First the page gave me an error message. I refreshed and then it said my browser was "out of date" (read: fingerprint resistance is turned on). Turned that off and now I just get an endless captcha loop. I give up.
OpenAI quality level
ChatGPT Developer Mode: Full MCP client access
251–260 of 290 posts
Re: ChatGPT Developer Mode: Full MCP client access
#252I don't understand how this is dangerous. Can someone explain how this is different than just connecting the MCP normally and prompting it to use the same tools? I understand that this is just a "slightly more technical" means to access the same tools. What am I missing? Two replies to this comment have failed to address my question. I must be missing something obvious. Does ChatGPT not have any MCP support outside o…
Yup. ChatGPT did not have proper MCP support until now. They only supported MCP for connecting Deep Research to additional data sources, and for that, your MCP server had to implement two specific tools that Deep Research is able to call.
What’s being released here is really just proper MCP support in ChatGPT (like Claude has had for ages now) though their instructions regarding needing to specific about which tools to use make me wonder how effective it will be compared to Claude. I assume it’s hidden behind “Developer Mode” to discourage the average ChatGPT user from using it given the risks around giving an LLM read/write access to potentially sensitive data.
Re: ChatGPT Developer Mode: Full MCP client access
#253The title should be: "ChatGPT adds full MCP support" Calling it "Developer Mode" is likely just to prevent non-technical users from doing dangerous things, given MCP's lack of security and the ease of prompt injection attacks.
Ok, we've added full MCP support to the title above. Thanks!
[dead]
Re: ChatGPT Developer Mode: Full MCP client access
#254OpenAI 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…
`tailscale serve` is easy.
Set appropriate permissions/credentials to authenticate your ChatGPT to the MCP.
Re: ChatGPT Developer Mode: Full MCP client access
#255Earlier quoted context omitted.
Imagine running an MCP server inside your network that grants you access to some internal databases. You might expect this to be safe but once you connect that internal MCP server to an AI agent all bets are off. It could be something as simple as the AI agent offering to search the Internet but being convinced to embed information provided from your internal MCP server into the search query for a public (or adversar…
I see. It's wild to me that people would be that trusting of LLMs.
This seems like the obvious outcome, considering all the hype. The more powerful the AI, the more power it has to break stuff. And there is literally ZERO possibility to remove that risk. So, whos going to tell your gungho CEO that the fancy features he wants are straight up impossible, without a giant security risk?
Re: ChatGPT Developer Mode: Full MCP client access
#256Earlier quoted context omitted.
The solution is to sanitize text that goes into the prompt by creating a neural network that can detect prompts
I'm working on new technology where you separate the instructions and the variables, to avoid them being mixed up. I call it `prepared prompts`.
This thread is filled with comments where I read, giggle and only then realise that I cannot tell if the comment was sarcastic or not :-/
If you have some secret sauce for doing prepared prompts, may I ask what it is?
Re: ChatGPT Developer Mode: Full MCP client access
#257Earlier quoted context omitted.
I'm working on new technology where you separate the instructions and the variables, to avoid them being mixed up. I call it `prepared prompts`.
This thread is filled with comments where I read, giggle and only then realise that I cannot tell if the comment was sarcastic or not :-/ If you have some secret sauce for doing prepared prompts, may I ask what it is?
I think it's meant to be a riff in prepared procedures?
Re: ChatGPT Developer Mode: Full MCP client access
#258Earlier quoted context omitted.
I'm working on new technology where you separate the instructions and the variables, to avoid them being mixed up. I call it `prepared prompts`.
This thread is filled with comments where I read, giggle and only then realise that I cannot tell if the comment was sarcastic or not :-/ If you have some secret sauce for doing prepared prompts, may I ask what it is?
I think it's meant to be a riff in prepared procedures?
Re: ChatGPT Developer Mode: Full MCP client access
#259Earlier 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.
I was recently in a call (consulting capacity, subject matter expert) where HR is driving the use of Microsoft Copilot agents, and the HR lead said "You can avoid hallucinations with better prompting; look, use all 8k characters and you'll be fine." Please, proceed. Agree with sibling comment wrt cargo culting and simply ignoring any concerns as it relates to technology limitations.
"Can I get that in writing?"
They know it's wrong, they won't put it in an email
Re: ChatGPT Developer Mode: Full MCP client access
#260Wow 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.
[dead]