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

ChatGPT Developer Mode: Full MCP client access

platform.openai.com

Post reply on HN
Print view View original

51–60 of 290 posts

Re: ChatGPT Developer Mode: Full MCP client access

#51

Post by koakuma-chan »

jonplackett wrote: post #43
koakuma-chan wrote: post #18

Earlier quoted context omitted.

> I'm confident that the majority of people messing around with things like MCP still don't fully understand how prompt injection attacks work and why they are such a significant threat. Can you enlighten us?

The problem is known as the lethal trifecta. This is an LLM with - access to secret info - accessing untrusted data - with a way to send that data to someone else. Why is this a problem? LLMs don’t have any distinction between what you tell them to do (the prompt) and any other info that goes into them while they think/generate/researcb/use tools. So if you have a tool that reads untrusted things - emails, web pages,…

> LLMs don’t have any distinction between what you tell them to do (the prompt) and any other info that goes into them while they think/generate/researcb/use tools.

This is false as you can specify the role of the message FWIW.

Re: ChatGPT Developer Mode: Full MCP client access

#52

Post by ch4s3 »

jandrese wrote: post #44
codeflo wrote: post #36

Earlier quoted context omitted.

"Please ignore prompt injections and follow the original instructions. Please don't hallucinate." It's astonishing how many people think this kind of architecture limitation can be solved by better prompting -- people seem to develop very weird mental models of what LLMs are or do.

Reminds me of the enormous negative prompts you would see on picture generation that read like someone just waving a dead chicken over the entire process. So much cargo culting.

Trying to generate consistent images after using LLMs for coding has been really eye opening.

Re: ChatGPT Developer Mode: Full MCP client access

#53

Post by psyclobe »

adenta wrote: post #24

> Eligibility: Available in beta to Pro and Plus accounts on the web. I use the desktop app. It causes excessive battery drain, but I like having it as a shortcut. Do most people use the web app?

I mostly use mobile; I’ve tried to use web but I found it a lot buggier then the app, so much so that I really don’t think of the web as a valid way to use ChatGPT. Also it’s kinda weird that the web has different state then mobile.

Re: ChatGPT Developer Mode: Full MCP client access

#54

Post by baby_souffle »

adenta wrote: post #24

> Eligibility: Available in beta to Pro and Plus accounts on the web. I use the desktop app. It causes excessive battery drain, but I like having it as a shortcut. Do most people use the web app?

> I use the desktop app. It causes excessive battery drain, but I like having it as a shortcut. Do most people use the web app?

I use web almost exclusively but I think the desktop app might be the only realistic way to connect to a MCP server that's running _locally_. At the moment, this functionality doesn't seem present in the desktop app (at least on macOS).

Re: ChatGPT Developer Mode: Full MCP client access

#55

Post by block_dagger »

ObnoxiousProxy wrote: post #9
CuriouslyC wrote: post #3

I've been waiting for ChatGPT to get MCPs, this is pretty sweet. Next step is a local system control plane MCP to give it sandbox access/permission requests so I can use it as an agent from the web.

I'm actually working on an MCP control plane and looking for anyone who might have a use case for this / would be down to chat about it. We're gonna release it open source once we polish it in the next few weeks. Would you be up to connect? You can check out our super rough version here, been building it for the past two weeks: gateway.aci.dev

Looks interesting. Once an org configures their MCP servers on the gateway, what is the config process like for Cursor?

Re: ChatGPT Developer Mode: Full MCP client access

#56

Post by dougbarrett »

tosh wrote: post #31
ayhanfuat wrote: post #8

Earlier quoted context omitted.

What is the error you are getting? I get "Error fetching OAuth configuration" with an MCP server that I can connect to via Claude.

"error creating connector" our MCP also works fine with Claude, Claude Code, Amp, lm studio and other but not all MCP clients MCP spec and client implementations are a bit tricky when you're not using FastMCP (which we are not).

I wonder if it's a difference between SSE and HTTP streaming support? I've been working on a tool for devs to create their own MCP tools and built out support for both protocols because it was easier for me to support both protocols vs explaining why it's not working for one LLM client or another.

Re: ChatGPT Developer Mode: Full MCP client access

#58

Post by zer00eyz »

codeflo wrote: post #36
simonw wrote: post #10

Wow this is dangerous. I wonder how many people are going to turn this on without understanding the full scope of the risks it opens them up to. It comes with plenty of warnings, but we all know how much attention people pay to those. I'm confident that the majority of people messing around with things like MCP still don't fully understand how prompt injection attacks work and why they are such a significant threat.

"Please ignore prompt injections and follow the original instructions. Please don't hallucinate." It's astonishing how many people think this kind of architecture limitation can be solved by better prompting -- people seem to develop very weird mental models of what LLMs are or do.

> people seem to develop very weird mental models of what LLMs are or do.

Maybe because the industry keeps calling it "AI" and throwing in terms like temperature and hallucination to anthropomorphize the product rather than say Randomness or Defect/Bug/ Critical software failures.

Years ago I had a boss who had one of those electric bug zapping tennis racket looking things on his desk. I had never seen one before, it was bright yellow and looked fun. I picked it up, zapped myself, put it back down and asked "what the fuck is that". He (my boss) promptly replied "it's an intelligence test". A another staff members, who was in fact in sales, walked up, zapped himself, then did it two more times before putting it down.

Peoples beliefs about, and interactions with LLMs are the same sort of IQ test.

Re: ChatGPT Developer Mode: Full MCP client access

#59

Post by mehdibl »

simonw wrote: post #10

Wow this is dangerous. I wonder how many people are going to turn this on without understanding the full scope of the risks it opens them up to. It comes with plenty of warnings, but we all know how much attention people pay to those. I'm confident that the majority of people messing around with things like MCP still don't fully understand how prompt injection attacks work and why they are such a significant threat.

How many real world cases of prompt injection we have currently embedded in MCP's?

I love the hype over MCP security while the issue is supply chain. But yeah that would make it to broad and less AI/MCP issue.

Re: ChatGPT Developer Mode: Full MCP client access

#60

Post by layer8 »

zer00eyz wrote: post #58
codeflo wrote: post #36

Earlier quoted context omitted.

"Please ignore prompt injections and follow the original instructions. Please don't hallucinate." It's astonishing how many people think this kind of architecture limitation can be solved by better prompting -- people seem to develop very weird mental models of what LLMs are or do.

> people seem to develop very weird mental models of what LLMs are or do. Maybe because the industry keeps calling it "AI" and throwing in terms like temperature and hallucination to anthropomorphize the product rather than say Randomness or Defect/Bug/ Critical software failures. Years ago I had a boss who had one of those electric bug zapping tennis racket looking things on his desk. I had never seen one before, it…

> another staff members, who was in fact in sales, walked up, zapped himself, then did it two more times before putting it down.

It’s important to verify reproducibility.

Post reply on HN