Munam

Was great to work on this and meet all the builders using the tool at large. Just want to keep people safe!

Hi! Really big fan of the work you guys are doing over at Stytch as well! We actually got started by thinking of what "agent native auth" looks like as a first-principle and realized the problem space was more than that, and what we actually wanted to tackle was making it as easy and seamless as possible for teams to ship with the tools they want.

We've talked to several massive Fortune 100 companies that have hundreds of models/workflows that have been developed but are stuck in purgatory because they can't get approved for production because of IT, Compliance, and Security Teams blocking them (for good reason!).

This MCP Security Analyzer was a natural thing that we would've had to build out regardless as we felt like it was table stakes for our Confidential Compute stack and we wanted to open-source it for everyone.

Would love to get in touch with you and chat because I think that there's a lot of areas where we trade notes.

My email is [email protected] or you can drop your email and I'll shoot you a note! Thanks!

Helped to build this out a little bit. Was really cool to get to play with Cerberus for the first time as well.

I'm really interested in learning more about how devs integrate MCP security into their routine code evals.

I think there's a big opportunity as a space to get tools like this into CI/CD pipelines and workflows.

Happy to answer any questions and happy to hear any feedback!

Thanks for checking it out :)

It's not all a buzzword fest.

I work as a Computational Researcher at Stanford Med. My work is quite literally translating 3D scans of the eyes (read MRI) into "digital twins" (read FEA Models).

I think that there is a subtlety in differentiating a digital twin from a model/simulation in intent. Our intent is to quite literally figure out how to use the digital twin specifically, NOT the scan that it is based on, as a way to replace more invasive diagnostics.

Of course, in the process, we figure out more about diagnosing medical problems as a function of just the scans themselves too.

Shameless plug, but I've been working on the following site for a little while:

https://options.fyi/

STILL A WORK IN PROGRESS

I wanted to hopefully arm people with some more knowledge about options before they started trading, and to try to protect them from themselves.

Thanks! Will probably end up fixing the links. We also have some dynamic sizing issues to clean up too. Just wanted to show everyone the project from a usable state!

Hello Everyone! My good friend Ali (user?id=AliChaudhary) and I built a Coronavirus visualization together. We ingest data from https://covid19api.com/ and built these visualizations in D3. This is meant as a simple visualization tool where one can click on any state or country in question to get more in depth statistics.

This website is best experienced on a desktop, where one can toggle between the following:

1 - Default - Active Covid-19 Cases per Million (https://covid19mapped.org/)

2 - Total Cases Worldwide (https://covid19mapped.org/total)

3 - Active US Cases per Million (https://covid19mapped.org/US)

4 - Total Cases in the US (https://covid19mapped.org/totalUS)

The most surprising takeaway visually was the US Cases per Million map. It painted a much bleaker picture than I expected for much of America, with just about every state looking far worse normalized the way we represented it.

The most surprising takeaway technically was how much trying to build alternative visualizations like density bubble maps or stick figure representations slowed and froze everything, along with the challenge of trying to find 9-10 colors that were colorblind friendly, more or less. Additionally, we got a surprising amount of traffic the first few days, with over 1000 hits the first 24 hours, with 0 advertisement or SEO optimization whatsoever, with Russian and Chinese hits at a surprising clip. It goes to show how much people are searching for Covid-19 related things.

I bought the URL BadSubscriptions.com because I came across the story of subscriptions/services that are hard to unsubscribe from over and over again. I haven't built anything that works yet, but what features/suggestions would you all have for a service that unsubscribes for you. How valuable is that to you?

I'm mocking up workflows with various API's right now but nothing is concrete so I'd love and welcome any and all suggestions.