Same here. I was inspired by your post https://simonwillison.net/2026/Jul/31/stateless-mcp/

I reversed engineered my supermarket API and made a custom MCP to automate my grocery shopping. Now I can fill my cart through ChatGPT.

More details about it on https://ducret.dev/grocery-shopping-with-ai/

Strangely, it's currently not reported on both https://status.openai.com/ and https://updog.ai/status/openai. Any better source (other than HN)?

unexpected status 404 Not Found: Unknown error, url: https://chatgpt.com/backend-api/codex/responses, cf-ray: a355....

In codex app and chat.com gives 404

Status pages of tech firms being useless is basically a tradition at this stage

I see it reported now. Strange this is down and claude at the same time

Maybe coreweave, aws, spacex datacenters are down, who knows..

even grok is down ..

Very interesting, thanks!

For the fingerprinting part, can you explain the difference with the JShelter browser extension (https://jshelter.org/)?

I checked as you did in your demo video with https://demo.fingerprint.com/playground (using JShelter in Firefox). It produces a fingerprint detector report, like so :

{

    "fpd_evaluation_statistics": [
        {
            "title": "Navigator.prototype.plugins",
            "type": "resource",
            "resource": "get",
            "group": "BrowserProperties",
            "weight": 0,
            "accesses": 0
        },
        {
            "title": "MediaDevices.prototype.enumerateDevices",
            "type": "resource",
            "resource": "call",
            "group": "BrowserProperties",
            "weight": 1,
            "accesses": 2
        },
        [...]

}

However, it appears there is no way to display what was actually produced by the browser.

Was this the reason you had to build your own browser? Or is it possible to extend JShelter to do the same?

Ooh nice, I haven’t seen this project! I actually tried attempting this as an extension at first but wasn’t able to override page window functions. I’m curious to know how they accomplished this. (edit: I see that I missed the chrome.scripting API facepalm)

Thank you for sharing :)

FWIW I still think a custom browser approach has some benefits (stealth and executing in out of process iframes. could be wrong on the second part, haven’t actually tested!)

Take a look at https://www.tducret.com/pure-markdown It's just a single JS script import, and then plain Markdown. You can host it as-is, no build required (à la Jekyll, Hugo...).

You can verify the content with : curl https://www.tducret.com/pure-markdown/

Hey, I made a small JS that allows you to host a markdown file directly (no pre-conversion or plugin needed). It is rendered in the browser as HTML.

It can definitely be used in such a local website, giving the convenience of just writing plain markdown.

=> https://www.tducret.com/pure-markdown/

(source code) https://github.com/tducret/pure-markdown

Looks more like you just made an HTML page that invokes "marked. Min. Js" from the npm cdn. Neat demo.

This is nice. I have used https://ndossougbe.github.io/strapdown/ to quickly throw out MarkDown files for people to see as rendered HTMLs. I love the cleanliness of your script. Thanks.

Hi fellow hackers!

Yesterday, I've built a minimalist solution to let you host Markdown files, while rendering it as html in the browser.

No preprocessing needed (like Hugo, Jekyll, Astro...).

- You just write plain markdown

- Add a script import at the top

- Upload

Check it out > https://www.tducret.com/pure-markdown/