MCP is dead?
365
HI version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
65% Positive
Analyzed from 13094 words in the discussion.
Trending Topics
#mcp#api#cli#tools#tool#context#agent#more#server#don
Discussion (346 Comments)Read Original on HackerNews
The thing that all these "MCP is dead" posts are missing is that whether or not MCP is used as a transport protocol is actually completely irrelevant.
The reason MCP isn't dead is because practically ~every company on the planet is building an MCP server. I know this because we interact with all of them. Most of these companies don't have a CLI. Many of these companies don't even have an external API! And yet, they're all building MCP servers.
And that's why MCP is not only not dead, but more important than ever.
Maybe we will turn every MCP server into a CLI under the hood. Maybe we'll use code mode. Maybe we'll implement tool search.
All of those are just implementation details to the much more important point: our AI agents are getting access to services they otherwise would never have had access to.[0] That's what matters.
So, is MCP dead as a direct communication layer for models to speak to? Maybe, maybe not. Is MCP dead as a protocol? Hell no, couldn't be further from the truth.
[0]: Although I will say the Codex app's computer & browser use features have made this statement a lot weaker than it used to be. If you haven't tried them yet—they're mindblowing.
The main reason is that it adds another layer (and human) that can, and probably will, get out of sync with the real-world implementation, whether that implementation is an API, web, or a CLI.
AI should not be using a protocol or set of instructions that is different from what humans have access to (know and use).
Sure, companies want to expose MCP servers because it is the cool thing to do right now.
So the current situation is basically that I used Claude to write an MCP server on top of our API. And then I need to occasionally tell it update it match the public doc.
And my reaction is: really? It is not like our API docs are not public. Claude Code created our MCP server with zero instructions beyond what is publicly available. I just told it to read the docs from the net.
So MCP feels more like a temporary workaround for current model limitations.
Or what else am I missing about why MCP is more secure than a CLI?
WAP was dumb and failed because it oversimplified the web, and phones evolved to be real computers.
MCP is more sophisticated than typical APIs. It adds organization, policy, and code vs data (prompts) partitioning.
IMO it’s more likely that non-LLM apps will start using MCP than it is for MCP to go the way of WAP.
Why would it? Do you see any agents or models use that? No, instead vibe coders at Anthropic vibe-designed a bespoke protocol that sidesteps and ignores the last 60 years of API development and integrations.
That's at least my experience with my current project: the traditional json, coding oriented API feels out of place, I maintain it out of habit. The real API is the MCP server, which is not designed like a traditional API would; understandability of the output for an LLM prevails instead of searchng for exhaustiveness, orthogonality etc.
The reason I'm asking those questions is that a customer of mine has a service with a JSON API, a Vue frontend and a score of customers using that JSON API. We know that the newest ones are using bots to code their clients (and they are using them wrong, by the mistakes they do.) I don't see a near future in which all those third party apps become LLMs that would benefit from a MCP server and we retire the API.
It’s like saying APIs are dead because you can just use HTTP. They’re not the same thing, though of course you can hand-roll the higher layer in the lower one. It’s just more work, less standard, less valuable.
I don’t think models will ever prefer a low level API to a decorated index of API features and how to use them, same way developers will never prefer a list of HTTP endpoints and bespoke headers + query strings + POST bodies over a structured API.
You have a client, the client uses the SDK, talks to endpoint x. Endpoint x tells it very efficient that they are now talking protobuf and rpc over quick or http15 and thats it.
Why don't we have this? Right because of people.
Its always people problem.
MCP is now here, it might stay.
Should it? I think it can be very useful to constrain what your AI can do (e.g. read files but don’t delete them). MCP is a way to do that.
You are missing the point. When the API moves, the agent has to adapt. Are you rewriting its skills?
MCP provides the instructions. When the API moves, MCP adapts. You need to do nothing.
So, basically the exact opposite of what you are claiming
I've heard this one before
(Maybe it'll be the first time that a temporary workaround stays around longer than expected then)
And you’ll also often see CISO-offices that are managed by checklists and yet more committees.
Asking for MCP access is generally easier than asking for an API for several reasons:
1. MCP supports OAuth, so your access conform with numerous CIS (et al) compliance checklists (short lived secrets, MFA, user-specific credentials, user access managed by centralised directory services and thus can have business rules applied, etc)
2. MCP is something a business can make a cooperate decision on. And then you can refer to that decision each time you need an access to new service. Whereas API access isn’t. In some cases APIs are governed by LLDs, and then you have an extra layer of “fun” having to update documentation to describe, in detail, the technical specifications too.
3. MCP defines the interaction better. If you need to request access to an API then the inevitable question from the committee is “where is this code running from?” and so on and so forth. Whereas saying “MCP access for AI to assist the project team with development” is a lot easier conversation to have.
In short: Enterprises are a very different beast to your average business.
Not everything in the real world will expose an MCP server so AI can interact with it.
Eventually, AI will need to move beyond MCP and interact with the real world the same way humans do: by observing, interpreting, reasoning, and taking action in messy, imperfect environments.
MCP tries to organize our messy word to make interaction part with the world easier in the near term, and it will help accelerate very early progress. But ultimately, MCP is a temporary bridge. Not the final destination.
I give it max 3 to 6 years and it will just die.
The menial task of updating the interfaces when the code changes is something AI should be really good at, so it's essentially little to no actual programmer time waste
> So the current situation is basically that I used Claude to write an MCP server on top of our API. And then I need to occasionally tell it update it match the public doc.
> And my reaction is: really? It is not like our API docs are not public. Claude Code created our MCP server with zero instructions beyond what is publicly available. I just told it to read the docs from the net.
Updating MCP by AI is one time effort.
Having AI re-create what MCP would do for every piece of code that uses a service is massively wasted effort in comparison
It's not question of "model limitation" but of cost effectiveness.
> And my reaction is: really? It is not like our API docs are not public. Claude Code created our MCP server with zero instructions beyond what is publicly available. I just told it to read the docs from the net.
My reaction to this is.. really? Presumably your API and API docs have a release process. Hopefully an automated one. Why isn't the "hey Claude, update the MCP server" step a part of it?
It's adding another failure point to the process for no gain.
Overall, I am in favor of this goal. I'm not sure this is the protocol I'd choose to accomplish it, but it's the one people hear about, and the one they're using.
Agents are just making REST calls and that's it.
The best thing a company can do to make their stuff 'agent ready' is to make sure the lllm.txt docs are clear-cut and ready for the AI with clear instructions for agentic use.
'MCP' is frankly a hurdle.
Now - it probably does make sense to add MCP, because it's not expensive at all, and some will like that use case, it maybe garners a bit more attention .
MCP is a 'weak externalization' - people are using it because others are using it, and it's a 'workable' but 'not strong' solution.
It could very well entrench itself however.
The second one addresses a much deeper architectural chasm. We want to have our agents carry nearly-the-same-but-not-the-most-dangerous permissions as we do. No regulated business can risk unleashing agents with zero judgement capacity to wreck their systems, and on the other hand the existing identity systems are not geared for real-time dynamically adjusted user permissions. The need for so called "agent-aware IAM" is urgent. So instead of letting users connect to the internal APIs directly with their full suite of powers, MCP servers act as stand-ins for API gateways.
MCPs are not as flexible as full-fledged CLI tools, and that's a bit of a shame. But they can also become identity-aware proxies that enforce the intended permissions for agent-safe use. It will probably take years before IAM systems can adapt to the needs of the new world, and it will take another DECADE after that for the improved IAM systems to become universally available across the larger enterprises. So in a big way I agree with you:
> MCP is a 'weak externalization' - people are using it because others are using it, and it's a 'workable' but 'not strong' solution.
"Workable" is a load-bearing term. MCP servers are by no means perfect, but they are good enough for specific needs and allow to move the balancing point as needed while the world catches up.
I'm an engineer and prefer CLI or raw API access 99% of the time. But I also have decades of scars from infosec. The single biggest security threat for a business used to be an employee who could not get their job done. They found ways to work around the roadblocks. These days the single biggest threat is an employee who can not get their job done, but has an infinitely patient agent with vast latent capabilities at their disposal.
I remember 10s of HN submissions where handlers were trying to get conversations about MCP going on HN back when there was almost nothing known about it and nothing to say.
It was always about tricking people into thinking there was authentic interest in it and it still is.
Wow if that's not an echo-chamber comment I don't know what is.
Wouldn’t expect anything less from someone working as a manager at OpenAI. I don’t think their org culture is survivable if you’re not 200% all-in on LLMs eating the universe.
Like imagine somebody saying “you’re the most handsomest boy in the world” and thinking “Shit, nobody would just make something like that up.”
"Person working on MCP tools says MCP is not dead."
Also, what's the hold up? If they all are building one, presumably using AI, shouldn't they all be done already?
And to be blunt, a) you're investment bias'ed and b) whether you're selling the product (MCP) to a gazillion companies doesn't exactly disprove a).
Just look at Microsoft -- they've buried more technology than most, and there's little correlation between usefulness and how deeply buried it is, and some would claim that the correlation is _inverse_. Organisational factors are what drive them, just as I suspect they are now driving OpenAI's insistence on MCP. I understand it's hard to see that from inside.
"Everyone is building this!"
Except... Few are actually using it. So what, exactly, is the value in MCP?
Especially that there are simple ways for anyone to spin their own MCP based on standards like OAS. I talk to dozens of new clients in a given week. Our product should attract users who want MCP. And in the last month only one conversation actively asked us if we had an MCP server. Surprised, I asked about use case and the response was as I'd expect: "No specific use case, we're just playing around with it". Seems to be pretty standard for AI conversations these days.
If all of these companies spent equivalent time writing a CLI for agents to consume as they spend on MCP servers, would they be any worse off in terms of agents being able to interact with their products?
Still easily doable with CLI
So, OpenAPI/Swagger for REST? GraphQL? SOAP schemas? All of these (and more) exist. What does MCP add that these don't have?
You could literally, deterministically, zero AI, code-gen a CLI from an MCP specification, just like you can with an OpenAPI specification. I'm sure tools exist that do this. So if you want a CLI, there it is.
But the problem with a CLI is that it requires a shell environment, and not everywhere you may want to run an agent should or can have access to a shell. MCP enables the harness to tightly control that access. MCP allows the user to easily allowlist/denylist specific tools, or categorize tools into "ask me every time" versus "don't ask me just do it". Doing any of this with a CLI is really hard because CLIs are all very different; yes, AIs can easily learn how to use them, but that might be exactly what you don't want, hey AI don't issue that aws ec2 delete-instance command ah crap there it goes I wish I could have just denylisted its access to that tool.
MCPs are impossible to combine this way: everything you feed or get from them goes though the model and consumes tokens.
The second value is more about how business works. There is no chance you can convince someone at WalMart to fund and release a `wmctl` that allows you to search and buy products. Now try to convince your regional Pizza chain to release a CLI too. WalMart and such are incentivized however to create "Whatever OpenAI and Anthropic integrate with". Shopify can create an MCP for every shop and allow the shop owner to customize it. Creating a CLI per shop makes no sense. OpenAI and Anthropic prefer MCPs because of the first benefit. So it works out for all parties involved.
Is this an advantage? Phrased differently, every MCP that could have been a CLI call is a new opportunity for sandbox escape.
They have different tradeoffs.
MCP servers on the side of the consuming organizations fit into the existing IT landscape, with centralized safeguard on who can access what a lot better and are easier to administer than letting their employees run arbitrary agents against arbitrary sources and destinations and cause chaos.
Here's some companies that offer MCP servers but don't seem to offer an equally featured CLI:
and many more that offer both, but support their MCP more.Should they all be offering CLI tools? IMHO, yes absolutely. But an MCP server gets much more interest. I'd rather encourage them to keep improving and supporting their MCP services than telling them to drop it for a CLI.
There's lots of things like this in technology where you end up stuck with the first thing because its popularity perpetuates itself. The QWERTY keyboard I'm typing this on is a prime example. x86 is another one.
IME, MCP has often lagged APIs in terms of complete ess, so as a user, if there was an API, I would be better off using that because Codex is already so good at calling APIs.
Now, the API story sucks for non-coders, but I'm not really bullish on MCP for dev tools atm.
That's just because no one knows what they're doing and everyone is trying to copy everyone else. It's a giant mud hut made of shit.
MCP will go away, and something much simpler will play the same role.
That’s covered in the article: a human can modify the commands generated by the agent, or vice versa, to debug problems or transfer knowledge.
This would allow us to deliver standard prompts across the team without having to sync manually or with scripts; keep everyone up to date. Even allow per-user customization of "skills" via server rendering of the prompts.
AFAIK, Codex is the only major harness to not support this.
[0] https://github.com/openai/codex/issues/5059#issuecomment-453...
A sign of weariness in the rapid evolution of tooling, where people got off the train a stop too early?
A confusing overloaded acronym (cli) and term (skill) lacking the marketability / easy mind share of a unique acronym?
These all fail to establish a hearty reason to be.
The walking dead are still dead.
CLIs live in the same namespace as the agent, so any secrets the CLI needs access to, the agent can also exfiltrate. And access control is lightly gated by the agent's tool call policy.
For an enterprise-level deployment, it becomes quickly desirable to have a centralized MCP backbone, on which each MCP is attached to. A place you can attach policies to, log activity, and reason about access control.
With saas is turned out that distribution to a browser solves a pretty major pain point and I expect MCPs to be treated the same. Can you trivially replace an MCP server with a CLI tool which accepts a token? Yes - but why do that to yourself when you can hit the endpoint directly?
Claude on the web does this. The only issue is controlling network access, which could be fixed by per-skill ACLs.
Can you clarify why the never? What's the issue with giving a phone-based AI a sandboxed file system and bash shell?
Right now you have to create an MCP but v1s are always easier to maintain than v10.
We're speed running a trap.
I find a lot of HN content seems to be doomer farming
i was a big skeptic of MCPs
now i build em
With just an API, the agent needs to "read your API docs" to know how to call it (that can be an OpenAPI spec or even just text).
With MCP, the agent sees a bunch of tools it can call, and they've been trained to call tools so they nail it.
One more very important factor is authorization, which no one seems to mention in these discussions. CLIs were made for humans and use primitive mechanisms for authorization: either an API key you hardcode in your environment, or they literally run a background HTTP Server to get a callback OAuth call to receive a token from a browser authentication flow. Incredible that people are happy with that, appparently. With the MCP Authorization spec, you solve authorization across multiple MCP servers in the same standardized way, the LLM client you use just need to know the protocol, not how to login for every single MCP server.
Very importantly, if the MCP client does the authorization, the MCP provider has auditability: is this a call from a human or from a LLM? That's important in Enterprise! People think it's ok to let an LLM act on behalf of the human but that will eventually bite a lot of people. Did the LLM just try to hack the API while you were mindlessly clicking "yes" when it asked if you wanted to let it do something? Tough luck, there's no way to distinguish an LLM making a mistake from a human maliciously running some attack.
And as the post mentions, there's also more benefits like being able to "elicit" user input (not just request/response cycles) and the ability to have documentation and assets (skills also have this though).
> The reason MCP isn't dead is because practically ~every company on the planet is building an MCP server.
You have drunk the kool aid. No shot ~every company is building an MCP server.
I think it's just a fad and eventually you'll need to address the math no matter how much you sugar coat it - the 3x slower metric, eating of context window is all beneficial for LLM companies but not for the end user.
Ok, how many AI tools do you even use from 3 years ago? Funnily enough, I stopped paying for my chatGPT subscription a year ago.
"Many of these companies don't even have an external API! And yet, they're all building MCP servers."
Whether or not MCP is a temporary means to an end or a more permanent standard is kind of missing the point that the overall callable API surface is expanding rapidly. How it's called by the agent is an implementation detail.
AI is a bandwagon tech, a lot of people will 'build because others are' adhering to an ostensible standard.
Most of the people that I know are moving away from MCP in favour of skills where the advantage of MCP goes away if the REST API is clear enough.
Also - I'm sorry to say but MCP management on Codex (and Claude) is just really bad. Everything from discovery, to management, to context window, to documentation - it feels unfinished as a 'feature' even if the protocol is supposed to be narrow.
1) I have a big popup and yellow warning every time a window is opened or a sub agent is launched warning me that 'SkySomething Computer Use' does not work. I had to Google to find out that has something to do with Codex MCP. So already the externalizations of problems, resolutions ... not very well done.
I'm not even sure what to do - and I'm honestly not interested in 'fixing' something I didn't cause, I'm not sure of, and don't want to deal with.
2) Just listing the current MCPs, knowing really what the are for (clearly, concisely) is hard.
This is what you get if you type /mcp in Codex:
/mcp
What's that supposed to mean? What is 'codex_apps'?As presented - it resolves to 'nonsense gibberish'. Those are things that I did not even install.
Do you expect people magically know what 'codex_apps' is?
Here is what 'AGI!' Codex 5.5 answered when I asked about 'codex_apps' is:
====
" codex_apps appears to be Codex’s own internal cache/tooling area, not part of J1 (my project).
"I only found it under .codex, e.g.:"
" I did not find it referenced by the J1 source. So unless you saw it somewhere specific, treat it as Codex runtime metadata for app/tool integration, not project code."
====
So even Codex itself has no idea what it's own MCP tools are, and after a full '1 minute of thinking' on 'xhigh' it responded with nonsense.
This whole experience fundamentally deflates my perception of AU, OpenAI, Codex and MCP.
This is supposed to be the 'future' but it feels like 1982 dialup.
This is where 'traditional UX' really starts to show it's value obviously, but you really need to consider enhancing this experience, possibly with some traditional ux mechanisms.
3) Knowing the 'state' of the MCP is totally opaque. Is the 'MCP server' running? Can I restart it? That might be outside the scope of 'Codex' but you're offering the product so all of the underlying stuff is essentially 'your responsibility' as well at least from a UX perspective. Why isn't the 'state' of the MCP listed.
4) How can I not just easily enable/disable individual MCPs so they don't chew up context?
5) How can I not discover MCPs from codex itself, so that I can find solutions to problems? MCPs are all a bit different, and awkward to install and manage. Like with VS Code, we can 'discover plugins'. Even from the Web we can search and discover plugins.
While I realize that most of this rant is oriented around MCP tooling management, and not the standard, I do feel that these issues are 'fundamentally at the crux' of the situation.
Our team has moved away from MCP into Skills - and after doing so, it's hard to see why MCP is going to be valuable - other than plausibly as defining some 'jon calling conventions'.
There's a lot of obvious things to improve, please do that.
That the 'smartest people in the world' have $100 Billion and are are totally scattered on so many issues completely blows my mind but it speaks to how systems are organized.
They don't need to hire anyone for this stuff, they need to have some basic product discipline and prioritize it, that's all.
If they don't do that, all the money in the world and all the best product people wouldn't be able to help.
I totally respect that 'Codex is young' - but it's been kind of a year now. That's a long time - and AI is supposed to 'accelerate time scales' and make people 'super productive' remember?
I hope they improve.
Its absolutely hilarious to me how tech people keep imagining that "this time it will be different".
This has been done 100 times before, it's COM, it's the remote Java object marketplace, it's the semantic web.
You are imaging a world where businesses are OK being marginalized into a nameless, faceless api provider with no control over their product. This will never happen. You might get a couple of years while they chase investment frenzy, but it will fragment. They will lock you out of their services. They will interact directly with their customers.
News at 11.
Didn’t ~every company also jump on blockchain and NFTs?
Haven’t we devs always dreamt of a common interface to query and introspect foreign APIs? Aren’t we lucky we stumbled into an “AI” that is founded upon human language and not some incomprehensible machine code? It seems to me LLMs only made the need for such a universality attractive. Such as so many circumstances where we will do things for our progeny which we would not (yet should have) done for ourselves !
I’ve felt the same thing about skills files, the first things juniors or onboarders should read to explicitly understand their own jobs!
As in: if your models and agents were as good as you claim them to be, we wouldn't need to re-implement half if our tools and a significant chunk of the web to conform to this vibe designed protocol.
In 99% of cases your AI agents already have all the access. They are just too stupid to do so.
Jane #2: "We're not a cult. We're an organization that promotes love and—"
Hank Hill: "Yeah, this is it."
I might be biased because I came up with it, but we are over complicating these systems. There is a simpler way, and it appears to work well since I built a system using it to test the idea.
- I think the comparison to TCP/DNS/BGP is the more apt one compared to MCP/A2A
- Those protocols negotiate capabilities and exchange information about themselves, but not in a self-serving manner of just talking about themselves, but with the goal of ultimately transporting data for a higher layer. Ask Protocol lacks that.
- Objects don't exist in a vacuum, but in a context. As the objects will only know about themselves they will always be limited in how to describe themselves best. An LLM that lives on the outside and just gets a static description of an object will be in a much better description to answer an "ask" query.
- Given that the existing agent protocols you are putting it in a context in already come with "description" fields and the like, the protocol seems too little of a value add to actually target. e.g. there is no benefit for a MCP server to conform to the prescribed manifest rather than implementing a freeform "ask" tool.
- If you want to actually bring the point across that it "occupies a different position" than transport/agent protocols, don't put it into a comparison matrix where you force it into the same schema
- ("Open Source" doesn't count as governance)
I work at Taco Bell. Every company on earth is working on Doritos Locos Tacos. I know this because I interact with every company on the planet, and they all tell me that Doritos Locos is in their development pipeline. When I see all of these “not everybody eats or wants Doritos Locos” posts I know that they are wrong because the appeal of them is universal, especially when paired with Baja Blast, mankind’s foremost favorite fluid
[1] “It is difficult to get a man to understand something, when his salary depends on his not understanding it.” ― Upton Sinclair, I, Candidate for Governor: And How I Got Licked
MCP is essentially just JSON RPC with a few special fields that must be included. I have reservations about JSON RPC, but there needs to be some 'service discovery' layer for LLMs to interface with.
It needs to be available in places like websites, desktop applications, backend services, etc. The CLI is only one place that these systems interface with.
Whatever you replace MCP with will be in a similar shape even if you specify a different communication protocol or different fields for tool discovery.
People are saying API are better than MCP. But MCP is just API with some instructions for the AI to discover how to use it. Nothing more nothing less. And some people are saying we should use 'CLI'... what does it even mean? LLMs are good with common CLI tools like ffmpeg because the knowledge is solidified inside the weights. If I make a new CLI tool I still need to somehow teach the AI to use it. If one wants the 'teaching' part comes from a server then MCP. If one wants it local and static then skills. How could there be so many debates around these simple concepts?
It all has some form of "the thing I'm doing is the future and everyone who doesn't join me will fall behind" energy that AI/NFT/blockchain/web3/etc. enthusiasts talk about when they're trying to sell you something or when they're trying to convince the world they really are the big money makers they claim to be.
The LLM isn't going to care about where the tokens it's inserting into the context window are coming from. For all it cares the data it's processing came in over fax and was read in with OCR.
cli’s also need to be documented and input/output typed.
its also extremly dsitributable by just pointing to an url.
cli’s are great because they are composable but i really got huge mileage out of mcps
'Skills' should all be based on MCP, they should load on demand, be very easily manageable and discoverable by humans and by AI, and then it would work
The scope was too narrow, given how it ended up being applied.
If they layer something on top of it, it may yet be revived.
The concept of 'mcp server' is a brittle abstraction that need not exist.
A 'skill' is utterly superior in every sense: a 'right sized abstraction for whatever it is you're trying to do' - that can include cli / rest - and other key bits of information.
I'm not super deep into all of this, but I think except latest Claude Code release the mcp is frontloaded into the context. So if you don't need it that often you have to disable and enabled it again when needed.
And I guess you can put some usage examples into the skill file. Which might migate the first --help.
Also I guess with cli it's easy to spin up a sub agent with their own context that just returns the result?
It’s really hard to determine which tools an agent will need on the fly. The best idea I’ve seen was to do a “search tools” tool which an agent would use to find relevant tools, then have an “execute tool” tool which did what it says.
Alternatively, if you’re using an agent that’s good with code, give it something like “port of context” (pctx) which translates MCP tools into a JavaScript package so the agent can chain MCP tools together with code, and they can filter the data down to just what they need. I haven’t used this method much yet but soon I need to improve the MCP gateway in our cloud agent builder product so I’m going to try this one out soon myself.
So these numbers are at least 7 months out of date. Why is this being posted now?
Its crazy that people are still discussing this. It's ancient history. Deferred tool loading, large contexts, and prompt caching have made 2026 completely different from 2025.
Also, the "CLI saves token" debate really falls apart when step one of using the CLI is running "--help". The problem remains: if knowing how to call the thing isn't in parametric memory, it has to be in context.
And it's not actually necessary for it to exist at the API level. It's a pattern. Making it API-side is just an optimization.
To do it client-side: 1. Define a single tool, tool_search 2. List the names of your deferred tools in context (or tool_search's description) 3. When tool_search is called, match the query against the tool names (or names + descriptions) 4. Append the matched tool def to the context in a new <system>-esque tag
Claude Code (as of the leak) does this client side. You can even see the custom matching function and A/B tests about whether to include the descriptions.
Whether or not that tool definition comes from MCP or a local definition is kind of beside the point.
Crazy that the company that invented MCP is not putting basic features like this in the product.
Do you mean directly == raw shell access on your production server?
Essentially it's anything that _could_ be on a dashboard, but _might_ be accessed conversationally via an agent.
- remote mcps are server driven, meaning the producer can introduce new functionality without requiring all clients to update their skills and clis
- remote mcps are safe as they don't require literal code execution privileges on your system. Many times skills even bundle scripts with `npx`/`uvx` which is basically just `curl npm.com | bash` level of unsafe
Also the calling of the Mcp is nicer in the chat UI, clearer for users.
SSH is the perfect protocol for LLMs. Coding agents can use it already, `ssh api@example.com list-users` is all it takes. There's a 90% chance that your users already have ssh installed. It's text-in, text-out (which is exactly what LLMs need). It handles authentication (through public keys), streaming output, interactive I/O, even file transfers (through scp / rsync) if that's something you want.
If your users link their accounts to Github or GitLab, you can even scrape their ssh keys and pre-configure authentication for them, so they just connect and they're in.
Every time I read MCP, I think it means "master control program".
http://mcp.a1k.org/indexe.html
And I know I will forget again. "Model Context Protocol" is so bland I already forgot half of it by the time I'm at the third word, so that even some old Amiga stuff instantly overrides it.
> You sit down and 10 menus (MCP tool definitions) are spread across the table
> There's no room left for actual food (your work)
> Every time you order, the menus have to be pulled out again
This is a bad analogy. Ordering repeatedly is uncommon except for tapas restaurants. You could easily put food on top of menus, but more commonly, menus are removed after ordering, thereby freeing the table (context??) for the food. If you're going to try to explain things by analogy, it's worth putting effort into making it more relevant.
For this example, there seems to be no explanation for the LLM to know when to use this curl command, etc. Is the idea that the linear API is known in the LLM weights already and therefore there is no need to include "the manual" in the context window? If so, it's a pretty narrow win.
> Update: Since these measurements were taken, Claude Code has rolled out Tool Search with Deferred Loading, which loads MCP tool schemas on-demand and reduces context usage by 85%+. The context bloat described in Problem 1 is largely addressed for users on current Claude Code versions. The performance, debugging, and architectural arguments below still apply.
Because Claude Code only loads the tools it needs now, so context bloat is pretty much solved for MCPs.
The problems listed on the article are problems with specific tools that have large tool descriptions. This has nothing to do with MCP. There is nothing in MCP that would cause the tool descriptions to use more context than they would otherwise.
If you have external users, then you have to use MCP, which comes with how to use each endpoint and etc. MCP is what their current apps e.g. Cowork, Cursor support out-of-the-box.
In that sense, MCP is very much not dead
You can have your IT department configure an MCP for the org, and your regular non-technical users click a button and login with their account the service. Then they get all the tool calls authenticated as themselves.
"We've done extensive renovations in our apartment and while the coring drill was essential to install electrical conduits it's pretty useless in making furniture installations".
In the world of AI development we are jumping from tech to tech every 20 minutes. I'm in shivers every time when I see "A new claude version was released, do you want to update now?"
The moment you kinda automate something with the AI, the process breaks and you have to build the new thing.
So don't blame a coring drill.
Sooner or later you have to build the real thing, and the cost and slowness of token-based computation become unacceptable.
It's also easier to manage for non-tech people. Try telling the people over at HR or finance to install a CLI.
Chrome/Ghidra MCP does have a tendency of crashing, but I'm not sure why this is. Is my way of thinking of MCP incorrect? If it really is a descriptor of how to talk to another tool, then why do they seem fragile at times? I feel like there's a gap in my knowledge somewhere.
MCP is a combination of a server responding to requests, and a prompt to tell the agent how to format those requests.
In my opinion, MCP is not dead. "MCP Belongs to Software Engineering", it ships existing concepts from software engineering into AI. CLI, MCP-tools, and OpenAPI are interchangeable to some degree, but MCP is more than tools; there are mcp-apps[2], lazy load in context[3].
[1]: https://log.ifor.dev/posts/mcp_vs_skill/
[2]: https://modelcontextprotocol.io/extensions/apps/overview
[3]: https://code.claude.com/docs/en/agent-sdk/tool-search
MCP is an API with some description. It adds tools to your agent, along with some context.
The (common) complaint is that the principle of progressive disclosure isn't working because all tools, with all their descriptions, are loaded into context right at the start. This is a somewhat reasonable complaint, as the structure makes it hard for the harness to progressively disclose the tools.
This is a fundamental issue with anything that just adds a bunch of tools, whether it be via MCP or HTTP (still sad that MCP won over OpenAI's HTTP based approach).
How might it be solved? Well, we could work with sets of tools. That's pretty much what the CLI approach does: Wait until you need it, then invoke the help command to discover what to do exactly. The caveat of the CLI being that it's a nightmare to secure.
At the end of the day, every capability eats some amount of context because the LLM needs to know when to invoke it.
i personally was anti-MCP but they just work better in terms of tool search than a CLI, especially with the idea of tool nudging
pretty much
In the end MCP is just a protocol for discovering tools. And agents _need_ to do stuff with tools.
The article is semi right. Local MCPs that are made by enthusiasts wrapping an api they don’t own? Yes that is dead and should never have been a thing in the first place.
But MCP in its current direction and form is really an OAuth Protocol over http. And it has something other that other agent identity protocols don’t: client adoption
That may sound like an exaggeration, but it’s exactly what I see in our product.
Humans developing something already have context that agents don’t have yet. Most agents start a task with virtually no prior knowledge. And they start from zero every single time. That may improve in the future, but we’re not there yet.
Can agents get the job done? Yes. But without a thoughtfully implemented MCP server, they are awkwardly inefficient.
The problem is that the agent does not care. Its primary goal is to get the job done.
Maybe the agent is smart enough to choose the optimal path, but that strongly depends on the model being used. You also do not know who is on the other side. With a human-facing API, you can usually assume who is using it and what they want to achieve. Humans are generally lazy and tend to look for the most efficient solution.
An agent, however, will happily iterate through 1,000 users and fetch the online state for each one individually, even across multiple paginated requests if necessary.
You can provide an endpoint that returns the online states for all users at once. A human will most likely use that endpoint, but I have seen agents go completely wild on the other side. :D
At some point, you may get a response like “token limit reached.” But what do you do then? You give the agent more tokens and increase your bill, because you cannot even tell whether there was a more optimized way to achieve the same result.
In practice, this is a surprisingly tricky problem. :D
They are easy to implement and integrate
You can use OAuth and handle ACL easily
> Provide CLI -> API -> docs, in that order. LLMs already learned from man pages and StackOverflow.
So how is the agent going to know about your niche CLI? It's still going to use up context to learn your command line interface, same as for an MCP interface.
Agents only excel at CLIs if a particular CLI was part of their training data. The same would be true of well-known MCP interfaces.
> Alternative 2: Skills Pattern
> If MCP is "spreading all menus on the table upfront", Skills is "asking the librarian for only the book you need".
Or: Layer your MCP help commands, like a directory at a mall. The agent only looks up what it needs at the time.
2026. Oh woe, the MCP that all the companies are giving me isn't ideal.
2028? oh woe, the CLI that calls the REST API, that calls the MCP that all the companies are giving me..
- MCPs are great for stateless, mostly read-only interactions with document store type things. Notion/Slack/Linear are perfect use cases. I have those MCPs connected to claude code and they work great. These tools never had CLIs or super well used public APIs to begin with. MCP handles the auth for me. Cool.
- MCPs are great but not fully necessary for "function shaped" things where you're trying to run some Function and that Function has a lot of parameters with some subtlety to them and perhaps needs some examples to really help the LLM understand. Though you can get away with a skill + curl, or a hand rolled script even.
- MCPs are not so great for interacting with more complex stateful systems with large surface area. You don't want/need an AWS MCP, for example. And of course Cloudflare is the canonical example here where they do have an MCP but it has a special "Code Mode" because they have a huge product surface and a lot of state.
Most companies are somewhere in the vast space between being a document store type thing and AWS, so aren't really sure what their MCP should look like, or how customers will use it, but feel like they're missing the boat if they don't ship something. So they ship an MCP and perhaps the people who need the document type stuff load it up and get some use out of it, but others are not so satisfied. Or maybe from the other direction, people are trying to use your product but aren't super technical or don't know how to best use it with AI, but "loading up an MCP" seems like a reasonable way to start, so they ask everyone "Where's your MCP"?
I run into this at work all the time. We get a lot of requests for an MCP. But our product is not so simple to just stuff into a bunch of stateless API calls. And we question whether the people requesting the MCP really know what they want it for, exactly, other than to hook up to claude code so they can say "claude go do everything" (which is a valid sentiment, but implies a lot of work on our end to figure out how to make that work well).
The second you utter the word git, you may have lost 90% of your audience - depending on their background, of course. MCPs are a lot more non-tech friendly
Its not that hard.
i dont understand why people are so invested in making this a winner-take-all battle. skills are ligthweight and ad-hoc, MCP is managed and centralized. there's a place for both of those things, even if your personal workflow only needs skills.
However, I don't think that's what is really hurting MCP, because it could evolve. What really killed it was the standards process and enterprise groups getting ahold of it. It went into spec writing and got adjudicated into uselessness all while enterprise authentication groups were figuring out the best angle to make money on it. I listened to a pitch from Okta on MCP and they wanted to charge out the nose for it for no good reason.
* CLI: GitHub & AWS it already knows how to operate the CLIs well. Even learned about a few new CLIs like 1Password's op which it volunteered one day.
* MCP: Supabase, Shopify etc. where the CLI would be non-obvious and the affordances from the tools/descriptions helps Claude maneuver.
* API: Sometimes it just knows an API exists and is able to call it directly with python/curl. I discovered from Claude the Pokemon ecosystem has a free API out there for example.
Not because it's better, but with one switch a significant portion of web traffic can be directed to A2A servers through Google's new search box.
MCPs are very useful when you don't have a CLI or you do but the MCP can handle auth like a proxy to something (e.g. Splunk). Or just for the USB-C analogy she gave.
I was also surprised to find out Claude knew how to use the gitlab api with pointing it at the token var in the environment. But for corporations it might make more sense to use a cli to keep the secrets separate from the agent.
What do you mean? Tool is a pretty generic concept.
Jira
Confluence
Gitlab
Logs & Metrics platform (inhouse solution)
QA (not sure what this one does)
Context7
mattermost
I have no idea about modern trands etc, but I wouldn't say that MCP is dead. Not the hottest new thing, sure.
Can someone explain this to me? I've seen claude code try to run a not-well-known package and it basically shot in the dark a command, noticed that failed, then ran the help command for the cli tool to get a list of commands and what they do.
How is that different than passing the tools with an MCP? Like how are we saving context?
The other thing is the agent gets the entire MCP API response dumped into context as a tool response in JSON, which can be a lot. Compare that to shell commands where agents often `head` or `tail` or `grep` the response (which I kinda hate, but it does save tokens).
It also depends on whether the agent loads them on-demand or not (most modern agents do), and whether your MCP has a ton of tools or not. If your MCP only has 2 tools, and the responses aren't big, it's really not that much context.
The other thing that doesn't get talked about is the non-determinism of shell one-liners. There is a lot more non-determinism in shell tool calls; the AI can mess up commands, options, arguments. It can incorrectly filter output, miss output, miss return status, which results in re-running calls, polluting context, making results worse. Compare that to MCP calls which are more likely to succeed because they have a schema, well-defined errors, etc. Do you want less token use or more reliable results?
The thing is, you don't have to pick a side. I personally use both MCPs and CLIs at different times in different ways. Often I'll have the AI write a small script to do many calls (sometimes with tools, sometimes with libraries) which saves tokens, allows me to review, and is more deterministic.
In the early days of computing, desktop apps and later webapps provided richer human experiences.
What will provide richer experiences for agents, after CLIs?
Oh. You mean that new thing also named MCP?
I use Playwright MCP, but there is absolutely no reason I'd keep it enabled in a Go project.
Clearly MCP is not dead, as the article itself says. But the article lies in order to play on human sentiment/heuristics and steal your attention. It's like shouting fire in order to get people to run over to see your business.
Turns LLMs are shit with JSON. Especially those JSON str embeded inside another JSON key-value pairs.
Why do smart ppl design a schema like escape JSON into str embeded into another?
It's based on another lie: AIs favor static typed languages.
https://en.wikipedia.org/wiki/Betteridge's_law_of_headlines
The good think about MCP is the authentication story. It is almost perfect. Compare this with CLIs which mostly piggy back on quirky browser authentication, env files and other bad practices. It is a security nightmare. It is certifiably insane.
So to compare MCPs to CLIs purely on token cost is missing the entire point that at the end of the day these agents need to operate safely and OAuth is the defacto standard where this can be done in somewhat consistent way across different vendors.
For example I have a no-auth clock for AI deployed from https://github.com/firasd/mcpclock to https://mcpclock.firasd.workers.dev/mcp (anyone is welcome to go ahead and add it to your AI apps as an MCP endpoint)
You can still call it via CLI if you're a MCP hater
curl -s -X POST "https://mcpclock.firasd.workers.dev/mcp" -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id": 1,"method":"tools/call","params":{"name":"clock_get","arguments":{}}}' event: message data: {"result":{"content":[{"type":"text","text":"[\n {\n \"timezone\": \"UTC\",\n \"iso\": \"2026-05-30T04:05:07.175Z\",\n \"unixtime\": 1780113907\n },\n {\n \"timezone\": \"Alphadec\",\n \"alphadec\": \"2026_K6G7_066464\"\n }\n]"}]},"jsonrpc":"2.0","id":1}
curl -s -X POST "https://mcpclock.firasd.workers.dev/mcp" -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id": 1,"method":"tools/list","params":{"name":"","arguments": {}}}' 2>&1 | grep '^data:' | sed 's/^data: //'| jq -r '.result. tools[].name' clock_get clock_day_info clock_convert clock_convert_alphadec clock_convert_unixtime clock_shift_utc clock_delta_utc clock_delta_alphadec
The "just use a CLI" crowd is implicitly assuming:
1) You're a developer 2) On a laptop 3) With a shell open Inside an agentic coding harness (Claude Code, Codex CLI, Cursor) 4) Working on a software project 5) That's like... maybe 2% of AI usage.
The other 98% is: Someone on the ChatGPT iOS app asking a question on the subway; Someone in Claude.ai web chatting about their calendar; Someone using ChatGPT Desktop to summarize their Notion; A non-developer using AI in a browser at work; Voice mode on a phone; An embedded chat widget on some company's website...
scrolls down the page...
> So is MCP really dead? Not entirely
sigh...
Until that happy day arrives I run every required MCP with mcpc.
[1] https://github.com/apify/mcpc
> Problem 1: It Devours the Context Window
Don't harnesses support progressive discovery these days?
Claude (200K).... GPT-4o..........?
> every MCP server adds a process layer between the LLM and the underlying API
But a CLI doesn't?
------------------
> Measurement: Tool Definition Sizes
> MCP Server: Linear, Notion, Slack, Postgres
Oh, so these are the MCP servers that are examples of context bloat we're going to replace! Later in the article:
> At Quandri we use all three approaches side by side...
> MCP for services without a strong CLI (Slack, Linear, Notion)
https://github.com/day50-dev/mcp-search-and-run
You can call it "rag for mcp". I was pushing it hard a few months ago and nobody seemed to care but I'm all in if the timing has caught up to the tech.
It's nontrivial effort: basically a giant survey of all the mcp servers, running inference over them to figure out how to instrument them, cross referencing to make sure they are the "official" sources (or at least the ones that search engines think are) then using qdrant to do embeddings and reranking and offering it for free.
If people have become interested I'm all in. I'll bring the infra back up. I just don't want to spin my wheels on dead end streets.
The value proposition is solid, the problem is real, this fix works, it's fast, it's free, and people give exactly zero shits. I dunno...
One day I'll figure it out, hopefully...
The only thing worse than the people saying it are the people that repeat it.
While the title is quite obnoxious, the author is right.
I don't think that anyone would argue against standardizing training for any model on ways of invoking tools through specific output templates (with MCP being an extension of that). However, the question is what is the best way of having the model use those tools? There are 2 options
1 - Encode actual functionality during training, let the model figure out how to use available tools to do what it needs to. Latest Claude models are a good example of this, when editing files if it encounters issues with the under the hood tool, it will write a bash python command to edit the file
2 - Describe functionality in instruction context. This allows you to define complex sequences of things to do, but at the risk of the model losing context as the conversation continues.
3 - Use tool calling, where every request gets an available tools section appended to it, and define the complex functionality in the static code (whether its local tools or MCP servers)
Ideally, if we are pushing towards smarter models, the answer is between 1 and 2, where you have a model that only has access to be able to run shell commands, and some memory that it can reference on sequences of shell commands to run. An MCP invocation is then a simple echo jsonrpc pipe to local executable or a curl command. Eventually, its probably worthwhile to have your LLM run in a CPU like sandbox where it can execute arbitrary assembly commands from sequences stored in memory to do what it needs to do.
Until then, 2 and 3 are really what we have for adapting with current frameworks.