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

191–200 of 290 posts

Re: ChatGPT Developer Mode: Full MCP client access

#191

Post by bhy »

n8m8 wrote: post #131
theshrike79 wrote: post #38

Earlier quoted context omitted.

Playwright mcp lets the agent operate a browser to test the changes it made, it can click links, execute JavaScript and analyse the dom

+1, I have a c4ai docker container + brave search MCP (2000 queries/mo free!) running on my laptop so I can ask claude code to do research similar to GPT deep research, but I config to ignore robots.txt since it's a one-off instance collecting data on my personal behalf, not a service (At least that's how I justify it)

What is c4ai? Crawl4ai?

Re: ChatGPT Developer Mode: Full MCP client access

#192

Post by mickael-kerjean »

tosh wrote: post #77
dougbarrett wrote: post #56

Earlier quoted context omitted.

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.

Oh, that might be it! Ours doesn’t support SSE.

mine does support SSE (https://github.com/mickael-kerjean/filestash) but it fails before getting there, with the log looking like this:

    2025/09/11 01:16:13 HTTP 200 GET    0.1ms /.well-known/oauth-authorization-server
    2025/09/11 01:16:13 HTTP 200 GET    2.5ms /
    2025/09/11 01:16:14 HTTP 404 GET    0.2ms /favicon.svg
    2025/09/11 01:16:14 HTTP 404 GET    0.2ms /favicon.png
    2025/09/11 01:16:14 HTTP 200 GET    0.2ms /favicon.ico
    2025/09/11 01:16:14 HTTP 200 GET    0.1ms /.well-known/oauth-authorization-server
    2025/09/11 01:16:15 HTTP 201 POST    0.3ms /mcp/register
    2025/09/11 01:16:27 HTTP 200 GET    1.4ms /
with the frontend showing: "Error creating connector" and the network call showing: { "detail": "1 validation error for RegisterOAuthClientResponse\n Input should be a valid dictionary or instance of RegisterOAuthClientResponse [type=model_type, input_value='{\"client_id\":\"ChatGPT.Dd...client_secret_basic\"}\\n', input_type=str]\n For further information visit https://errors.pydantic.dev/2.11/v/model_type" }

Re: ChatGPT Developer Mode: Full MCP client access

#193

Post by srcreigh »

daft_pink wrote: post #79
jumploops wrote: post #69

The 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.

I’m just confused about the line that says this is available to pro and plus on the web. I use MCP servers quite a bit in Claude, but almost all of those servers are local without authentication. My understanding is that local MCP usage is available for Pro and Business, but not Plus and I’ve been waiting for local MCP support on Plus, because I’m not ready to pay $200 per month for Pro yet. So is local MCP support s…

Use codex CLI

Re: ChatGPT Developer Mode: Full MCP client access

#194

Post by qarl »

ch4s3 wrote: post #150
withinboredom wrote: post #133

Earlier quoted context omitted.

Your question is a bit like asking how a word processor is better than a typewriter... they both produce typed text, but otherwise not comparable.

I'm looking at their blog[1] and yeah it looks like they're doing literally the exact same thing the other tools I named are doing but with a UI inspired by things like shader pipeline tools in game engines. It isn't clear how it's doing all of the things the grandparent is claiming. [1] https://blog.comfy.org/p/nano-banana-via-comfyui-api-nodes

There's no need to belittle dataflow graphs. They are quite a nice model in many settings. I daresay they might be the PERFECT model for networks of agents. But time will tell.

Think of it this way: spreadsheets had a massive impact on the world even though you can do the same thing with code. Dataflow graph interfaces provide a similar level of usefulness.

Re: ChatGPT Developer Mode: Full MCP client access

#195

Post by philipov »

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.

"do_not_crash()" was a prophetic joke.

Re: ChatGPT Developer Mode: Full MCP client access

#196

Post by stingraycharles »

andoando wrote: post #26
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.

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

I use zen-mcp-server for workflow automation. It can do stuff like analyzing codebases, planning and also features a “consensus” tool that allows you to query multiple LLM to reach a consensus on a certain problem / statement.

Re: ChatGPT Developer Mode: Full MCP client access

#197

Post by downboots »

akomtu wrote: post #151
pton_xd wrote: post #123

AI companies: Agentic AI has been weaponized. AI models are now being used to perform sophisticated cyberattacks, not just advise on how to carry them out. We need regulation to mitigate these risks. The same AI companies: here's a way to give AI full executable access to your personal data, enjoy!

Today it's full access to your laptop, a decade from now it will be full access to your brain. Isn't it the goal of tech like neuralink?

In the year 252525... https://www.youtube.com/watch?v=zKQfxi8V5FA

Re: ChatGPT Developer Mode: Full MCP client access

#198

Post by dstroot »

toomuchtodo wrote: post #45
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.

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.

HR driving a tech initiative... Checks out.

Re: ChatGPT Developer Mode: Full MCP client access

#199

Post by adastra22 »

jazzyjackson wrote: post #155
adastra22 wrote: post #75

Earlier quoted context omitted.

How would it have access to API keys? You don’t put those in your git repo, do you?

If the code can call a method that provides the API key, what would stop the LLM from calling the same code? How do you propose to let an LLM run tests that execute code that requires API without the LLM also being able to grab the key?

I don’t give it access to calls requiring API keys in the first place.

This is just good dev environment stuff. Have locally hosted substitutes for everything. Run it all in docker.

Re: ChatGPT Developer Mode: Full MCP client access

#200

Post by CuriouslyC »

ObnoxiousProxy wrote: post #174
CuriouslyC wrote: post #13

Earlier quoted context omitted.

A MCP gateway is a useful tool, I have a prototype of something similar I built but I'm not super enthusiastic about working on it (bigger fish to fry). One thing I'd suggest is to have a meta-mcp that an agenct can query to search for the best tool for a given job, that it can then inject into its context. Currently we're all manually injecting tools but it's a pain in the ass, we tend to pollute context with tools…

Our gateway lets team members bundle together configured MCPs into a unified MCP server with only two tools -- search and execute, basically a meta-mcp! Very interesting! What kind of use cases are you using your agent (Smith) for? Is it primarily coding, or quite varied across the board?

Right now I'm 100% coding focused, that's the big show in terms of agents. Orchestrating current agent tools is clunky, they're low performance, they lack fine grained extensibility to really modify their behavior on a dynamic task based basis (CC's hooks are the "best" option and they're really weak), the security model around them is flawed, there's a laundry list of issues with them.

The agent itself is designed to be very general, every trace action has hooks that can transform the payload using custom javascript, so you can totally change the agent's behavior dynamically, and the system prompts are all composed from handlebars templates that you can mix/match. The security model makes it great for enterprise deployment because instead of installing agent software on systems or giving agents limited shell access to hosts, you install a small secure binary that basically never changes on hosts, and a single orchestrator service can be a control plane for your entire enterprise. Then every action your agent takes is linked into the same reactive distributed system, so you can trigger other actions based on it besides just fulfillment of intent.

Post reply on HN