Pinned Tweet
super excited to announce plugin extensions today 🎉
you can now use the exact same platform we use to build ChatGPT features like meetings, health, finance, and many others 🤯
all based on the same MCP & MCP Apps you’re already used to: github.com/openai/mcp-extens…
Introducing Raycast MCP 🔌
Use Raycast from any agent:
📂 Access your Notes, Clipboard History and more
⌨️ Automate your setup, like assigning hotkeys
🧠 Share AI Memory with agents like Claude and Codex
Turn it on in Settings → MCP
Changelog 👉 raycast.com/changelog
Max Stoiber retweeted
Product Hunt insider tip (I'm the CEO):
Launches submitted via MCP are 3 times more likely to be featured than manual launches.
Our MCP actually helps you create a better launch.
We just released the future of Product Hunt
Builders: you can launch via MCP, and find related / competitive products for research and inspiration!
Investors: Find the most compelling new startups to invest in, including filtering by our proprietary model which predicts Series A likelihood
Operators: Find the right tool by searching over 500,000 apps
Try it out and let me know what you think!
please don’t restrict your MCP server to only have a “ask_agent” tool or similar, please expose actual tools
your agent doesn’t have any context on who i am, so it’s answers are going to be much worse for me than if my agent can access the data directly and put it into context
that being said, the pain point of getting feedback about what users are using your MCP for is real. some early solutions coming to chatgpt plugins there soon 👀
This is why you should actively invest in an embedded agent and an MCP.
MCP observability only allows you to see tools called and you have to reverse engineer intent.
If you have an actively used embedded agent, you would have seen this query and been able to ID that the proper filters were not in place. Fix the tool and it benefits both surfaces.
You can also get a lot of benefits by adding a submit_feedback tool to your MCP to gather this data.
Max Stoiber retweeted
resumes are looking super different than they were even 6mos ago. it’s very clearly a result of ai-assistance (slop) in applying for jobs.
so! be the change and all that - here’s what i’m seeing (plz spread the word).
our devday talk on chatgpt plugins is live!
if you’re curious about how you can extend chatgpt, watch this. @coreyching and I walk you through a few of our favorite plugins live and then show how they work under the hood 👀
youtube.com/watch?v=pIW_8Vyv…
Max Stoiber retweeted
fyi, eligible ChatGPT users can get a @Yubico bundle 46% off right now
just go to this link: chatgpt.com/yubikey
my recommendation: use ChatGPT computer use to help set up your C Nano and C NFC
then throw the C NFC on your keys // Nano on mac/pc
stay secure friends!
Max Stoiber retweeted
MCP is all about openess and working together. If it is a good idea, we adopt it. Looking forward to working together to standardize it as part of MCP apps and giving it a modelcontextprotocol.io key
Max Stoiber retweeted
Labs innovating together ftw
Replying to @claudeai
Also new: with interactive connectors, you can now open the full version of a tool inside Claude. Work in Adobe, Atlassian, and Box beside your conversation. Make changes yourself, or ask Claude to make them with you.
Rolling out on web and desktop.
mine too.
super great news for all our partners who have already built extensions: now they'll just work™ with Claude, too!
powered by OpenAI plugin extensions 🤯
github.com/openai/mcp-extens…
Replying to @claudeai
Also new: with interactive connectors, you can now open the full version of a tool inside Claude. Work in Adobe, Atlassian, and Box beside your conversation. Make changes yourself, or ask Claude to make them with you.
Rolling out on web and desktop.
Max Stoiber retweeted
So bullish on MCP. Its utility exceeds the "M" part: even AI aside, it'll be a civilization-scale accomplishment to get all our systems communicating through one universal open protocol.
A missing piece was how to get arbitrary callbacks across sessions. MCP could read and write, but it couldn't tell you later "this event happened." MCP Events fixes this.
We're adding support in our own MCP. Say an agent makes a deployment, and wants to know when it's complete. Instead of polling, it can subscribe to 𝚍𝚎𝚙𝚕𝚘𝚢𝚖𝚎𝚗𝚝.𝚜𝚞𝚌𝚌𝚎𝚎𝚍𝚎𝚍.
PSA: With Vercel Queues and Workflows, writing the backend machinery for your own MCPs to do this is easy peasy.
Vercel MCP now publishes events.
Agents can subscribe to events like 𝚍𝚎𝚙𝚕𝚘𝚢𝚖𝚎𝚗𝚝.𝚜𝚞𝚌𝚌𝚎𝚎𝚍𝚎𝚍 and 𝚍𝚎𝚙𝚕𝚘𝚢𝚖𝚎𝚗𝚝.𝚎𝚛𝚛𝚘𝚛 and get webhook notifications when they fire. No more polling for changes.
Changelog → vercel.com/changelog/vercel-…
Max Stoiber retweeted
Ever thought about building your own games? The Codex edition @modretro Chromatic is now on Supply Co.
With the ModRetro Chromatic plugin in Codex, you can design levels, animate sprites, and playtest on your handheld.
Speedrun checkout while Codex builds your ROM 😉
Max Stoiber retweeted
Not gonna lie. The process for submitting plugins to the @ChatGPT marketplace has been a bit painful...but I'm actually very impressed with how quickly the @OpenAI team has responded to our feedback.
The review process used to be weeks and now it's a day. Reported a confusing version mismatch in the UI today and it was fixed in hours.
Max Stoiber retweeted
integrating with OpenAI can drive a lot of business:
Max Stoiber retweeted
btw, am now leading ChatGPT/Codex Web + Desktop infra group
if you’ve already made other developers meaningfully faster (platform, tooling, reliability, DX), the opportunity is to do the same work at AGI scale
hit me up if interested
RT @Foamyseal: we are aware & actively fixing an issue that prevents devs from creating new plugins or updating existing plugin metadata in…
We've scaled source control at @OpenAI to keep up with merges, commits, & repo growth.
Here's our technical blog post about how we do it.
& one more thing: we've kept git compatibility, and we continue to contribute generally useful changes upstream.
This is just the start.





























