News for hackers. Stuff that matters.

willcarkner

Re:Show HN: MCP for Ordering Assembled PCBs on Monday October 19, 2026 @03:28PM (#50156879)
This is something we are working on right now. The MCPs main focus is going to be integrating with design tools, especially the ones that agents are using. Would be very interested in collaborating on a marketplace. Your project seems cool and has similar intentions!
Re:Show HN: MCP for Ordering Assembled PCBs on Monday October 19, 2026 @02:00PM (#50155676)
Yes, has access to all the vendor APIs and makes subs if not in stock
Re:Show HN: MCP for Ordering Assembled PCBs on Monday October 19, 2026 @01:44PM (#50155450)
Hola HN, Will and Johnny from ProvenMetal (https://provenmetal.com) – we’re automating the circuit board supply chain.

Ordering an assembled circuit board is a seriously messed up process.

Roughly…

upload design chase down manufacturer for a quote manufacturer emails a bunch of technical questions you answer the technical questions they ask more technical questions you answer more technical questions then you realize that components that were available at the start of the process are no longer there, so you have to find and source substitute parts you consign them to the manufacturer and try to co-ordinate with them deal with shipping delays of the consigned parts, they say they won’t start until all components are there they start the build, come across some design issue, stop working until it’s resolved you resolve the issue they finish and send it to you and then it gets stuck in customs / a natural disaster happens to the delivery truck

We automated these steps for our own orders, collected data on every error, and built that into our own manufacturing co-ordination system.

I’m a big believer that this time next year, most new circuit board designs will be AI generated. Designs are useless if they can’t be manufactured well. So we’re connecting agents to manufactured electronics. Design agents should know what can actually be built, with what parts, by when.

A bit on how the sausage is made: Integrate with both domestic and overseas manufacturers, integrate with their quoting models, use APIs where available, and auto-select based on lead time, price, and capability. Use manufacturing capability data and historical design data, with heuristic based harnesses, to automate design review. The design agent takes this data to improve designs. Integrate with component vendors (big and small) to have complete supply chain coverage of every component based on availability, lead-time, and price. With big vendors, we use APIs. With small vendors, we use browser agents. Manufacturers have technical questions that add days to lead time. We use agents to automate email responses. With enough data, you can predict their questions, and give them answers to questions before they have them. Every order has a digital thread of every single action related to an order. Each order is constantly monitored to pick up on issues before they blow up lead times.

We’ve done $280k worth of orders in our first 3 months to develop this model.

Limitations: Rigid-flex & flex PCBs - quotes aren’t instant and need more engineering review. Complex fabrication processes – HDI and RF boards need more engineering review. Stuff will break. We launch fast, find issues, and fix them fast.

Install MCP: https://provenmetal.com/mcp

Normal ordering flow: https://central.provenmetal.com/order

We are very interested in your opinion. This is a very messy problem to solve. Try out the MCP for free. Let us know what breaks.

We can do this by continuing to give them work. They are currently happy with us routing jobs through them, and I expect this to continue. It means they don't have to go searching for customers.
1. Through partner fabs located mainly in the Bay Area but also across the US.

2,3,4. Some of our partner fabs can, publishing a detailed spec sheet asap

1) Well noted, we are working on fixing that 2) Agreed, fixed with 1) 3) We should be more clear about testing. We offer a range of tests (in house x-ray, functional, bring-up) that we should show more clearly. 4) This will be made more clear on the site 5) We don't aim to be a broker in the end. We aim to own the whole stack. This is how we start. 6) True, we do in-house testing and rework, which should be more clear on the site.
Everything in stock on US distributors, but we will make a tool for this too.
A PCB design tool that has manufacturing built in, for use by humans or agents.
That's exactly what we are trying to do.
True, there are a few standout cases of larger CMs. Tempo was the poster child and they did a lot of things right. MacroFab and CircuitHub will be great competitors to have, and as stated in earlier threads we believe our edge will come from owning the entire stack from design to testing.
Absolutely. Let's do it for everything
I would be super interested in chatting. Sending a DM.
Yes and no, I could imagine a system where they have on demand capacity with a company like us and pay for that service.
#1 price is more expensive than China, parts availability is higher.

#2 it is accessible, but more expensive so if cost is your main constraint it's not the right choice.

Yes we're going to build that into it. In the pipeline definitely.
You're right. I'm updating the website with capabilities now. The NDA simplification is also a good idea, we will implement that as well. Thanks!
Yes, a bunch of companies offer it but we aim to make it more available for a lower cost.
Yes that's where we're putting our energy right now. We do most of our assembly with CMs now, but looking at Juki when we open our facility.
Ok, fair points. 2. is our focus right now and then we may add 1. over time.
Youtube tutorials are pretty great to get started
Very interesting, I'm wondering if that low-utilization rate justifies the capex of building a line.
In this case specifically they also have a huge amount of automation and process learnings from being around for 20+ years.
Yes I agree. If it turns out that there is not enough demand to service in defense, we can use the optimizations found from the defense market to take a stab at the general market. It doesn't make sense to start with that off the bat.
Agreed completely. The recent bans are one way of doing this but not the most sustainable long term at all.

We have two options, give up and allow China to control all production, or start the hard battle to improve manufacturing here.

Updating that as we speak.
Wow. Sounds like a super interesting product. Hadn't considered lines of credit yet, but definitely would be valuable to some higher ticket customers.
Yes macrofab has a great service. We are best for quick turn, but long term we aim to cater for production as well. All in good time.
yes, what was the utilization like?
Yes, though it was only somewhat recently that they transitioned to building their own automated facility.

We don't plan to do the design ourselves, we realize that our users will be using AI design tools that need to be integrated with the factory. We will build that link.

Older »