client to a user for
               | interaction. It's the user who makes decision what
               | controls to interact with. For example, when I'm writing
               | this comment, HN server gave a hypermedia document, which
               | contains your comment, a textarea input and a button to
               | submit my reply, and me, the human in the loop, decides
               | what to put in it the input and when to press the button.
               | A machine can't do that on its own (but LLMs potentially
               | can), so a user is required. That also means that JSON
               | APIs meant for purely machine to machine interactions,
               | commonly referred to as REST, can't be considered HATEOAS
               | (and REST) due to absence of hypermedia controls.
               | 
               | Further reading:
               | 
               | - https://htmx.org/essays/how-did-rest-come-to-mean-the-
               | opposi...
               | 
               | - https://htmx.org/essays/hateoas/
        
               | NomDePlum wrote:
               | So that's not my understanding. Hypermedia, as I
               | understand it, are embedded links in responses that
               | present possible forward actions.
               | 
               | They are structured in a way that machine program could
               | parse and use.
               | 
               | I don't believe it requires human-in-the-loop, although
               | that is of course possible.
        
               | mort96 wrote:
               | If you have machine <-> machine interaction, why would
               | you use HTML with forms and buttons and text inputs etc?
               | Wouldn't JSON or something else (even XML) make more
               | sense?
        
               | chriswarbo wrote:
               | Hypermedia isn't just for human consumption. Back in the
               | 90s, the Web was going to be crawled by "User Agents":
               | software performing tasks on behalf of people (say,
               | finding good deals on certain items; or whatever). Web
               | browsers (human-driven interfaces) were the most common
               | User Agent, but ended up being a lowest-common-
               | denominator; the only other User Agents to get any
               | widespread support were Google crawlers.
        
           | jaredsohn wrote:
           | Feels like segment.com but for calling APIs rather than
           | adding libraries to the frontend.
        
           | gavinray wrote:
           | MCP is a JSON RPC implementation of OpenAPI, or, get this,
           | XML and WSDL/SOAP.
        
         | caust1c wrote:
         | In my mind the only thing novel about MCP is requiring the
         | schema is provided as part of the protocol. Like, sure it's
         | convenient that the shape of the requests/response wrappers are
         | all the same, that certainly helps with management using
         | libraries that can wrap dynamic types in static types, but
         | everyone was already doing that with APIs already we just
         | didn't agree on what that envelope's shape should be. BUT, with
         | the requirement that schema be provided with the protocol, and
         | the carrot of AI models seamlessly consuming it, that was
         | enough of an impetus.
        
           | marcosdumay wrote:
           | > the only thing novel about MCP is requiring the schema is
           | provided as part of the protocol
           | 
           | You mean, like OpenAPI, gRPC, SOAP, and CORBA?
        
             | sneak wrote:
             | You can't connect to a gRPC endpoint and ask to download
             | the client protobuf, but yes.
        
               | ahmedtd wrote:
               | It's not enabled by default, but you can --- gRPC
               | Reflection:
               | 
               | * https://github.com/grpc/grpc-
               | java/blob/master/documentation/...
               | 
               | * https://grpc.io/docs/guides/reflection/
               | 
               | You can then use generic tools like grpc_cli or grpcurl
               | to list available services and methods, and call them.
        
             | doug_durham wrote:
             | Where is the mandatory human readable prose description of
             | the purpose of the tool in any of those specs. It isn't.
             | Also the simplicity of JSON interface descriptions is key.
        
         | TZubiri wrote:
         | Damn, I just read this and it's comforting to see how similar
         | it is to my own response.
         | 
         | To elaborate on this, I don't know much about MCP, but usually
         | when people speak about it is in a buzzword-seeking kind of
         | way, and the people that are interested in it make these kinds
         | of conceptual snafus.
         | 
         | Second, and this applies not just to MCP, but even things like
         | JSON, Rust, MongoDB. There's this phenomenon where people learn
         | the complex stuff before learning the basics. It's not the
         | first time I've cited this video on Homer studying marketing
         | where he reads the books out of order
         | https://www.youtube.com/watch?v=2BT7_owW2sU . It makes sense
         | that this mistake is so common, the amount of literature and
         | resources is like an inverted pyramid, there's so little
         | classical foundations and A LOT of new stuff, most of which
         | will not stand the test of time. Typically you have
         | universities to lead the way and establish a classical corpus
         | and path, but being such a young discipline, 70 years in and we
         | are still not finding much stability, Universities have gone
         | from teaching C, to teaching Java, to teaching Python (at least
         | in intro to CS), maybe they will teach Rust next, but this
         | buzzwording seems more in line with trying to predict the
         | future, and there will be way more losers than winners in that
         | realm. And the winners will have learned the classicals in
         | addition to the new technology, learning the new stuff without
         | the classics is a recipe for disaster.
        
         | gdecaso wrote:
         | The main difference between MCP and REST is `list-tools`.
         | 
         | REST APIs have 5 or 6 ways of doing that, including "read it
         | from our docs site", HATEOAS, OAS running on an endpoint as
         | part of the API.
         | 
         | MCP has a single way of listing endpoints.
        
           | gavinray wrote:
           | WSDL + XML API's have been around since 1998.
           | 
           | OpenAPI, OData, gRPC, GraphQL
           | 
           | I'm sure I'm missing a few...
        
             | doug_durham wrote:
             | Where is "list-tools" in any of those low level protocols?
        
           | OJFord wrote:
           | > The main difference between MCP and REST is `list-tools`.
           | 
           | > REST APIs have 5 or 6 ways of doing that
           | 
           | You think nobody's ever going to publish a slight different
           | standard to Anthropic's MCP that is also primarily intended
           | for LLMs?
        
             | doug_durham wrote:
             | Why would they? I'm sure the "Enterprise" folks are putting
             | together some working group to develop ANSI-xyzzy standard
             | for Enterprise operability which will never see the light
             | of day.
        
         | rco8786 wrote:
         | One major difference is that MCP has discovery built into the
         | protocol. There's nothing in REST that informs clients what the
         | API can do, what resources are available, etc.
        
       | quotemstr wrote:
       | It's articles like this that tell you we're close to peak hype.
       | There's nothing revolutionary about a text encoding plus a
       | schema. SOAP could do this 20 years ago.
        
         | AnotherGoodName wrote:
         | SOAP was worse than horrendous though. I'm sure i'm not the
         | only one hit by 'well Java SOAP and .net SOAP encode
         | differently so they don't work together well' (let alone all
         | the other different implementations each with their own similar
         | differences).
         | 
         | Or how about 'oh it looks like your client is using SOAP 1.2
         | but the server is 1.1 and they are incompatible'. That was
         | seriously a thing. Good luck talking to many different servers
         | with different versions.
         | 
         | SOAP wasn't just bad. It was essentially only useable between
         | same languages and versions. Which is an interesting issue for
         | a layer whose entire purpose was interoperability.
        
         | rikafurude21 wrote:
         | This reminded me of that HN comment on the Dropbox announcement
         | post where the user says that theres nothing new about it since
         | FTP and USB-sticks exist. Also, anyone who ever had the
         | misfortune of using SOAP know how horrendeous it is. Truth is,
         | sometimes the "new thing" does it better and wins out.
         | Applications have standardized APIs now because of AI hype.
         | This is a step in the right direction
        
       | jampa wrote:
       | I don't want to sound like a skeptic, but I see way more people
       | talking about how awesome MCP is rather than people building cool
       | things with it. Reminds me of blockchain hype.
       | 
       | MCP seems like a more "in-between" step until the AI models get
       | better. I imagine in 2 years, instead of using an MCP, we will
       | point to the tool's documentation or OpenAPI, and the AI can
       | ingest the whole context without the middle layer.
        
         | bryancoxwell wrote:
         | But this whole post is about using MCP sans AI
        
           | iLoveOncall wrote:
           | MCP without AI is just APIs.
           | 
           | MCP is already a useless layer between AIs and APIs, using it
           | when you don't even have GenAI is simply idiotic.
           | 
           | The only redeeming quality of MCP is actually that it has
           | pushed software vendors to expose APIs to users, but just use
           | those directly...
        
             | ricardobeat wrote:
             | And that's the whole point - it's APIs we did not have. Now
             | app developers are encouraged to have a public, user
             | friendly, fully functional API made for individual use,
             | instead of locking them behind enterprise contracts and
             | crippling usage limits.
        
               | weird-eye-issue wrote:
               | MCPs don't change that at all lol
        
               | iLoveOncall wrote:
               | Right, but we would have had them even if MCP did not
               | exist. The need to access those APIs via LLM-based
               | "agents" would have existed without MCP.
               | 
               | At work I built an LLM-based system that invoke tools. We
               | started before MCP existed, and just used APIs (and
               | continue to do so).
               | 
               | Its engineering value is nil, it only has marketing value
               | (at best).
        
               | Maxious wrote:
               | As https://www.stainless.com/blog/mcp-is-eating-the-world
               | --and-... recaps, tool calling existed before MCP, some
               | vague standards existed, nothing took off, no really
               | normal users don't want to just download the OpenAPI
               | spec.
               | 
               | Anthropic wants to define another standard now btw
               | https://www.anthropic.com/engineering/desktop-extensions
        
               | iLoveOncall wrote:
               | Normal users don't know what MCP is and will never use an
               | MCP server (knowingly or unknowingly) in their life. They
               | use ChatGPT through the web UI or the mobile app, that's
               | it.
               | 
               | MCP is for technical users.
               | 
               | (Maybe read the link you sent, it has nothing to do with
               | defining a new standard)
        
               | drivers99 wrote:
               | > it's APIs we did not have
               | 
               | Isn't that what we had about 20 years ago (web 2.0) until
               | they locked it all up (the APIs and feeds) again? ref:
               | this video posted 18 years ago:
               | https://www.youtube.com/watch?v=6gmP4nk0EOE
               | 
               | (Rewatching it in 2025, the part about "teaching the
               | Machine" has a different connotation now.)
               | 
               | Maybe it's that the protocol is more universal than
               | before, and they're opening things up more due to the
               | current trends (AI/LLM vs web 2.0 i.e. creating site
               | mashups for users)? If it follows the same trend then
               | after a while it will become enshittified as well.
        
               | candiddevmike wrote:
               | Do you have an example of a company who previously had an
               | undiscoverable API now offering a MCP-based alternative?
        
         | qsort wrote:
         | Regardless of how good a model gets, it can't do much if it
         | doesn't have access to deterministic tools and information
         | about the state of the world. And that's before you take into
         | account security: you can't have a model running arbitrary
         | requests against production, that's psychotic.
         | 
         | I don't have a high opinion of MCP and the hype it's generating
         | is ridicolous, but the problem it supposedly solves is real. If
         | it can work as an excuse to have providers expose an API for
         | their functionality like the article hopes, that's exciting for
         | developers.
        
         | dghlsakjg wrote:
         | > we will point to the tool's documentation or OpenAPI
         | 
         | You can already do this as long as your client has access to a
         | HTTP MCP.
         | 
         | You can give the current generation of models an openAPI spec
         | and it will know exactly what to do with it.
        
           | nikolayasdf123 wrote:
           | you don't even need MCP for that. just access to hosted
           | swagger file.
        
             | dghlsakjg wrote:
             | That's what I mean. Give an LLM the swagger file, and it
             | can make those calls itself given the ability to make an
             | HTTP request (which is what the MCP is for)
        
         | caust1c wrote:
         | It's incredible for investigating audit logs. Our customers use
         | it daily.
         | 
         | https://blog.runreveal.com/introducing-runreveal-remote-mcp-...
        
         | arbuge wrote:
         | I could see that happening... perhaps instead of plugging in
         | the URL of the MCP server you'd like to use, you'd just put in
         | the URL of their online documentation and trust your AI
         | assistant of choice to go through all of it.
        
         | mtkd wrote:
         | It's very different to blockchain hype
         | 
         | I had similar skepticism initially, but I would recommend you
         | dip toe in water on it before making judgement
         | 
         | The conversational/voice AI tech now dropping + the current
         | LLMs + MCP/tools/functions to mix in vendor APIs and private
         | data/services etc. really feels like a new frontier
         | 
         | It's not 100% but it's close enough for a lot of usecases now
         | and going to change a lot of ways we build apps going forward
        
           | moooo99 wrote:
           | Probably my judgement is a bit fogged. But if I get asked
           | about building AI into our apps just one more time I am
           | absolutely going to drop my job and switch careers
        
             | mtkd wrote:
             | That's likely because OG devs have been seeing the
             | hallucination stuff, unpredicability etc. and questioning
             | how that fits with their carefully curated perfect system
             | 
             | What blocked me initially was watching NDA'd demos a year
             | or two back from a couple of big software vendors on how
             | Agents were going to transform enterprise ... what they
             | were showing was a complete non-starter to anyone who had
             | worked in a corporate because of security, compliance, HR,
             | silos etc. so I dismissed it
             | 
             | This MCP stuff solves that, it gives you (the enterprise)
             | control in your own walled garden, whilst getting the gains
             | from LLMs, voice etc. ... the sum of the parts is massive
             | 
             | It more likely wraps existing apps than integrates directly
             | with them, the legacy systems becoming data or function
             | providers (I know you've heard that before ... but so far
             | this feels different when you work with it)
        
               | bwfan123 wrote:
               | There are 2 kinds of usecases that software automates. 1)
               | those that require accuracy and 2) those that dont
               | (social media, ads, recommendations).
               | 
               | Further, there are 2 kinds of users that consume the
               | output of software. a) humans, and b) machines.
               | 
               | Where LLMs shine are in the 2a usecases, ie, usecases
               | where accuracy does not matter and humans are end-users.
               | there are plenty of these usecases.
               | 
               | The problem is that LLMs are being applied to 1a, 1b
               | usecases where there is going to be a lot of frustration.
        
               | mtkd wrote:
               | https://www.withriviera.com/
        
               | moooo99 wrote:
               | > That's likely because OG devs have been seeing the
               | hallucination stuff, unpredicability etc. and questioning
               | how that fits with their carefully curated perfect system
               | 
               | That is the odd part. I am far from being part of that
               | group of people. I'm only 25, I joined the industry in
               | 2018 as part of an training program in a large
               | enterprise.
               | 
               | The odd part is, many of the promises are a bit Deja-vu
               | even for me. ,,Agents going to transform the enterprise"
               | and other promises do not seem that far off the promises
               | that were made during the low code hype cycle.
               | 
               | Cynically, the more I look at the AI projects as an
               | outsider, the more I think AI could fail in enterprises
               | largely because of the same reason low code did.
               | Organizations are made of people and people are messy, as
               | a result the data is often equally messy.
        
               | ptx wrote:
               | How does MCP solve any of the problems you mentioned? The
               | LLM still has to access your data, still doesn't know the
               | difference between instructions and data, and still gives
               | you hallucinated nonsense back - unless there's some
               | truly magical component to this protocol that I'm
               | missing.
        
               | doug_durham wrote:
               | The information returned by the MCP server is what makes
               | it not hallucinate. That's one of the primary use cases.
        
         | TZubiri wrote:
         | I wasn't able to find a good source on it, but I read a couple
         | of times that Anthropic (builders of MCP) do
         | astroturfing/shilling/growth hacking/SEO/organic advertisement.
         | Everything I've read so far with MCP and Claude and the hype I
         | see on social media is consistent with that, hype and no value.
        
           | jasondclinton wrote:
           | This is false.
        
         | ashwinsundar wrote:
         | I had a use case - I wanted to know what the congresspeople
         | from my state have done this week. This information is
         | surprisingly hard to just get from the news. I learned about
         | MCP a few months ago and thought that it might be a cool way to
         | interact with the congress.gov API.
         | 
         | I made this MCP server so that you could chat with real-time
         | data coming from the API -
         | https://github.com/AshwinSundar/congress_gov_mcp. I've actually
         | started using it more to find out, well, what the US Congress
         | is actually up to!
        
         | doug_durham wrote:
         | Me and my colleagues are building cools stuff with it. I see
         | many examples of truly useful things being build today.
        
         | 3abiton wrote:
         | > MCP seems like a more "in-between" step until the AI models
         | get better. I imagine in 2 years, instead of using an MCP, we
         | will point to the tool's documentation or OpenAPI, and the AI
         | can ingest the whole context without the middle layer.
         | 
         | I doubt the middleware will disappear, it's needed to accomdate
         | the evolving architecture of LLMs.
        
         | beefnugs wrote:
         | I can't believe there isn't a universal "api/firewall" by now.
         | You know like a middle program that can convert any input api
         | to any output api. With middleware features like
         | logging/firewall/stateful denial and control.
         | 
         | Once cryptocurrency was a thing this absolutely needed to exist
         | to protect your accounts from being depleted by a hack. (like
         | via monthly limits firewall)
         | 
         | Now we need universal MCP <-> API to allow both programmatic
         | and LLM to the same thing. (because apparently these AGI
         | precursors arent smart enough to be trained on generic API
         | calling and need yet another standard: MCP?)
        
       | superluserdo wrote:
       | Seems like we're just currently in the top-right of this comic
       | https://xkcd.com/2044/
        
         | readthenotes1 wrote:
         | Someone should write an AI tool that evaluates every top
         | article in hacker News and provides the appropriate XKCD comic
         | as a comment.
        
           | dexterdog wrote:
           | And then a few steps later it's just bots talking to bots.
           | Then what did we read when we're on the loo?
        
       | OJFord wrote:
       | HTTP: A (Deliberately) Universal Plugin System
        
       | phh wrote:
       | I agree with the article, and I love how the author is
       | (mis-)using MCP. I just want to rephrase what the accident
       | actually is.
       | 
       | The accident isn't that somehow we got a protocol to do things we
       | couldn't do before. As other comments point out MCP (the
       | specificaiton), isn't anything new or interesting.
       | 
       | No, the accident is that the AI Agent wave made interoperability
       | hype, and vendor lock-in old-fashioned.
       | 
       | I don't know how long it'll last, but I sure appreciate it.
        
         | iLoveOncall wrote:
         | > I don't know how long it'll last
         | 
         | I'm just baffled no software vendor has already come up with a
         | subscription to access the API via MCP.
         | 
         | I mean obviously paid API access is nothing new, but "paid MCP
         | access for our entreprise users" is surely on the pipeline
         | everywhere, after which the openness will die down.
        
           | Bjartr wrote:
           | And I expect there'll eventually be a way for an AI to pay
           | for an MCP use microtransaction style.
           | 
           | Heck, if AIs are at some point given enough autonomy to
           | simply be given a task and a budget, there'll be efforts to
           | try to trick AIs into thinking paying is the best way to get
           | their work done! Ads (and scams) for AIs to fall for!
        
             | iLoveOncall wrote:
             | > Heck, if AIs are at some point given enough autonomy to
             | simply be given a task and a budget, there'll be efforts to
             | try to trick AIs into thinking paying is the best way to
             | get their work done!
             | 
             | We're already there, just take a look at the people
             | spending $500 a day on Claude Code.
        
           | adamesque wrote:
           | I think for enterprise it's going to become part of the
           | subscription you're already paying for, not a new line item.
           | And then prices will simply rise.
           | 
           | Optionality will kill adoption, and these things are
           | absolutely things you HAVE to be able to play with to
           | discover the value (because it's a new and very weird kind of
           | tool that doesn't work like existing tools)
        
           | pininja wrote:
           | Mapbox is just a small step away from that with their MCP
           | server wrapping their pay-by-use API. I wouldn't be surprised
           | to see a subscription offering with usage limits if that
           | somehow appealed to them. MapTiler already offers their
           | service as a subscription so they're even closer if they
           | hosted a server like this on their own.
           | 
           | https://github.com/mapbox/mcp-server
        
         | sshine wrote:
         | Hype, certainly.
         | 
         | But the way I see it, AI agents created incentives for
         | interoperability. Who needs an API when everyone is job secure
         | via being a slow desktop user?
         | 
         | Well, your new personal assistant who charges by the Watt hour
         | NEEDS it. Like when the CEO will personally drive to get pizzas
         | for that hackathon because that's practically free labor, so
         | does everyone want everything connected.
         | 
         | For those of us who rode the API wave before integrating became
         | hand-wavey, it sure feels like the world caught up.
         | 
         | I hope it will last, but I don't know either.
        
           | mh- wrote:
           | Unfortunately, I think we're equally likely to see
           | shortsighted lock-in attempts like this [0] one from Slack.
           | 
           | I tried to find a rebuttal to this article from Slack, but
           | couldn't. I'm on a flight with slow wifi though. If someone
           | from Slack wants to chime in that'd be swell, too.
           | 
           | I've made the argument to CFOs multiple times over the years
           | why we should continue to pay for Slack instead of just using
           | Teams, but y'all are really making that harder and harder.
           | 
           | [0]: https://www.reuters.com/business/salesforce-blocks-ai-
           | rivals...
        
             | ebiester wrote:
             | It's going to take more people willing to move away from
             | slack for those purposes.
             | 
             | As it is, I'm going to propose that we move more key
             | conversations outside of slack so that we can take
             | advantage of feeding it into ai. It's a small jump from
             | that to looking for alternatives.
        
             | dgacmu wrote:
             | I'm happier we went with Zulip each day.
        
             | SoftTalker wrote:
             | Sounds sort of like an innovator's dilemma response. New
             | technology appears and the response is gatekeeping and
             | building walls rather than adaptation.
        
         | bitwize wrote:
         | Remember Web 2.0? Remember the semantic web? Remember
         | folksonomies? Mash-ups? The end of information silos? The
         | democratizing power of HTTP APIs?Anyone? Anyone?
        
           | karaterobot wrote:
           | I don't understand your point. Some of those things were
           | buzzwords, some were impossible dreams, some changed the way
           | the web works completely. Are you just saying that the future
           | is unknown?
        
             | klabb3 wrote:
             | No. What they are saying is best said with a quote from
             | Battlestar Galactica:
             | 
             | > All of this has happened before, and all of this will
             | happen again.
             | 
             | "It" here being the boom and inevitable bust of interop and
             | open API access between products, vendors and so on. As a
             | millenial, my flame of hope was lit during the API
             | explosion of Web 2.0. If you're older, your dreams were
             | probably crushed already by something earlier. If you're
             | younger, and you're genuinely excited about MCP for the
             | potential explosion in interop, hit me up for a bulk
             | discount on napkins.
        
               | bwfan123 wrote:
               | And then, there are "architecture astronaut"s dreaming of
               | an entire internet of MCP speaking devices - an "internet
               | of agents" if you will. That is now requiring a separate
               | DNS, SMTP, BGP etc. for that internet.
        
               | fragmede wrote:
               | I'm older and would like a discount please. The "this
               | time it's different" energy is because assuming a human
               | can interact with the system, and that vision models can
               | drive a gui, who cares if there's an actual API, just
               | have the AI interact with the system as if it was coming
               | in as a human.
        
               | danielrico wrote:
               | I think battlestar Galactica must be quoting one of the
               | Eddas. I've only read if it from Borges in Spanish, but
               | Conner the same meaning: "Estas cosas han pasado. Estas
               | cosas tambien pasaran."
        
             | potatolicious wrote:
             | I take their point to be that the underlying incentives
             | haven't changed. The same forces and incentives that
             | scuttled those things are likely to scuttle this as well.
             | 
             | I actually disagree with the OP in this sub-thread:
             | 
             | > _" No, the accident is that the AI Agent wave made
             | interoperability hype, and vendor lock-in old-fashioned."_
             | 
             | I don't think that's happened at all. I think some
             | interoperability will be here to say - but those are
             | overwhelmingly the products where interoperability was
             | already the norm. The enterprise SaaS that your company is
             | paying for will support their MCP servers. But they also
             | probably already support various other plugin interfaces.
             | 
             | And they're not doing this because of hype or new-
             | fangledness, but because their incentives are aligned with
             | interoperability. If their SaaS plugins into [some other
             | thing] it increases their sales. In fact the lowering of
             | integration effort is all upside for them.
             | 
             | Where this is going to run into a brick wall (and I'd
             | argue: already has to some degree) is that closed platforms
             | that aren't incentivized to be interoperable still won't
             | be. I don't think we've really moved the needle on that
             | yet. Uber Eats is not champing at the bit to build the MCP
             | server that orders your dinner.
             | 
             | And there are a lot of really good reasons for this. In a
             | previous job I worked on a popular voice assistant that
             | integrated with numerous third-party services. There has
             | always been vehement pushback to voice assistant
             | integration (the ur-agent and to some degree still the holy
             | grail) because it necessarily entails the service declaring
             | near-total surrender about the user experience. An "Uber
             | Eats MCP" is one that Uber has comparatively little control
             | over the UX of, and has poor ability to constrain poor
             | customer experiences. They are right to doubt this stuff.
             | 
             | I also take some minor issue with the blog: the problem
             | with MCP as the "everything API" is that you _can 't_
             | really take the "AI" part out of it. MCP tools are not
             | guaranteed to communicate in structured formats! Instead of
             | getting an HTTP 401 you will get a natural language string
             | like "You cannot access this content because the author
             | hasn't shared it with you."
             | 
             | That's not useful without the presence of a NL-capable
             | component in your system. It's not parseable!
             | 
             | Also importantly, MCP inputs and outputs are
             | _intentionally_ not versioned nor encouraged to be stable.
             | Devs are encouraged to alter their input and output formats
             | to make them more accessible to LLMs. So your MCP interface
             | can and likely will change without notice. None of this
             | makes for good API for systems that aren 't self-adaptive
             | to that sort of thing (i.e., LLMs).
        
           | apgwoz wrote:
           | I think we found a new backronym for MCP: Mashup Context
           | Protocol.
           | 
           | (The mashup hype was incredible, btw. Some of the most
           | ridiculous web contraptions ever.)
        
           | kasey_junk wrote:
           | Yes. Pieces of all of those things surround us now. And where
           | we are wrt locking and interop is far beyond where we were
           | when each of those fads happened.
           | 
           | Mcp is a fad, it's not long term tech. But I'm betting
           | shoveling data at llm agents isn't. The benefits are too high
           | for companies to allow vendors to lock the data away from
           | them.
        
             | fragmede wrote:
             | I know we're all just soaked by a wave of hype right now
             | but I think MCP will go the way of other "but it works"
             | tech, like zip files, RSS and shell scripts.
        
             | overfeed wrote:
             | > Mcp is a fad, it's not long term tech
             | 
             | One that won't be supported by any of the big names except
             | to suck data into their walled gardens and lock it up. We
             | all know the playbook.
        
           | aorloff wrote:
           | Nobody remembers the semantic web anymore
        
             | walterbell wrote:
             | Palantir remembers..
             | 
             | https://www.palantir.com/docs/foundry/ontology/overview
        
           | overfeed wrote:
           | Yahoo Pipes, XMPP, self-hosted blogs, RSS-based social
           | networks, pingbacks; the democratized p2p web that briefly
           | was. I bet capitalism will go 2 for 2 against the naive
           | idealism that gatekeepers will stop gatekeeping.
        
         | adregan wrote:
         | How ironic given the amount of APIs that were locking down
         | access in response to AI training!
         | 
         | Though the general API lockdown was started long before that,
         | and like you, I'm skeptical that this new wave of open access
         | will last if the promise doesn't live up to the hype.
        
           | TimTheTinker wrote:
           | MCP is supposed to grant "agency" (whatever that means), not
           | merely expose curated data and functionality.
           | 
           | In practice, the distinction is little more than the
           | difference between different HTTP verbs, but I think there is
           | a real difference in what people are intending to enable when
           | creating an MCP server vs. standard APIs.
        
             | adregan wrote:
             | Might be another reflection of McLuhan's "the medium is the
             | message" in that APIs are built with the intended interface
             | in mind.
             | 
             | To this point, GUIs; going forward, AI agents. While the
             | intention rhymes, the meaning of these systems diverge.
        
           | notatoad wrote:
           | i don't think it's ironic at all. the AI boom exposed the
           | value of data. there's two inevitable consequences when the
           | value of something goes up: the people who were previously
           | giving it away for free start charging for it, and the people
           | who weren't previously selling it at all start selling it.
           | 
           | the APIs that used to be free and now aren't were just
           | slightly ahead of the game, all these new MCP servers aren't
           | going to be free either.
        
         | mellosouls wrote:
         | _the AI Agent wave made interoperability hype, and vendor lock-
         | in old-fashioned_
         | 
         | Perhaps but we see current hypes like Cursor only using MCP one
         | way; you can feed into Cursor (eg. browser tools), but not out
         | (eg. conversation history, context etc).
         | 
         | I love Cursor but this "not giving back" mentality originally
         | reflected in it's closed source forking of VS Code leaves an
         | unpleasant taste in the mouth and I believe will ultimately see
         | it lose developer credibility.
         | 
         | Lock-in still seems to be locked in.
        
           | talos_ wrote:
           | The VSCode extension Continue provides similar capabilities
           | and gives you full access to your interaction traces (local
           | database and JSON traces)
        
         | visarga wrote:
         | The main benefit is not that it made interoperability
         | fashionable, or that it make things easy to interconnect. It is
         | the LLM itself, if it knows how to wield tools. It's like you
         | build a backend and the front-end is not your job anymore, AI
         | does it.
         | 
         | In my experience Claude and Gemini can take over tool use and
         | all we need to do is tell them the goal. This is huge, we
         | always had to specify the steps to achieve anything on a
         | computer before. Writing a fixed program to deal with dynamic
         | process is hard, while a LLM can adapt on the fly.
        
           | freeone3000 wrote:
           | The issue holding us back was never that we had to write a
           | frontend -- it was the data locked behind proprietary
           | databases and interfaces. Gated behind API keys and bot
           | checks and captchas and scraper protection. And now we can
           | have an MCP integrator for IFTTT and have back the web we
           | were promised, at least for a while.
        
             | whitten wrote:
             | what is IFTTT ?
        
               | lazyasciiart wrote:
               | If this then that - a zapier type glue provider.
        
               | Mtinie wrote:
               | Minor chronological point but Zapier is an IFTTT-type
               | glue provider.
               | 
               | IFTTT was announced Dec. 14, 2010 and launched on Sept.
               | 7. 2011.
               | 
               | Zapier was first pitched Sept. 30, 2011 and their public
               | beta launched May 2012.
        
           | HumanOstrich wrote:
           | I don't understand what you mean.
           | 
           | > It (the main benefit?) is the LLM itself, if it knows how
           | to wield tools.
           | 
           | LLMs and their ability to use tools are not a benefit or
           | feature that arose from MCP. There has been tool
           | usage/support with various protocols and conventions way
           | before MCP.
           | 
           | MCP doesn't have any novel aspects that are making it
           | successful. It's relatively simple and easy to understand
           | (for humans), and luck was on Anthropic's side. So people
           | were able to quickly write many kinds of MCP servers and it
           | exploded in popularity.
           | 
           | Interoperability and interconnecting tools, APIs, and models
           | across providers are the main benefits of MCP, driven by its
           | wide-scale adoption.
        
         | Animats wrote:
         | > Want spell check? MCP server.
         | 
         | > Want it to order coffee when you complete 10 tasks? MCP
         | server.
         | 
         | With a trip through an LLM for each trivial request? A _paid_
         | trip? With high overhead and costs?
        
           | notatoad wrote:
           | the whole point of the article is that it _doesn 't_ need to
           | be an LLM, MCP is just a standard way to expose tools to
           | things that use tools. LLMs _can_ use tools, but so can
           | humans.
        
             | therein wrote:
             | So the whole point of the article is that an API is an API
             | and anything can call an API?
        
               | lazyasciiart wrote:
               | Maybe phrasing it this way will be the lightbulb moment
               | for everyone who hasn't got that yet.
        
               | tveita wrote:
               | There is a long tail of applications that are not
               | currently scriptable or have a public API. The kind that
               | every so often make you think "if only I could automate
               | this instead of clicking through this exact same dialog
               | 25 times"
               | 
               | Before, "add a public API to this comic reader/music
               | player/home accounting software/CD archive manager/etc."
               | would be a niche feature to benefit 1% of users. Now more
               | people will expect to hook up their AI assistant of
               | choice, so the feature can be prioritized.
               | 
               | The early MCP implementations will be for things that
               | already have an API, which by itself is underwhelming.
               | 
               | You would think Apple would have a leg up here with
               | AppleScript already being a sanctioned way to add
               | scriptable actions across the whole of macOS, but as far
               | as I can tell they don't hook it up to Siri or Apple
               | Intelligence in any way.
        
               | dstanko wrote:
               | I see the point as "let's not overcomplicate the API with
               | complex schemas and such. Lets not use GraphQL for
               | everything. Just create a simple API and call it to
               | extend stuff. Am I wrong?
        
             | OkGoDoIt wrote:
             | Part of the reason AI agents and MCP work is because AI can
             | programmatically at runtime determine what plug-ins to use.
             | Without the AI part, how does the host app know when to
             | call a MCP server function?
        
         | conradev wrote:
         | AI agents didn't only make adversarial interoperability hype,
         | they've also made it inevitable! From here all the way until
         | they're probing hardware to port Linux and write drivers.
        
         | exe34 wrote:
         | > made interoperability hype, and vendor lock-in old-fashioned
         | 
         | I always imagined software could be written with a core that
         | does the work and the UI would be interchangeable. I like that
         | the current LLM hype is causing it to happen.
        
         | stavros wrote:
         | I haven't seen an app that didn't have an API create one via
         | MCP. The only MCP servers I've seen were for things that I
         | could already access programmatically.
        
         | alexpotato wrote:
         | Reminds me of the days of Winsock.
         | 
         | For those that don't remember/don't know, everything network
         | related in Windows used to use their own, proprietary setup.
         | 
         | Then one day, a bunch of vendors got together and decided to
         | have a shared standard to the benefit of basically everyone.
         | 
         | https://en.wikipedia.org/wiki/Winsock
        
       | furyofantares wrote:
       | Agents (presumably) increase the demand for APIs and if those
       | APIs as well as already existing APIs get exposed as MCPs then I
       | can see it.
       | 
       | It is dependent on agents actually creating new demand for APIs
       | and MCP being successful as a way to expose them.
        
       | taytus wrote:
       | The author glosses over some practical realities. Just because
       | something can be repurposed doesn't mean it should be. MCP was
       | designed with specific assumptions about how AI models consume
       | and process information. Using it as a general plugin system
       | might work, but you'd likely hit limitations around things like
       | authentication, real-time communication, or complex data flows
       | that weren't priorities for the AI use case.
        
       | bigmattystyles wrote:
       | I thought MCPs just 'figured out' using docs how to call a
       | program's API. Won't it matter that many APIs just suck?
        
       | b0a04gl wrote:
       | before we just figured out apis ,read some docs ,guessed and
       | moved on... now apis gotta work for llms they don't read anything
       | they just parse ,so standardising shifts... from neat docs to
       | explainable api specs. schema + inputs + reflection + docstrings
       | + specs + X . else agent just skips it. we are not only the
       | consumer now
        
       | inheritedwisdom wrote:
       | Lowering the bar to integrate and communicate is what has
       | historically allowed technology to reach critical mass and
       | enabled adoption. MCP is an evolution in that respect and
       | shouldn't be disregarded.
       | 
       | We had a non technical team member write an agent to clean up a
       | file share. There are hundreds of programming languages,
       | libraries, and apis that enabled that before MCP but now people
       | don't even have to think about it. Is it performant no, is it the
       | "best" implementation absolutely not. Did it create enormous
       | value in a novel way that was not possible with the resources,
       | time, technology we had before 100%. And that's the point.
        
         | citizenpaul wrote:
         | >non technical team member write an agent to clean up a file
         | share
         | 
         | This has to be BS(or you think its true) unless it was like
         | 1000 files. In my entire career I've seen countless crazy file
         | shares that are barely functional chaos. In nearly ever single
         | "cleanup" attempt I've tried to get literally ANYONE from the
         | relevant department to help with little success. That is just
         | for ME to do the work FOR THEM. I just need context from them.
         | I've on countless occasion had to go to senior management to
         | force someone to simply sit with me for an hour to go over the
         | schema they want to try to implement. SO I CAN DO IT FOR THEM
         | and they don't want to do it and literally seemed incapable of
         | doing so when forced to. COUNTLESS Times. This is how I know AI
         | is being shilled HARD.
         | 
         | If this is true then I bet you anything in about 3-6 months you
         | guys are going to be recovering this file system from backups.
         | There is absolutely no way it was done correctly and no one has
         | bothered to notice yet. I'll accept your downvote for now.
         | 
         | Cleaning up a file share is 50% politics, 20% updating
         | procedures, 20% training and 10% technical. I've seen companies
         | go code red and practically grind to a halt over a months long
         | planned file share change. I've seen them rolled back after
         | months of work. I've seen this fracture the files shares into
         | insane duplication(or more) because despite the fact it was
         | coordinated, senior managers did not as much as inform their
         | department(but attended meetings and signed off on things) and
         | now its too late to go back because some departments converted
         | and some did not. I've seen helpdesk staff go home "sick"
         | because they could not take the volume of calls and abuse from
         | angry staff afterwards.
         | 
         | Yes I have trauma on this subject. I will walk out of a job
         | before ever doing a file share reorg again.
         | 
         | You'll roll it out in phases? LOL
         | 
         | You'll run it in parallel? LOL
         | 
         | You'll do some <SUPER SMART> thing? LOL.
        
       | Workaccount2 wrote:
       | I know this is nit-picky and not really relevant to the actual
       | meat of the story, but a toaster (outside of a gag gift or
       | gimmick) cannot run on USB-C since your typical toaster draws
       | ~1kW and USB-C power spec tops out at 240W.
        
         | hnlmorg wrote:
         | A car lighter also cannot run a pizza oven for the same reason.
         | 
         | But you're right, it does kind of miss the point.
        
         | jcul wrote:
         | I assumed they were controlling the toaster over usb c or
         | getting some data from it, interfacing with it, rather than
         | actually powering it!
         | 
         | > But it worked, and now Rex's toast has HDMI output.
         | 
         | > Toaster control protocols? Rex says absolutely.
        
       | vinkelhake wrote:
       | While reading this, the old ARexx (Amiga Rexx) popped into my
       | head. It was a scripting language that in itself wasn't very
       | noteworthy. However, it also made it easy for applications to
       | expose functionality through an ARexx port. And again, offering
       | up an API itself isn't noteworthy either. But it shipped by
       | default in the system and if an application wanted to open itself
       | up for scripting, ARexx was the natural choice. As a result, a
       | ton of applications _did_ have ARexx ports and there was a level
       | of universality that was way ahead of its time.
       | 
       | Come to think of it - I don't know what the modern equivalent
       | would be. AppleScript?
        
         | layer8 wrote:
         | PowerShell with COM interfaces.
        
         | billmcneale wrote:
         | Microsoft introduced this in Windows in 1993, it's called COM
         | and is still in (heavy) use today.
         | 
         | It basically powers all inter communication in Windows.
        
       | iambateman wrote:
       | Where do I get started with MCP? I'm all in, but
       | kinda...confused?
       | 
       | A REST API makes sense to me...but this is apparently
       | significantly different and more useful. What's the best way to
       | think about MCP compared to a traditional API? Where do I get
       | started building one? Are there good examples to look at?
        
         | airstrike wrote:
         | It's kinda like a REST API in which the schema tags along with
         | the requests.
         | 
         | The use case in AI is sort of reversed such that the code runs
         | on your computer
        
         | randomcatuser wrote:
         | Yeah, one way to think about it is like... protocols restrict
         | things, so that people can expect the same stuff.
         | 
         | With a traditional API, people can build it any way they want,
         | which means you (the client) need API docs.
         | 
         | With MCP, you literally restrict it to 2 things: get the list
         | of tools, and call the tool (using the schema you got above).
         | Thus the key insight is just about: let's add 1 more endpoint
         | that lists the APIs you have, so that robots can find it.
         | 
         | Example time: - Build an MCP server (equivalent of "intro to
         | flask 101"):
         | https://developers.cloudflare.com/agents/guides/remote-mcp-s...
         | - Now you can add it to Claude Desktop/Cursor and see what it
         | does - That's as far as i got lol
        
         | stefan_ wrote:
         | I think I'm living in a parallel universe. You can tell an LLM
         | in a million ways what "tools" it can "call". Anthropic & co
         | standardized a shitty variant so they have an uniform way of
         | letting others play in their sandbox, until they invariably
         | decide which of these things make sense and then usurp them in
         | a desperate way out of the commodity rat race to the bottom.
        
         | ashwinsundar wrote:
         | Start by reading the documentation -
         | https://modelcontextprotocol.io/introduction
         | 
         | Then use FastMCP to write an MCP server in Python -
         | https://github.com/jlowin/fastmcp
         | 
         | Finally, hook it up to an LLM client. It's dead simple to do in
         | Claude Code, create an .mcp.json file and define the server's
         | startup command.
        
         | namtab00 wrote:
         | it's not a recipe, but I found this sufficiently interesting,
         | at least for grasping the conceptual differences.
         | 
         | https://youtu.be/eeOANluSqAE
        
       | croes wrote:
       | Universal but insecure
        
         | gabriel_export wrote:
         | Easy, just add an S to the end (for secure).
        
       | moron4hire wrote:
       | This isn't a snide comment, I am legitimately asking. I don't
       | understand the difference between MCP and REST. I know there are
       | differences because I've used it a little. I mean, like, on an
       | existential level. Why isn't it just REST? What parts do MCP give
       | us that REST doesn't?
        
         | gunalx wrote:
         | I cannot really answer, but it seems you can just wrap mcp in a
         | rest wrapper, as thqt is how open web ui seems to integrate mcp
         | into its tooling..
        
       | neoden wrote:
       | So much scepticism in the comments. I spent last week
       | implementing an MCP server and I must say that "well-designed" is
       | probably an overstatement. One of the principles behind MCP is
       | that "an MCP server should be very easy to implement". I don't
       | know, maybe it's a skill issue but it's not that easy at all. But
       | what is important imo, is that so many eyes are looking in one
       | direction right now. That means, it has good chances to have all
       | the problems to be solved very quickly. And second, often it's so
       | hard to gather a critical mass of attention around something to
       | create an ecosystem but this is happening right now. I wish all
       | the participants patience and luck)
        
         | mattmanser wrote:
         | We've done it before, it hasn't worked before and it's only a
         | matter of years if not months before apps starting locking down
         | the endpoints so ONLY chatgpt/claude/etc. servers can use them.
         | 
         | Interoperability means user portability. And no tech bro firm
         | wants user portability, they want lock in and monopoly.
        
         | klabb3 wrote:
         | > One of the principles behind MCP is that "an MCP server
         | should be very easy to implement".
         | 
         | I'm not familiar with the details but I would imagine that it's
         | more like:
         | 
         | "An MCP server which re-exposes an existing public/semi-public
         | API should be easy to implement, with as few changes as
         | possible to the original endpoint"
         | 
         | At least that's the only way I can imagine getting traction.
        
         | newtwilly wrote:
         | It's pretty easy if you just use the MCP Python library. You
         | just put an annotation on a function and there's your tool. I
         | was able to do it and it works great without me knowing
         | anything about MCP. Maybe it's a different story if you
         | actually need to know the protocol and implement more for
         | yourself
        
       | shalev123 wrote:
       | Oh boy, if only our personal AI assistants could be as reliable
       | as a good old-fashioned pizza run by the CEO. The irony is
       | delicious - we're moving towards universal plugins not because of
       | some grand vision, but because everyone's desperate to make sure
       | their AI doesn't go on an energy-saving nap mid-task.
       | 
       | It's almost poetic how we're now incentivizing interoperability
       | simply because our digital buddies have to eat (or rather, drink)
       | to stay awake. Who would've thought that the quest for
       | connectivity would be driven by the humble Watt hour?
       | 
       | I guess when it comes down to it, even AI needs a good power-up -
       | and hopefully, this time around, the plugins will stick. But hey,
       | I'll believe it when my assistant doesn't crash while trying to
       | order takeout.
        
       | brap wrote:
       | I guess I'm finally old enough to become old-man-yelling-at-
       | cloud.
       | 
       | I'm convinced that the only reason why MCP became a thing is
       | because newcomers weren't that familiar with OpenAPI and other
       | existing standards, and because a protocol that is somehow tied
       | to AI (even though it's not, as this article shows) generates a
       | lot of hype these days.
       | 
       | There's absolutely nothing novel about MCP.
        
       | phreeza wrote:
       | Is this basically the XML/RSS/semantic web of this tech wave?
        
       | sureglymop wrote:
       | I've thought of this as well but in reality, aren't MCP servers
       | mostly just clients for pre existing APIs?
       | 
       | For example, the Kagi MCP server interacts with the Kagi API.
       | Wouldn't you have a better experience just using that API
       | directly then?
       | 
       | On another note, as the number of python interpreters running on
       | your system increases with the number of MCP servers, does anyone
       | think there will be "hosted" offerings that just provide a sort
       | of "bridge" running all your MCP servers?
        
         | graerg wrote:
         | This has been my take, and maybe I'm missing something, but my
         | thinking has been that in an ideal case there's an existing API
         | with an OpenAPI spec you can just wrap with your FastMCP
         | instantiation. This seemed neat, but while I was trying to do
         | authenticated requests and tinkering with it with Goose I ended
         | up just having Goose do curl commands against the existing API
         | routes and I suspect with a sufficiently well documented
         | OpenAPI spec, isn't MCP kinda moot?
         | 
         | On the other hand, in the absence of an existing API, you can
         | implement your MCP server to just [do the thing] itself, and
         | maybe that's where the author sees things trending.
        
         | mkagenius wrote:
         | My understanding is MCP = original APIs + 1 more API
         | 
         | The additional API is /list-tools
         | 
         | And all the clients consume the /list-tools first and then rest
         | of the APIs depending on which tool they want to call.
        
           | sureglymop wrote:
           | Yes. But in order to do that you run the MCP server for that
           | API locally. Is it really worth doing that just to have the
           | additional /list-tools, when it is otherwise basically just a
           | bridge/proxy?
        
       | Stwerner wrote:
       | https://www.dreamsongs.com/RiseOfWorseIsBetter.html
        
       | mudkipdev wrote:
       | Anyone else feel like this article was written with ChatGPT
        
         | neuronic wrote:
         | Not in this particular case. At this point I am starting to
         | wonder if the
         | 
         | > Anyone else feel like this article was written with ChatGPT
         | 
         | comments are actually written by ChatGPT.
        
       | TZubiri wrote:
       | >What if it's just "a standardized way to connect AI models
       | literally anything to different data sources and tools"?
       | 
       | Then you aren't exploring a novel concept, and you are better
       | served learning about historical ways this challenge has been
       | attempted rather than thinking it's the first time.
       | 
       | Unix pipes? APIs? POSIX? Json? The list is endless, this is one
       | of the requirements that you can identify as just being a basic
       | one of computers. Another example is anything that is about
       | storing and remembering information. If it's so foundational,
       | there will be tools and protocols to deal with this since the
       | 70s.
       | 
       | For the love of god, before diving into the trendy new thing,
       | learn about he boring old things.
        
       | MontagFTB wrote:
       | Bret Victor had an old video where he talked about a world in
       | which computers very organically figured out how to interoperate.
       | MCP feels like the first realization of that idea.
        
       | bovermyer wrote:
       | > emotional support portable fan
       | 
       | I can't be the only person that non-ironically has this.
        
       | nimish wrote:
       | Interoperability is, and always was, the hardest part of
       | programming systems together. It's telling that the ai tooling
       | needed sustained non ai effort to expose the interfaces via MCP
       | (or ws-* or rest or an enterprise service bus or xml or CORBA or
       | EJB or...)
        
       | chopete3 wrote:
       | The real accident is that the prompts became a programming
       | language. I don't think the ML Engineers set out to create a
       | general purpose programming language.
       | 
       | A2A (agent 2 agent) mechanism is an another accidental discovery
       | for the interoperability across agent boundaries
        
         | namtab00 wrote:
         | "The hottest new programming language is English" - Karpathy
         | 
         | I call bullshit, mainly because any natural language is
         | ambiguous at best, and incomplete at worst.
        
       | rsingel wrote:
       | For those who don't read things on Substack
       | 
       | http://archive.today/OUymS
        
       | gavinray wrote:
       | > _" The author discovers API's/JSON RPC"_
       | 
       | I'm too young to be posting old_man_yells_at_cloud.jpg
       | comments...
        
       | ummadi wrote:
       | So does that mean mcp is good to integrate along with Agentic AI
        
       | Uml2657 wrote:
       | So does that mean mcp is good to integrate along with Agentic AI
        
       | Uml2013 wrote:
       | So does that mean it's good to integrate mcp with agentic ai
        
       | rubatuga wrote:
       | Can someone link to this supposed toaster with DP-alt mode? That
       | supposedly runs on 240W? (Max PD power)
        
       | afro88 wrote:
       | The author is missing the bit that the LLM provides:
       | automatically mapping input parameters to things the user wants
       | to do, and responses to the way the UI displays them.
       | 
       | Take out the LLM and you're not that far away from existing
       | protocols and standards. It's not plugging your app into any old
       | MCP and it just works (like the USB-C example).
       | 
       | But, it is a good point that the hype is getting a lot of apps
       | and services to offer APIs in a universal protocol. That helps.
        
       | belter wrote:
       | This all starting to look like autonomous driving. We are nowhere
       | near solving it but everybody acts like it's here.
        
       | tankenmate wrote:
       | "Want your AI agents to respond like peons from Warcraft 3 when
       | you assign them a task?" -- I'd rather be sailing.
        
       | alangpierce wrote:
       | > What if you just... removed the AI part?
       | 
       | Maybe I'm not fully understanding the approach, but it seems like
       | if you started relying on third-party MCP servers without the AI
       | layer in the middle, you'd quickly run into backcompat issues.
       | Since MCP servers assume they're being called by an AI, they have
       | the right to make breaking changes to the tools, input schemas,
       | and output formats without notice.
        
       ___________________________________________________________________
       (page generated 2025-06-28 23:00 UTC)