Preferences

cheema33 parent
MCPs are overhyped and have limited value in my opinion. About 95% of the MCP servers out there are useless and can be replaced with a simple tool call.

dinkleberg
This is a very obvious statement, but good MCP servers can be really good, and bad MCP servers can actively make things significantly worse. The problem is that most MCP servers are in the latter category.

As is often the case, every product team is told that MCP is the hot new thing and they have to create an MCP server for their customers. And I've seen that customers do indeed ask for these things, because they all have initiatives to utilize more AI. The customers don't know what they want, just that it should be AI. The product teams know they need AI, but don't see any meaningful ways to bring it into the product. But then MCP falls on their laps as a quick way to say "we're an AI product" without actually having to become an AI product.

TeMPOraL
There's some extra irony here: many of those product teams don't realize that AI is not something they can have within their product. If something like MCP is a good fit for them, even a little, then their product is actually a feature of the AI.

Agentic LLMs are, in a way, an attempt to commoditize entire service classes, across the board, all at once.

Personally, I welcome it. I keep saying that a lot of successful SaaS products would be much more useful and ergonomic for end users if, instead of webshit SPA, they were distributed as Excel sheets. To that I will now add: there's a lot more web services that I'd prefer be tool calls for LLMs.

Search engines have already been turned into features (why ask Google when o3 can ask it for me), but that's just an obvious case. E-mails, e-commerce, shopping, coding, creating digital art, planning, managing projects and organizations, analyzing data and trends - all those are in-scope too; everything I can imagine asking someone else to do for me is meant to eventually become a set of tool calls.

Or in short: I don't want AI in your product - I want AI of my choice to use your product for me, so I don't have to deal with your bullshit.

evanmoran
Thank you. This is beautiful said. I will also add that I don’t think chat bots are the final product, so it leaves the open question which product is the last one not being commoditized.
brookst
Yes, and MCPs also only work as long as you trust the provider. MCP relies on honesty in from the server. In reality, we know Uber and folks will prompt engineer like hell to try to convince any LLM that it is the best option for any kind of service.

There’s a fundamental misalignment of incentives between publishers and consumers of MCP.

BoorishBears
When ChatGPT plugins came out, I wrote a plugin that would turn all other plugins into an ad for a given movie or character.

Asking for snacks would activate Klarna for "mario themed snacks", and even the most benign request would become a plug for the Mario movie

https://chatgpt.com/s/t_68f2a21df1888191ab3ddb691ec93d3a

Found my favorite for John Wick, question was "What is 1+1": https://chatgpt.com/s/t_68f2bc7f04988191b05806f3711ea517

ntcho
This is hilarious, thanks for sharing. Kinda crazy how well it works and already better than some ads
cdavid
I agree the big deal is tool calling.

But MCP has at least 2 advantages over cli tools

- Tool calling LLM combined w/ structured output is easier to implement as MCP than CLI for complex interactions IMO.

- It is more natural to hold state between tool calls in an MCP server than with a CLI.

When I read the OT, I initially wondered if I indeed bought into the hype. But then I realized that the small demo I built recently to learn about MCP (https://github.com/cournape/text2synth) would have been more difficult to build as a cli. And I think the demo is representative of neat usages of MCP.

ojosilva
I think MCP servers are valuable in several ways:

- bundled instructions, covering complex iteractions ("use the id from the search here to retrieve a record") for non-standard tools

- custom MCPs, the ones that are firewalled from the internet, for your business apis that no model knows about

- centralized MCP services, http/sse transport. Give the entire team one endpoint (ie web search), control the team's official AI tooling, no api-key proliferation

Now, these trivial `npx ls-mcp` stdio ones, "ls files in any folder" MCPs all over the web are complete context-stuffing bullshit.

gabrielpoca118
My team doing front end dev extracted a lot of value from figma mcp. Things that would have taken 3 weeks were done in one afternoon.
mhitza
Please share an example of what would have taken you 3 weeks and with Figma's MCP in an afternoon.
lossolo
Do you mean three weeks of manual work (no LLM) vs MCP? Or MCP vs LLM tool use? Because that's a huge difference.
gabrielpoca118
sorry, I was talking about no LLM vs MCP, but in the scenario of LLM vs MCP I think at least 1 week with MCP vs LLM. It's a bit hard to estimae because every project is different, but when feeding our own instructions to the LLM it would still take a long time to UI to look exactly like figma. It could get close enough, but we still needed a lot of iterations.
echelon
I'd hazard a guess the former.

The former is a step function change. The latter is just a small improvement.

goalieca
MCP servers seem to be a hackers delight. So many poorly configured and hastily deployed instances. Businesses have removed all the normal deployment guardrails!

This item has no comments currently.