What if you don't need MCP at all? • Hacker News Board

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

#131

Post by TranquilMarmot » Mon, Nov 17, 2025, 7:07 AM UTC

growt wrote: post #125

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

The mcp part is not essential for the actual controlling of the applications. You could “rip out” the mcp functionality and replace it with something else. The only reason why the authors chose mcp is most likely that it was the first and therefore most common plugin interface for llm tools.

Unfortunately, most standards that we end up with are only standard because they're are widely used and not because they are the best or they make the most sense.

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

#132

Post by block_dagger » Mon, Nov 17, 2025, 7:22 AM UTC

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…

Perhaps you haven't used many MCP server, but those that I have used (GitHub, Atlassian, Glean, BuildKite, Figma, Google Workspace, etc) work very well. They teach an LLM how to do exactly what you're saying - "use the API standards...your models/agents directly interact with those API endpoints." Most MCP severs don't sit in between the LLM and the API endpoints, they just teach them how to use the tools and then the LLM calls the APIs directly as any HTTP client would. I find it works quite well and seems far better than manually maintaining rules or pointing at docs and installing CLI tools (like "gh" for GitHub) or using curl to interact with APIs from a terminal within a chat session.

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

#133

Post by bradgessler » Mon, Nov 17, 2025, 7:29 AM UTC

MCP has been a weird ride. I built https://terminalwire.com before MCP was a thing to make it way easier for people to add a CLI/TUI to their web apps/SaaS.

Then MCP comes out and AI explodes, sucking all the air out of the room for non-AI tools.

Now it seems like AI can work with CLIs better than MCP, so I’m tempted to slap AI integration all over the project to better convey the idea.

It’s crazy how quickly MCP has run it’s course and watching an entire ecosystem rediscover things from first principals.

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

#134

Post by blitzar » Mon, Nov 17, 2025, 8:39 AM UTC

cyanydeez wrote: post #20

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…

probably easier to just tell people: You want MCP? Add a "description" field to your rest API that describes how to call it. That's all it's doing. Just plain ole context pollution. World could be better served by continuing to build out the APIs that exist.

> World could be better served by continuing to build out the APIs that exist.

before LLM's and MCP the world was depreciating or locking down APIs

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

#135

Post by pjmlp » Mon, Nov 17, 2025, 8:57 AM UTC

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…

Fully agree, however we need to reach our KPIs and OKRs regarding AI adoption.

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

#136

Post by 72deluxe » Mon, Nov 17, 2025, 11:22 AM UTC

MCP sounds like the modern equivalent of COM, where you could query an object to see what functions it exposed but had zero idea of what they did. MCP is the same: apparently it is LLM-readable, but the explanations of what everything does are human readable, and there is no standard on operations available.

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

#137

Post by frumplestlatz » Mon, Nov 17, 2025, 11:56 AM UTC

whoknowsidont wrote: post #115

paulddraper wrote: post #112

Earlier quoted context omitted.

The hate for MCP here is absurd. It's JSON-RPC, with some descriptors. And some comments about OAuth 2. The value is in the consensus. You can make a tool that agents can connect to with no apriori knowledge.

>It's JSON-RPC, with some descriptors. That's not even true. It defines the lifecycle of tool calling. JSON-RPC with some descriptors would have been fine and amazing.

I’m struggling to understand where you’re coming from. Your hate for MCP seems grossly outsized relative to what it actually is.

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

#138

Post by CuriouslyC » Mon, Nov 17, 2025, 12:06 PM UTC

sunaookami wrote: post #122

CuriouslyC wrote: post #58

Earlier quoted context omitted.

Claude Skills are just good documentation wrapped into Anthropic's API in a proprietary way that's designed to foster lock-in.

How are skills vendor lock-in when they're just Markdown files that any LLM can read? You are not locked to Anthropic at all.

The API runs your skills, it's not client side coordinated. You have to replicate the skill-running behavior locally.

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

#139

Post by manbitesdog » Mon, Nov 17, 2025, 12:28 PM UTC

paulddraper wrote: post #112

didibus wrote: post #108

Earlier quoted context omitted.

> MCP was a really shitty attempt at building a plugin framework Can you go more in depth? The protocol is relatively simple, what about it you feel is "shitty" as a plugin framework?

The hate for MCP here is absurd. It's JSON-RPC, with some descriptors. And some comments about OAuth 2. The value is in the consensus. You can make a tool that agents can connect to with no apriori knowledge.

Things like OpenAPI have existed for 15 years now and they also offer standarization.

The value on MCP is not on its features or innovation, but on the rate of adoption it has had. Companies have now an incentive to open, document and standarize their APIs to enable this new distribution channel.

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

#140

Post by filearts » Mon, Nov 17, 2025, 12:54 PM UTC

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 `cmd/mcp` and configure a `go run ./cmd/mcp` MCP server for the Agent.

It helps that I'm quite invested in MCP and built github.com/ggoodman/mcp-server-go, which is one of the few (only?) MCP SDKs that let you scale horizontally over https while still supporting advanced features like elicitation and sampling. But for local tools, I can use the familiar and ergonomic stdio driver and have my Agent pump out the tools for me.