Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What if you don't need MCP at all?

mariozechner.at

Post reply on HN
Print view View original

181–190 of 194 posts

Re: What if you don't need MCP at all?

#181

Post by filearts »

lsaferite wrote: post #153
filearts wrote: post #140

What I've started experimenting with and will continue to explore is to have project-specific MCP tools. I add MCP tools to tighten the feedback loop. I want my Agent to be able to act autonomously but with a tight set of capabilities that don't often align with off-the-shelf tools. I don't want to YOLO but I also don't want to babysit it for non-value-added, risk-free prompts. So, when I'm developing in go, I create…

Horizontal scaling of remote MCP Servers is something the spec is sadly lacking any recognition around. If you've done work in this space, bravo. I've been using a message bus to decouple the HTTP servers from the MCP request handlers. I'm still evolving the solution, but it's been interesting so far.

This is the interface I landed on to make pluggable 'session hosts': https://github.com/ggoodman/mcp-server-go/blob/b8216cc1830ad...

It goes a tad beyond the spec minimum because I think it's valuable to be able to persist some small KV data with sessions and users.

Re: What if you don't need MCP at all?

#182

Post by anon84873628 »

voidhorse wrote: post #63
whoknowsidont wrote: post #15

MCP was a really shitty attempt at building a plugin framework that was vague enough to lure people into and then allow other companies to build plugin platforms to take care of the MCP non-sense. "What is MCP, what does it bring to the table? Who knows. What does it do? The LLM stuff! Pay us $10 a month thanks!" LLM's have function / tool calling built into them. No major models have any direct knowledge of MCP. Not…

Yeah there's no there there when it comes to MCP. It's crazy to me that the world bought into the idea when the "spec" literally boils down to "have your server give the LLM some json". Just illustrates how powerful it is to attach names to things, especially in a hypestorm in which everyone is already frothing at the mouth and reason is hard to come by. Give people some word they can utter to help them sound like th…

It gave everyone a reason to think about the usability of the interfaces they were exposing.

Many endpoints have tons of fields irrelevant to 95% of external users. Now those are gone.

Or they implemented higher level abstractions for the actual tasks instead of making developers compose a bunch of little pieces.

And it has a standardized manifest.

Execs, PMs, and customers having that word to utter as part of the AI hype train created the opportunity for that industry-wide cleanup to happen. Calling it pointless is very naive. It's actually kind of extraordinary.

Re: What if you don't need MCP at all?

#183

Post by anon84873628 »

cjonas wrote: post #93
whoknowsidont wrote: post #85

Earlier quoted context omitted.

>This effect is _significantly_ stronger than putting info about available API/cli into CLAUDE.md. No it's not. Honestly this conversation is extremely weird to me because somehow people are gravely misunderstanding what MCP even purports to do, let alone what it actually CAN do in the most ideal situation. It is a protocol and while the merits of that protocol is certainly under active discussion it's irrelevant bec…

This response is spot on. People seem very confused about what MCP actually is. It's just a standard way to provide an LLM with tools. And even how that happens is up to the agent implementation. There are some other less common features, but the core is just about providing tool definitions and handling the tool_call. Useful but basically just OpenAPI for LLM

I think people are really underappreciating the "OpenAPI for LLM" part. The hype forced a lot of different SaaS products and vendors of all stripes to actually follow a standard and think somewhat critically about the usability of what they expose.

Re: What if you don't need MCP at all?

#184

Post by voidhorse »

anon84873628 wrote: post #182
voidhorse wrote: post #63

Earlier quoted context omitted.

Yeah there's no there there when it comes to MCP. It's crazy to me that the world bought into the idea when the "spec" literally boils down to "have your server give the LLM some json". Just illustrates how powerful it is to attach names to things, especially in a hypestorm in which everyone is already frothing at the mouth and reason is hard to come by. Give people some word they can utter to help them sound like th…

It gave everyone a reason to think about the usability of the interfaces they were exposing. Many endpoints have tons of fields irrelevant to 95% of external users. Now those are gone. Or they implemented higher level abstractions for the actual tasks instead of making developers compose a bunch of little pieces. And it has a standardized manifest. Execs, PMs, and customers having that word to utter as part of the AI…

Thanks for offering another perspective on it. I can buy into this partially.

At the same time, I'm skeptical that this won't just become yet another dead protocol once the hype abates, at which point all of the perceived benefits were for naught.

Re: What if you don't need MCP at all?

#185

Post by jcelerier »

whoknowsidont wrote: post #150
nilslice wrote: post #119

Earlier quoted context omitted.

What do all of the links below have in common? Do you know of another way you can control all of those applications via LLMs? Computer use? https://github.com/ahujasid/ableton-mcp https://github.com/ahujasid/blender-mcp https://github.com/CoplayDev/unity-mcp https://github.com/mikechambers/adb-mcp

Can you do yourself a favor and look at the source code and tell me why you think MCP is necessary here? I mean you just took some examples and went "See MCP!" without any actual understanding of what that code is doing. All of these have underlying API's that have exactly ZERO need for MCP. All of this functionality already exists and can be used with LLM's. * https://help.ableton.com/hc/en-us/articles/209072009-Ins…

So again, how do I automate Ableton live over a network socket with a standard API? I don't know if you've read the remote control API but it doesn't open a magic socket to remote control Live, you have to code the entire integration and protocol yourself to map whatever API messages you want to Live actions manually.

Let's forget about LLMs completely as they are only tangentially relevant to the benefits of MCP. I want to write 15 lines of python that - no matter the software - is going to trigger the "play" button/action in that software. E.g. I want to hit "play" in both Ableton, Unity and Blender without having to write three times the code, without having to manually write them each an extension plug-ins. How do you do that, today, 2025-11-17 ?

Re: What if you don't need MCP at all?

#186

Post by paulddraper »

cstrahan wrote: post #166
didibus wrote: post #157

Earlier quoted context omitted.

Is that just bad implementation? Where are the wasted tokens? I noticed your second issue, but to me it's just from bad implementation. For some reason people keep exposing generic overlapping tools from multiple MCP servers. I don't know that MCP causes this issue, any vendor offering a "tools API" if they shove to many APIs it would bloat things up.

> Is that just bad implementation? Where are the wasted tokens? How wouldn't it be wasteful? I'll try to summarize a couple sources: https://www.anthropic.com/engineering/code-execution-with-mc... https://blog.cloudflare.com/code-mode/ Here's what Anthropic has to say about it: As MCP usage scales, there are two common patterns that can increase agent cost and latency: Tool definitions overload the context window; In…

> Now, if you were to instead have the LLM write code

Okay....now what function calls or libraries should the API use to write that code?

Anthropic article describes a good approach, combining code gen with MCP.

Re: What if you don't need MCP at all?

#187

Post by whoknowsidont »

lsaferite wrote: post #162
whoknowsidont wrote: post #161

Earlier quoted context omitted.

>To get this out of the way, you are an unpleasant person You are clearly very emotional about this, for whatever reason. But again it has no place on this forum. >I would point out that I haven't see one link in all of your railing against MCP until this very response. Because everything I've stated are fundamental facts about the technology. If you need sources for it, that means you are missing elementary concepts…

The absurdity of this response is astounding. As it's clear you have no actual interest is an honest discussion I'll just drop off here and leave you to your echo chamber.

I am actively involved in multiple threads across this post. Claiming I have no interest in "honest discussion" when it's clear people are engaging constructively elsewhere is a delusional take.

You came in, made things quite personal for no reason, and have said nothing that anyone can work with.

Just vague grandstanding.

Fix your attitude while on this forum.

Re: What if you don't need MCP at all?

#188

Post by cstrahan »

paulddraper wrote: post #186
cstrahan wrote: post #166

Earlier quoted context omitted.

> Is that just bad implementation? Where are the wasted tokens? How wouldn't it be wasteful? I'll try to summarize a couple sources: https://www.anthropic.com/engineering/code-execution-with-mc... https://blog.cloudflare.com/code-mode/ Here's what Anthropic has to say about it: As MCP usage scales, there are two common patterns that can increase agent cost and latency: Tool definitions overload the context window; In…

> Now, if you were to instead have the LLM write code Okay....now what function calls or libraries should the API use to write that code? Anthropic article describes a good approach, combining code gen with MCP.

> Okay....now what function calls or libraries should the API use to write that code?

Whatever the most popular library is which provides a client to whatever "thing" (locally running process, or service, or whatever) you are trying to interact with via LLM.

I have had LLMs generate probably 10s of thousands of lines of code, all without providing an MCP. LLMs can do that. They are trained on code.

What if there isn't a library available? Well, sure, then you could go implement an MCP server... or you could just write a library. It's practically the same effort.

Not that I'm 100% against MCP servers. But I think there's some misconception spreading across the software community that an MCP server is always inherently the optimal, obvious solution; all I'm suggesting is that people actually think about the problem, instead of outsourcing that responsibility via a "no one ever got fired for buying IBM" type of appeal to bandwagon fallacy.

Re: What if you don't need MCP at all?

#189

Post by cstrahan »

didibus wrote: post #179
cstrahan wrote: post #166

Earlier quoted context omitted.

> Is that just bad implementation? Where are the wasted tokens? How wouldn't it be wasteful? I'll try to summarize a couple sources: https://www.anthropic.com/engineering/code-execution-with-mc... https://blog.cloudflare.com/code-mode/ Here's what Anthropic has to say about it: As MCP usage scales, there are two common patterns that can increase agent cost and latency: Tool definitions overload the context window; In…

But none of the criticisms here is specific to MCP, just to tool calls in general, it wouldn't matter if the agent used a custom tool protocol, plain OpenAPIs, etc. These issues would still exist.

> These issues would still exist.

I just explained why these issues don't apply to the LLM writing and invoking code: again, this is because code can apply successive transformations to the input without having to feed the intermediate results into the LLM's context. That code can read a file that would weigh in at 50,000 tokens, chain 100 functions together, producing a line that would be 20 tokens, and only the LLM will only see the final 20 token result. That really is only 20 tokens for the entire result -- the LLM never sees the 50,000 tokens from the file that was read via the program, nor does the LLM see the 10s of thousands of tokens worth of intermediate results between the successive transformations from each of the 100 functions.

With MCP, there's no way for the LLM to invoke one tool call that expresses "compose/pipeline these 100 tools, please, and just give me the final result" -- the LLM must make 100 individual tool calls, manually threading the results through each tool call, which represents 100 opportunities for the LLM to make a mistake.

It sounds like you are disagreeing with what I am saying, but it doesn't look you're giving any reason why you disagree, so I'm a bit confused.

Re: What if you don't need MCP at all?

#190

Post by jrm4 »

chpatrick wrote: post #172
urbandw311er wrote: post #61

Earlier quoted context omitted.

Even with zero temperature (and some of the latest models don’t allow that) you’re still not absolutely guaranteed deterministic output.

What does deterministic mean in this case?

Right, I'm using a perhaps loose definition of deterministic here, as in -- "With AI tools, you cannot 100% predict any output based on input, the way you can with most programming."
Post reply on HN