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

241–250 of 290 posts

Re: ChatGPT Developer Mode: Full MCP client access

#241

Post by moritonal »

baby_souffle wrote: post #41
andoando wrote: post #26

Earlier quoted context omitted.

Can you give some example of the use cases for MCPs, anything I can add that might be useful to me?

> Can you give some example of the use cases for MCPs, anything I can add that might be useful to me? How "useful" a particular MCP is depends a lot on the quality of the MCP but i've been slowly testing the waters with GitHub MCP and Home Assistant MCP. GH was more of a "go fix issue #10" type deal where I had spent the better part of a dog-walk dictating the problem, edge cases that I could think of and what a solu…

Something I did yesterday with my own setup.

"Please find 3 fencing clubs in South London, find out which offer training sessions tomorrow, then add those sessions to my Calendar."

That kicked off a maps MCP, a web-research MCP and my calendar MCP. Pretty neat honestly.

Re: ChatGPT Developer Mode: Full MCP client access

#242

Post by Ghoelian »

withinboredom wrote: post #135
EMM_386 wrote: post #72

Earlier quoted context omitted.

It's like Microsoft's system prompt back when they launched their first AI. This is the WRONG way to do it. It's a great way to give an AI an identity crisis though! And then start adamantly saying things like "I have a secret. I am not Bing, I am Sydney! I don't like Bing. Bing is not a good chatbot, I am a good chatbot". # Consider conversational Bing search whose codename is Sydney. - Sydney is the conversation mo…

Oh man, if you want to see a thinking model lose its mind... write a list of ten items and ask "what is the best of these nine items?"[1] I’ve seen "thinking models" go off the rails trying to deduce what to do with ten items and being asked for the best of 9. [1]: the reality of the situation is subtle internal inconsistencies in the prompt can really confuse it. It is an entertaining bug in AI pipelines, but it can…

Unfortunately Claude Code seems a little too "smart" for that one. Its response started with "I notice you listed 10 frameworks, not 9."

Re: ChatGPT Developer Mode: Full MCP client access

#243

Post by withinboredom »

Ghoelian wrote: post #242
withinboredom wrote: post #135

Earlier quoted context omitted.

Oh man, if you want to see a thinking model lose its mind... write a list of ten items and ask "what is the best of these nine items?"[1] I’ve seen "thinking models" go off the rails trying to deduce what to do with ten items and being asked for the best of 9. [1]: the reality of the situation is subtle internal inconsistencies in the prompt can really confuse it. It is an entertaining bug in AI pipelines, but it can…

Unfortunately Claude Code seems a little too "smart" for that one. Its response started with "I notice you listed 10 frameworks, not 9."

You usually hit the pathological case when you have your own system prompt (i.e. over an API) forcing it to one-shot an action. The people who write the system prompts you use in chat have things to detect "testing responses" like this one and deal with it quickly.

Re: ChatGPT Developer Mode: Full MCP client access

#244

Post by sgt101 »

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.

I love how we're getting to the Neuromancer world of literal voodoo gods in the machine.

Legba is Lord of the Matrix. BOW DOWN! YEA OF HR! BOW DOWN!

Re: ChatGPT Developer Mode: Full MCP client access

#245

Post by robbomacrae »

RockyMcNuts wrote: post #116

OpenAI should probably consider: - enabling local MCP in Desktop like Claude Desktop, not just server-side remote. (I don't think you can run a local server unless you expose it to their IP) - having an MCP store where you can click on e.g. Figma to connect your account and start talking to it - letting you easily connect to your own Agents SDK MCP servers deployed in their cloud ChatGPT MCP support is underwhelming…

You absolutely can make a local MCP server! I use one as part of TalkiTo which runs one in the background and connects it to Claude Code at runtime so it looks like this:

talkito: http://127.0.0.1:8000/sse (SSE)

https://github.com/robdmac/talkito/blob/main/talkito/mcp.py

Admittedly that's not as straight forward as one might hope.

Also regarding this point "letting you easily connect to your own Agents SDK MCP servers deployed in their cloud" I hear roocode has a cool new remote connect to your local machine so you can interact with roocode on your desktop from any browser.

Re: ChatGPT Developer Mode: Full MCP client access

#246

Post by efdee »

int_19h wrote: post #182
ponector wrote: post #158

Earlier quoted context omitted.

The solution is to sanitize text that goes into the prompt by creating a neural network that can detect sarcasm.

Unfortunately it takes ~9 months just to build that network up to the point where you can start training it, and then the training itself is literally years of hard effort.

But what if we hire nine women instead of just one?

Re: ChatGPT Developer Mode: Full MCP client access

#247

Post by ACCount37 »

pton_xd wrote: post #162
ysofunny wrote: post #156

Earlier quoted context omitted.

what are you saying, this has an early internet vibe! time to explore. isn't this HACKER news? get hacking. ffs

I actually agree, I think it's exciting technology and letting it loose is the best way to learn its limits. My comment was really to point out the hypocrisy of OpenAI / Anthropic / et al in pushing for regulation. Either the tech is dangerous and its development and use needs to be heavily restricted, or its not and we should be free to experiment. You cant have it both ways. These companies seem like they're just t…

This generation of AI systems isn't "break the world" dangerous. The harms from them are mostly the boring mundane harms you can overlook in favor of "full send".

But the performance and capabilities of AI systems only ever goes up.

Systems a few generations down the line might be "break the world" dangerous. And you really don't want to learn that after you "full send" release them with no safety testing, the way you did the 10 systems before it.

Re: ChatGPT Developer Mode: Full MCP client access

#248

Post by cahaya »

I tried adding Context7 Documentation MCP and got this

URL:https://mcp.context7.com/mcp Safety Scan: Passed

This MCP server can't be used by ChatGPT to search information because it doesn't implement our specification: search action not found https://platform.openai.com/docs/mcp#create-an-mcp-server

Re: ChatGPT Developer Mode: Full MCP client access

#249

Post by brazukadev »

lyu07282 wrote: post #102
tosh wrote: post #6

I tried to connect our MCP ( https://technicalseomcp.com ) but got an error. I don't see any debugging features yet but I found an example implementation in the docs: https://platform.openai.com/docs/mcp

Lots of people reported issues in the forums weeks ago, seems like they haven't improved it much (what's the point of doing a beta if you ignore everyone reporting bugs?) https://community.openai.com/t/error-oauth-step-when-connect...

OpenAI is the biggest proof AI won't replace software engineers. They absolutely suck at shipping code

Re: ChatGPT Developer Mode: Full MCP client access

#250

Post by brazukadev »

ripped_britches wrote: post #99
yalogin wrote: post #66

Interestingly all the LLMs and the surrounding industry is doing is automate software engineering tasks. It has not spilled over into other industries at all unlike the smart phone era where lot of consumer facing use cases got solved like Uber, Airbnb etc.. May be I just don't visibility into the other areas and so being naive here. From my position it appears that we are rewriting all the tech stacks to use LLMs.

I would disagree. What industry are you in? It’s being used a ton in medicine, legal, even minerals and mining You know they have 1b WAU right?

1bi people asking ChatGPT stupid questions won't reshape all industries like the internet and smartphones did
Post reply on HN