The Creators of Model Context Protocol

**SPEAKER_1** (0:00)
Welcome back. MCP, MCP, MCP. After the NYC Summit, we wrote a popular piece explaining why we think the Model Context Protocol from Anthropic seems to have won the Agent Open Standard Wars of 2023 to 2025 It seems everyone is now jumping on the MCP bandwagon, from Cursor and Windsurf to OpenAI to Google DeepMind. Our AI engineer community is hungry for more, so we are doing two things to explore the MCP phenomenon. First, today's guests, Justin Sparr-Somers and David Soria-Parrer, are the co-creators of the Model Context Protocol, who were kind enough to do their first ever podcast with us, about the origin, challenges and future of MCP, and gamely indulged all the questions that we asked from the Latent Space community. Second, Swyx has announced that there will be a dedicated MCP track at the 2025 AI Engineer World's Fair, taking place June 3rd to 5th in San Francisco, where the MCP core team and major contributors and builders will be meeting. Join us and apply to speak or sponsor at AI.Engineer. Watch out and take care.

**Alessio** (1:17)
Hey everyone, welcome back to Latent Space. This is Alessio, partner and CTO at Decibel, and I'm joined by my co-host Swyx, founder of Small AI.

**Swyx** (1:25)
Hey, morning. And today we have a remote recording, I guess, with David and Justin from Anthropic over in London. Welcome. Hey.

**Justin** (1:35)
Good to be here. Welcome.

**Swyx** (1:37)
You guys have created a storm of hype because of MCP, and I'm really glad to have you on. Thanks for making the time. What is MCP? Let's start with a crisp definition from the horse's mouth, and then we'll go into the origin story. But let's start off right off the bat. What is MCP?

**Justin** (1:57)
Yeah, sure. So Model Context Protocol, or MCP for short, is basically something we've designed to help AI applications extend themselves or integrate with an ecosystem of plugins, basically. The terminology is a bit different. We use this client server terminology, and we can talk about why that is and where that came from. But at the end of the day, it really is that. It's like extending and enhancing the functionality of AI applications.

**Swyx** (2:19)
David, would you add anything?

**David** (2:21)
Yeah, I think that's a good description. I think there's a lot of different ways for how people are trying to explain it. But at the core, I think what Justin said is extending AI applications is really what this is about. And I think the interesting bit here that I want to highlight is, it's AI applications and not models themselves that this is focused on. That's a common misconception that we can talk about a bit later.

**Swyx** (2:45)
But, yeah.

**Justin** (2:46)
Another version that we've used and gotten to like is like, MCP is kind of like the USB-C port of AI applications, and that it's meant to be this universal connector to a whole ecosystem of things.

**Swyx** (2:58)
Yeah, specifically, an interesting feature is, like you said, the client and server, and it's all sort of two-way, right? Like in the same way that said, USB-C is two-way, which could be super interesting. Yeah, let's go into a little bit of the origin story. There's many people who have tried to make standards around agents, many people who try to build open source. I think there's an overall also, my sense is that Anthropic is going hard after developers in the way that other labs are not. And so I'm also curious if there was any external influence, or was it just you two guys just in a room somewhere riffing?

**David** (3:31)
It is actually mostly like us two guys in a room riffing. So this is not part of a big strategy.
You know, if you roll back time a little bit and go into like July 2024, I was like started at Anthropic like three months earlier, two months earlier. And I was mostly working on internal developer tooling, which is what I've been doing for like years and years before. And as part of that, I think there was an effort of like, how do I empower more like employees at Anthropic to use, you know, to integrate really deeply with the models we have, because we seem to like how good it is, how amazing it will become even in the future and of course, you know, just dog food your own model as much as you can. And as part of that, from my development tooling background, I quickly got frustrated by the idea that, you know, on one hand side I have Cloud Desktop, which is this amazing tool with artifacts, which I really enjoy it. But it was very limited to exactly that feature set. And it was, there was no way to extend it. And on the other hand side, I like work in IDEs, which could greatly like act on like the file system and a bunch of other things. But then they don't have artifacts or something like that. And so what I constantly did was just copying things back and forth between Cloud Desktop and the IDE. And that quickly got me honestly just very frustrated. And part of that frustration was in like, how do I go and fix this? What do we need? And back to like this development developer like focus that I have, I really thought about like, well I know how to build all these integrations, but what do I need to do to let these applications let me do this? And so it's very quickly that you see that this is clearly like an M times N problem. Like you have multiple like applications and multiple integrations you want to build. And like, what is better there to fix this than using a protocol? And at the same time, I was actually working on an LSP related thing internally that didn't go anywhere. But you put these things together in someone's brain and let them wait for like a few weeks. And out of that comes like the idea of like, let's build some protocol. And so, back to like this little room, like it was literally just me going to a room with Justin and go like, I think we should build something like this. This is a good idea. And Justin, lucky for me, just really took an interest in the idea and took it from there to like, to build something together with me. That's really the inception story. It's like, it's us to, from then on, just going and building it over the course of like, like a month and a half of like building the protocol, building the first integration. Like Justin did a lot of the, like, the heavy lifting of the first integrations in Cloud Desktop. I did a lot of the first proof of concept of how this can look like in an IDE. And if you, we could talk about like some of the tidbits you can find way before the inception of, like before the official release, if you were looking at the right repositories at the right time. But there you go. That's like some of the rough story.