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

The Future of MCPs

iamcharliegraham.substack.com

Post reply on HN
Print view View original

61–70 of 90 posts

Re: The Future of MCPs

#61

Post by szvsw »

quantadev wrote: post #57
happyopossum wrote: post #40

Earlier quoted context omitted.

> You didn't "build an MCP" The author explicitly states he built 2 MCP servers , not 2 MCPs, so I don’t know where your beef is coming from

I had the exact same reaction to the plural "MCPs". That's silly wording. There are no multiple MCPs. It's a single protocol. It's hilariously awkward wording to say you built "an MCP". It's like saying you built "an FTP", or "an HTTP". I guess every Web App is really just "an HTTP". We've been talking wrong all these years. lol.

On the other hand, IP addresses have crossed into the popular lexicon in exactly this manner… it’s common enough to hear people say “what’s my “ip?” or “are there any free ips?” or what are the IPs for x/y/z”.

I agree that it sounds stupid and incorrect, but that doesn’t necessarily mean using MCP as a metonym for MCP server.

Re: The Future of MCPs

#63

Post by lysecret »

baalimago wrote: post #58

If LLMs are so smart, why do they need a custom "MCP" format to what's commonly known as a normal API? Why can't they just call normal APIs? Extending this thought: why would there be any difference between offering data behind an API, and offering data behind a "MCP api"? At the end of the day, the underlying data will be the same (weather, stock market info, logs, whatever), it seems LLMs just needs this to be "sta…

Ye its also funny to me. On the one side people are saying: Look we have computer use, browser use etc. so we don't need an api! And on the other side saying, look apis are way too complicated we need our own protocol!

Re: The Future of MCPs

#64

Post by gadders »

fullstackchris wrote: post #44
troupo wrote: post #30

Earlier quoted context omitted.

> If MCPs gave the LLMs a window into all the major supermarkets home shopping sites that looks like it's a step closer. And how exactly will they do that?

Not OP but perhaps the following mcp tools: google maps api, nearest supermarkets, puppeteer their product listing pages? Though to be honest not sure why you would need so much info - if I need lettuce or tomatoes for example, I know theyre gonna be at essentially every supermarket in my area....

In the UK, most supermarkets offer their own home delivery services.

I was hoping that an LLM would do the heavy lifting of working out who can get your shopping cheapest from various supermarkets.

Probably not worth it if you're buying lettuce and tomatoes, but if you have a large family with a £100+ grocery bill per week it might be worth it?

Re: The Future of MCPs

#66

Post by Garlef »

daxfohl wrote: post #34
freedomben wrote: post #3

Interesting thoughts regarding MCPs being the future App Store/Platform. I don't know that I agree but I don't necessarily disagree either. Time will certainly tell. To me, MCP feels more like an implementation detail, not something that most people would ever use directly. I would expect that the future would be some app distributed through existing channels, which bundles the MCP client into it, then uses a server-…

I'd expect "local MCP servers" will be generally installed as part of something else. Photoshop, or Outlook, or whatever could come with a local MCP server to allow chat clients to automate them. Maybe printer drivers or other hardware would do similar. I don't think there's much reason to install a cloud service MCP server to run locally; you'd just use the one provided in the cloud.

Interesting thought.

But maybe the companies would actually like to at least pipe the communication throught the cloud to get all the usage data. Here's one possible architecture:

local chat client

  - talks to cloud LLM
  - talks to local MCP servers
local MCP server provided by company

  - connects to company cloud (this lets the company collect usage data)
  - forwards tasks to the cloud
local tool (for example photoshop)

  - connects to company cloud to get a users tasks
  - executes the tasks (this lets the company use the users hardware, saving cloud costs)

Re: The Future of MCPs

#67

Post by lou1306 »

gadders wrote: post #10

>>MCP Affiliate Shopping Engines As someone else once said, I want a Grocery Shopping Engine. "Here's my shopping list, taking into consideration delivery times and costs, please buy this for the lowest cost from any combination of supermarkets and deliver by day after tomorrow at the latest." If MCPs gave the LLMs a window into all the major supermarkets home shopping sites that looks like it's a step closer.

This requires arithmetics and constraint solving skills that are wildly out of reach to any pure-LLM platform. At the very least you would need interfacing with a real SMT or LP solver to get something that fits the bill.

Re: The Future of MCPs

#68

Post by johntash »

baalimago wrote: post #58

If LLMs are so smart, why do they need a custom "MCP" format to what's commonly known as a normal API? Why can't they just call normal APIs? Extending this thought: why would there be any difference between offering data behind an API, and offering data behind a "MCP api"? At the end of the day, the underlying data will be the same (weather, stock market info, logs, whatever), it seems LLMs just needs this to be "sta…

I don't understand why just using something like openapi specs didn't become the "normal" thing to do. We already have APIs for pretty much everything, why do we need a new protocol that wraps around an existing api?

Re: The Future of MCPs

#69

Post by gadders »

lou1306 wrote: post #67
gadders wrote: post #10

>>MCP Affiliate Shopping Engines As someone else once said, I want a Grocery Shopping Engine. "Here's my shopping list, taking into consideration delivery times and costs, please buy this for the lowest cost from any combination of supermarkets and deliver by day after tomorrow at the latest." If MCPs gave the LLMs a window into all the major supermarkets home shopping sites that looks like it's a step closer.

This requires arithmetics and constraint solving skills that are wildly out of reach to any pure-LLM platform. At the very least you would need interfacing with a real SMT or LP solver to get something that fits the bill.

Looks like we're stuck with coding assistants and Studio Ghibli pics then :-)

Re: The Future of MCPs

#70

Post by kanwisher »

3np wrote: post #16
guideamigo_com1 wrote: post #8

MCP might be one of the few technology pieces where more articles have been written about it than the actual use-cases being built. It is like the ERC20 era all over again.

ERC20 stood the test of time and is ubiquitous today. Who knows what MCP looks like in a decade?

yeah even with its extreme flaws of requiring two transactions per transfer, and not having any way of the destination reacting to the transfer without another transaction.
Post reply on HN