← Latent Space: The AI Engineer Podcast
Latent Space: The AI Engineer Podcast
One Year of MCP — with David Soria Parra and AAIF leads from OpenAI, Goose, Linux Foundation
01:39:18
Loading summary
Transcript247 lines
- [00:00]
A
Foreign. Welcome to the Latent Space podcast. This is Alessio, founder of Kernel Labs and I'm joined by Squiggs, editor of Latent Space. Hey.
- [00:14]
B
And here we are joined finally in the studio for the first time. Welcome back David from Anthropic mcp.
- [00:20]
A
Yeah.
- [00:20]
C
Hey, well, nice to finally talk to you in person. Last time like a year ago it was over VC and this is way fun.
- [00:27]
B
I watched it back, it was eight months. It's been a crazy eight months. And I think we just celebrated like the one year anniversary of mcp.
- [00:35]
C
Yes.
- [00:35]
B
At least a public announcement. And also last night or yesterday was the Agentic AI launch.
- [00:42]
A
Yeah, that was nice. Was a nice event. It was nice to see the Anthropic office. And I'm in. You like it?
- [00:47]
B
Yeah, it's very good food. I would say in terms of my food bench, Anthropic does rank over OpenAI.
- [00:54]
D
Yeah.
- [00:56]
C
At least that's what we have going for us.
- [01:00]
A
Awesome, man. Do you want to give just a quick overview of what's happening with MCP and how you're donating it to the foundation? And then we'll do kind of like a one year recap of the protocol itself and then we'll have the rest of the leads from the foundation join us to do more of the high level.
- [01:14]
C
Yeah, yeah, that sounds good. Yeah. I mean where we at at the moment? We have done like a year, like a year ago we launched it and then we had this like crazy adoption over the last year now, which it felt like an eternity honestly. But we have this crazy growth and adoption initially through Thanksgiving and Christmas very early with a lot of builders building mcp. And then you had the first big clients coming in cursor and VS code. And then you had this inflection point around April with Sam Altman and Satya and Sundar and all posting about MTP and that they're going to adopt MTP at Microsoft, at Google, at OpenAI. And that was really like the big inflection point. So. Yeah, but in all of the time you also had to do a lot of work on the protocol itself. Right. We like, we moved. We launched originally as like basically local only you could like build local MCP servers for cloud desktop. But then we like in March this year we moved into like how can you do remote MCP servers? So connect like really about like to a remote server and introduced like the first iteration of authentication. And then in June we revisited that and improved it quite a little bit so that it works better for enterprises in Particularly and we were very, very lucky that in that time from March, June, we were able to have absolute industry leading experts that literally work on OAUTH itself to help us with some of the pieces and how to get it right. And then we focused a lot of on security best practices and this type of work and now we're, I feel we have a really solid foundation and we just launched in our end of November. Then the recent iteration of the protocol, finally the next bigger improvement to the protocol which is long running tasks to really allow for deep research type of task and maybe even agent to agent communication. And so I think we're just stepping into this territory now with like okay, we have really solid foundations, we have one more big primitive we want to add, we want to make a little bit more scalability things work and then we're you know gonna get into a phase where it probably becomes a bit more stable. And so yeah, it's been, it's been an absolute crazy year, man.
- [03:35]
A
You did say the agent to agent. So there is a 2A protocol. I'm curious, when the Agentec AI Engineering foundation got formed or just Agentech AI foundation, was there any discussion about any of these other protocols being a part of it or. You know, Sean wrote a post called ymcp1 already.
- [03:54]
E
So one of my favorite posts of.
- [03:56]
A
The year, maybe it was already.
- [03:58]
B
And it was before Sam and all the other guys.
- [04:00]
C
Yeah, yeah, you were right.
- [04:02]
B
Well, I mean I think it was just obvious that was going to happen.
- [04:05]
C
Yeah. So yeah, so we of course have conversations around like what is else is in the market, like there are payment protocols that are interesting and so on. But when we wanted to start a foundation we wanted to make sure first of all two things. We wanted to start small and make sure that the group that is founding this like for us it's the first time we had anthropic have an open source foundation. So this is all new to us. So we really want to start it small and making sure we're learning along the ways and being able to shepherd this in the way we feel is best for the industry together with OpenAI and Block. But the second part of that is also we really felt like we wanted to see things that have a lot of adoption or de facto like at least on the protocol side like a defactor standards. And I don't think any of the other protocols, it feels like they're not just there yet. But of course if they get there then we are like super open. As long as they're like complementary to what's in the foundation. On the application side, we're a little bit more flexible and we're more open. But on the protocol side, I think we really want to make sure that we're not offering the foundation doesn't encompass five protocols for the same communication there. And so, yeah, there was discussion, but I think for now we just want to start it small.
- [05:21]
B
Is there a role like a double hat that you have now with the foundation or are you more focused on mcp?
- [05:28]
C
I am still mostly focused on mcp. There's a bit of a double hat. So there is this, like, I think people need to understand, like the foundation part is mostly just an umbrella to make sure the projects under it stay always neutral. And I think that's really the most important part. You want to get a lot, you know, want to understand because the rest of it is like, okay, how do we use the budget of the foundation for events and things that are quite dry and then the technical parts to mcp, they stay actually the same. On the way we govern mcp, nothing has really changed. And so that's really still my job as the lead core maintainer of shepherding the processes, shepherding the protocol forward, and then beyond that, now the additional double rollers. I'm also going to be on the, the technical steering committee of the foundation, which will like, make sure to like figure out what are the projects we want to have in the foundation. So if someone comes with a project to us, the people that have projects in it will decide, is this something we would want? Is this something that we feel is like well maintained, has a lot of adoption, is not going to go away. We want to make sure the foundation is, have like super interesting and important projects and not like a dumping ground like have, you know, how some foundations might have ended up with.
- [06:42]
B
That's true. So we're going to meet some of the others later, but maybe we'll just focus back on the sort of MCP development. You covered a lot. There's been four spec releases.
- [06:51]
C
That's a lot.
- [06:52]
B
Yeah. Some people may have missed some of them is what I'm saying. Right. And I think it's really interesting how you've continued to work on really important parts. I always think it's very hard to follow up a major success with a sequel because the SQL usually it's hard to repeat that impact. But I think every single time you've actually managed to focus on something important. So maybe we can cover, I guess maybe we'll start with the march May one Which is HTTP streaming, which is good. And the auspec.
- [07:24]
C
Yeah.
- [07:24]
B
Any other. I don't know if you want to highlight any others, but we'll just catch people up on that stuff.
- [07:28]
C
Yeah, so I think that was really a. That was such an important one.
- [07:33]
B
It was the number one requested thing.
- [07:34]
C
Yeah, it was like, it really opened up this like remote thing. And we were, we already knew actually in December and November that the next big thing will be like, how can you do this over the over remote? And authentication is quite important. One of the things I think people very rarely notice when it comes to mcp. MCP is very, very prescriptive in like each layer. Like other protocols are not like that. For example, like we like you want to do authentication if the client and the server don't know each other, you need to do OAuth. Right. And so we were very early. We wanted to have like one way to do something. And so we really focused on like, what does this mean? Like, how do we get it over? How do we build a protocol that has this, like these streaming properties that we require and then how do we do authentication? Very early for authentication. In the first iteration, I think we did an okay job, but we got some aspects wrong. And most of them honestly were just me not understanding enterprises well enough. But then again, I think the strengths that we have with mcp and I think the one thing, if anything, I'm proud of is like building a community of people that can come together and help me figure shit out, because I have my set of experiences of what I'm good at. And enterprise authentication, it turns out, is not one of them. But they're way better suited people for that. And so that's when we, like after.
- [08:51]
B
That March, I saw you post that, but I didn't really dig into the details. Was it like the typical Samuel type authentication issue?
- [09:00]
C
The main issue we did is in OAuth there are two components. There is the authentication server who gives you the token, and then there's the resource server takes the token and gives you the resource in return. And in the first iteration of our authentication spec, we combine them together into the MCP server, which if you were building, unusable. Yeah, it's kind of usable. If you build like an MCP server, like as, like a, like a public server as a, you know, you're a startup, you're building a server for yourself. You want to bind this to the accounts you already have that is completely usable. The reality in enterprises is you don't authentic. You authenticate with Some central entity like, you know, you know, you have some ID identity provider, an IDP and you okta. Yeah, for most people, what they don't even notice that's happening. All they know is like, oh, in the morning I'm gonna go log in with Google 4 and then get access to all my work stuff. Right. But that's effectively the idp and if you combine these into the same server, you just can't do this anymore. And so all we needed to do is like, okay, we are a resource server. The MCP server is a resource server. How you get the token from the authentication server, we have opinions on how you should do it, but it's kind of separated. And that's what happened then in the joinspec where we separated this out and worked through a lot of these, like, okay, how do you do dynamic client registration? Other aspects, which also were part of the March spec. We can talk about that. That's a whole other story of like we were actually pushing the boundaries of what OAuth can do with MCP because we're trying something very unique with MCP. But yeah, that was the big part in March, which we like. And that was that authentication spec, the first iteration, then fixing it in June.
- [10:43]
A
Yeah, what's the state of agents authenticating on my behalf? Because even today with the OAuth, I still have to, you know, log into linear and whatnot.
- [10:52]
C
Wallet itself is for the most part a very human centric protocol. It just tells you how you obtain a token if you don't have a token. Once you have a token, actually it doesn't matter. You just put it into the bearer token. And so we are not very prescriptive of what like agent to agent authentication would look like on behalf of agents. They are ideas that we are looking into. And I don't have all the specifics, but we are not prescriptive in the same way we're prescriptive as with OAuth. But you can technically at the moment you have a token that might be like bound to like a workload identity or something like that, then you just can pass that still to the MCP server. We're just not telling you how to obtain it just yet. And so we're not prescriptive. And so people do this and they can do it, particularly when they're within like an enterprise and have a somewhat closed ecosystem. But if the client and the server don't know each other, we just don't have a good solution for now.
- [11:42]
E
Yep.
- [11:42]
A
And then yeah, on the remote thing you went from local servers like SSC and then streamable HTTP. Any learnings you want to call out there, any regrets or learnings for others?
- [11:53]
C
Man, transport, the one discussion has never stopped from the very beginning of the last years of our transport and we literally just spent the last two days at the Google offices with a bunch of like senior engineers From Google, Microsoft, AWS, Anthropic, OpenAI just like what do we need to do here to really, really make this solid? When we looked into Mark, we wanted to get a transport going that basically retains a lot of the properties we had from Standard I.O. because you really, and I still believe this until today, that MCP should also enable agents and agents are inherently somewhat stateful and there's some form of like long term communication going between like the client and the server. And so we always looked for something like that. We also knew that we looked into alternatives like, okay, what happens if we do websockets for example? And we have found a lot of issues with doing a proper bi directional stream. And we were like, okay, what is the right middle ground between having something that can be used in the simplest form that people do, like where they just want to provide a tool but then is able to be upgraded to like a full bidirectional stream if you need it? Because you really have complex agents communicating with each other. That's where streamashtp was born with that intent. And I think there's something that in retrospective we got right and something that we got wrong. I think we got right that we are really leaning just on standard HTTP in that regard. We got wrong that we made a lot of things optional for the clients to do. Like the client can connect and open this return stream from the server, but it doesn't have to. And the reality is no client does it because it's optional. And so a lot of the bidirectionality goes away. And so features like elicitations and sampling are just not available to servers because they don't have that stream open. Because the client implementer was like, ah, that's the minimal viable product for me, I don't have to do it. And so that became an issue. So I think there are lessons there. The second part of the lesson is that the way we designed the protocol, the transport protocol requires some form of holding state on the server side. And that is fine if you have one server, but the moment you scale this horizontally across multiple pods, like in containers or something like that, well now if you get like true call and then elicitation and an Elicitation result you somehow require to like, you might hit two different servers and you need to find a way to have these two servers somehow get this result together. And you effectively need some form of shared, like redis, memcache, whatever you want, like some form usually pops up or something like that to have like a shared state that you can like have. And that's kind of okay. And like we have seen this in PHP application and Python application being done, but it's not fun if you do this at scale. And we know from like some companies, like the Googles of the world, the Microsoft of the world, they're doing MCP at a scale that I can't tell you the numbers, but it's like in the million of requests. And so now it becomes a problem. Right. And so now we're sitting here like, okay, how do you build an iteration of the protocol that allows for basically these principles of like make it as simple as possible for simple MTP servers, but allow this full spectrum of like really bidirectional streaming if you need it, but also make it scalable. And I think we're just allowed to find the right solutions. But it's just. Is complicated. Yeah. Because a lot of the technology today is really just. There's very little like that. People either do the simple thing and then you do like something like Rest or you do like a full buy stream and then you're just gonna do like websockets or like GRPC and so on. And we need kind of both.
- [15:37]
B
What's it like to be in that kind of meeting where you have all these impressive companies and everyone is senior and everyone has an opinion.
- [15:45]
C
It's much fun to work with some of the best engineers in the industry. Like, it's insane.
- [15:50]
B
Okay, well who decides? You know, usually there's.
- [15:54]
C
We're trying to get to consensus. Like the reality is technically I decide in the end of the day, but I think that's more like a formalism in the end of the day what you're trying to do is just to really narrow down of like what's the, what are the real problems we all agree on, what are the things where we not necessarily agree on and what are the, you know, and then within those bounds, like build the best solution and it takes a while, it takes a lot of iterations. But it's so much, honestly it's so much fun because you get to see these unique problems from the companies. You see some of the identity of the companies in the problems themselves. Right. Like, you know, Google Has a different set of problems like Microsoft. And a lot of it comes from like just the ways of building things. And then the problem from Anthropic looked different from the problem from OpenAI. But what I love about all of this is that everybody is that like sometimes you step back and like you sit in a room with all these competitive companies, but you're actually building something together. And I love that. I've been in open source for like 25 years.
- [16:56]
B
Yeah, it's very.
- [16:56]
C
I love this kind of stuff.
- [16:58]
B
And when a standard works, this is the ideal.
- [17:00]
C
And these people are all amazing. I just learn from, from all my peers so much so I'm very grateful to be in the situation. Yeah.
- [17:06]
B
This reminds me of the IETF standards process. Is there some discussion about how this works as a private group versus something more traditional?
- [17:16]
C
It's an interesting one. It does look a little bit like the itf. The ITF is slightly different. The ITF is like an open forum where everybody can go. And the result of that, it's like the ITF is very consensus based and by accident, not necessarily because they want to be, but by accident quite slow in the processes, which is very good in many ways.
- [17:37]
B
It cannot be undone. Right. Once it's up.
- [17:39]
D
Yeah.
- [17:40]
C
And for example, when you look at the OAuth 2.1 spec, it's been in the works for three years or four years and they're just not done with it. Right. And that's the length of which ITF standardization works. These things can take a long, long time and I think that's good for certain pieces. But I think in AI at the moment is just so fast moving, you are somewhat forced to find a smaller group. And so that's why we run MCP as like a really traditional open source project with like a core maintainer group of like eight people that basically decide everything and then like input from everybody else. Like we get input and people can make suggestions and we have a lot of the changes don't come from the core maintainers, but they're the ones that decide it. And that's like way more. It's like a middle ground of being somewhat consensus based, but also somewhat like a bit of a dictatorship, which can be good if you want to move fast, which MCP wants to do at the moment.
- [18:31]
A
How do you balance the influence of like the model improvements with how to shape the protocol? Because obviously, you know, you have anthropic and OpenAI. You guys are doing post training on these models to make them better tool calling and you have preferences on the Shape of the protocol versus there's people that are not aware of like how you're structuring that. So yeah. Do you like share some of these, like, does the protocol influence some of the model post training or like vice versa? Maybe.
- [18:56]
C
I'm not 100% familiar. I'm a product person. I'm not fully familiar with everything we do on the research side for sure. But it influences the post training in the sense that we're making use of things like the MCP atlas that we're having in our model card of making sure that we're taking this large set of tools in the wild and make sure that our models work with that. And I think the primitives of the protocol, they're actually very rarely influenced by model improvements. I think there's a sense that we do anticipate the exponential that the models are on in terms of improvement and that we're relying to some degree of mechanics that you can put into the model training. I'm going to get more concrete here. So for example, people have had long conversations around context build of MCP servers. And that happens because MCP opens up the door to a lot of tools. And if you naively take all the tools or throw them into the context window, you just get a lot of bloat. It would be the equivalent if you take all the skills, take all the markdown files and just throw them all into the context, you would also have a lot of bloat. But we already knew, and I think we always knew that you can do something like progressive discovery. And that's like a general principle thing of like you can give the model some information, let the model then decide to and gain more information. Right. And of course here is where we're like, you know, some of the foresight that we see because we are at the big model companies, we know that we can train this if you wanted to. And what the training does is just optimizes it. The model can do it in principle already. Right. And any model can do it that does any type of tool calling. But if you train the model for it, it's just better at it. Right. And so these things then go hand in hand in a way. But in the end of the day, the general mechanic of progressive discovery or progressive discovery, that's just inherent to any type of model that can do any type of tool calling in the end of the day, if that makes sense.
- [20:56]
A
Yeah. And I think the context fraud point is important. And I think down there's the MCP versus code mode thing and then it's like, well, if anthropic says code mode and Anthropic made mcp, maybe is that the best way to.
- [21:08]
B
So the blog post never actually called it code mode. That's the qualfare term.
- [21:11]
C
That's it. But yeah, but like people call it, we call it pre chromatic MCP and other call it code mode. In the end of the day, what it boils down to is just like, okay, and here's the interesting part. So first of all, MCP is a protocol between the AI application and servers, right? So the model is actually technically not involved in mcp. And so now you have an application go like, I have a bunch of tools, what can I do with it? And you can do the naive thing and go like, okay, I have tools, I'll throw them into tools for the model and I call them. But you can be more creative with it. You can go and like, okay, Pauls are really good at writing code. What if I take this and treat it just like API calls and you give it to the model and now the model generates code and what you're effectively doing is this composability that the model would have done anyway by call tool A, get the result, go back to inference to call B and then combine it into call three. Now all you've done is you let the model optimize it in advance and put them into a bunch of code that is just executed in a sandbox and go like, call one, put it into two, put the results into three, get a result, and all you've done is an optimization in the end of the day. But the benefits of mcp, of having authentication done for you, having something that is suited for the LLM, something that is automatically, that is discoverable and self documenting, this thing has not gone away, that's still MCP for you. You're just using it a different way. So I'm always a little bit confused when people go like, but mcps. Why does it tell me that? Does it mean MCPS uses. No, it's still just a different use, right? And I think you will see evolutions as we're getting better of how we use these models and the infrastructure around it gets a bit more mature. You suddenly can assume that most model AI applications will have some form of sandboxing for execution. You can do a lot more fun stuff like that. But I don't think that the value of a protocol that connects the model to the outside world is gone because of it. That makes sense. I see it purely as an optimization, honestly, as a token optimization.
- [23:13]
B
Is this a good time to bring up skills?
- [23:16]
C
Always.
- [23:18]
B
So skills is a more recent concept. I only bring it up because it's mentally linked in my mind to progressive disclosure and to adding preset code scripts and all that. Skillz can also create skills, which is very fun. Well, I think a lot of people are trying to place MCP versus skills. Obviously they're not overlapping, but how do you view it?
- [23:42]
C
Yeah, I agree. I think that's the interesting part is like, they're not overlapping. I think they solve different things. I think skills are super great. And I think that the first that really they've been built from the principle is progressive discovery. But I think the mechanism of progressive discovery, that's just universal to any type of thing you can do with the model. But what skills do they give you? The domain knowledge for a specific set of tasks, like how you are, how you behave, how should the model behave as a data scientist or how should the model behave as an accountant or whatever. But MCP gives you the connectiveness of the actual actions that you can take with the outside world. And so I think they're somewhat orthogonal in terms of the skills really gives you this. Domain knowledge is kind of vertical. And then MCP gives you this horizontal of like, okay, give me that one action. And of course, skills can take actions. They can take actions because you can have code and scripts in there. And that's great. But it has two interesting aspects that I think people got. The first one is you need an execution environment. So you need to. You need to use a way to access your machine. Yeah, yes, and that's perfectly fine for, you know, if you like, run a local, like, you know, cloud code or something, then we can talk about, like clis, for example, in those scenarios where you have like an execution environment, these things make a lot of sense and then it's great. Or if you have a remote execution environment, then it makes a lot of sense, but you still don't get authentication in that regard. And so what I think MCP brings is the authentication piece. It brings the piece that you don't have to like an external person. Like, for example, if you have a linear MTP server, they can improve the server. You don't have to deal with that in your skill. Right. It's not fixed in space. And then the third part is that you don't necessarily need an execution environment because the execution environment is effectively somewhere else on the server. And so if you build a web application or like a mobile application, These things work better in some of these regards. So I think they are orthogonal in that regard for the most part. And I've seen some quite cool deployments where people use skills to explore of different functions different like the accountant, the engineer, the data scientist, and then use MCP servers to connect these skills to the actual data sources within the company. And I think that's actually a really fun model and I think that's the closest how I think about this.
- [26:07]
F
Yeah.
- [26:07]
B
So MCP is the connectivity layer. I think it's the word that you choose.
- [26:10]
C
The communication layer.
- [26:11]
B
Communication layer, yeah. So is it architecturally, I'm wondering if it's like the MCP client inside of each skill or is there a shared client that can discover skills?
- [26:25]
C
We do that as shared, we do that as a shared one. I think you technically want a bit more shared ones because you do. The more shared you have, the better, the more you can do like discovery things. You can do things like, okay, I have connection pooling, I can do automatic discovery of things. I can even like, you know, in a skill you might just very loosely describe what you want and I can look into the registry that I have access to and get an MCP server for you. Right. These things can you do, can do when you do. But I think both works at the end of the day. Yeah, but this is things to experiment with.
- [26:55]
B
I do want to highlight for people who might have missed it. You said we do blah, blah, blah. Actually, I think nobody understands enough how much anthropic dog foods mcp. And I only understood this when I watched John Welch do his talk at AIE where he was like, yeah, we have MCP gateway. Everything goes through this. And what can you say more about that?
- [27:17]
C
Yeah, I mean we use both, right? We use a lot of, we use a lot of skills internally. We use a lot of MCP servers internally because we have, you know, obviously, you know, you want to make it very easy for people to deploy mcp. You want to like have some form of like integration with uidps and so on. So we have a gateway that we built custom purpose for ourselves and you just got to like deploy your MCP servers.
- [27:37]
B
It is all internal apps, it's all internal stuff. Yeah, yeah.
- [27:40]
C
Some of them are like external things. Like, like technically external things. But in the lack of them offering a third party one, we have our own, like we have a Slack MCP server which I love to use that have Claude summarize my Slack for me. And so there's quite a lot of usage for that we even have an MCP server. We're doing a semi biannual survey, for example, around how we feel about the company, about the future, about AI, about safety, these type of things. And we have an MCP server for that. And I can ask Clark questions around the results, which is really fun.
- [28:12]
B
Is it your team maintaining it?
- [28:14]
C
No, we maintain a gateway. But I think one of the fun part is when we started mcp, it was always like MCP before we even open sourced it. It was born of the idea of like I'm in a company that is growing crazy. I'm in the development side of things, development tooling side of things. I will grow slower than the rest. How can I build something that they can all build for themselves? And that's really the origin story of mcp. And so it's fun to see a year later that's what's actually going on. It's like people build MCP server for themselves. I probably don't even know 90% of the MCP service that anthropic because, you know, they might be in research and I might not even see them or I just don't know because people build for themselves.
- [28:54]
B
But do they host it themselves? Is there a remote?
- [28:57]
C
They effectively have a command to launch it and it just launches in like a kubernetes cluster for them. So it's like partially managed.
- [29:06]
B
Yeah, that's good infra for anyone at a large company to build any platform infrastructure.
- [29:11]
C
And some there are platforms that offer that to you. For us, from security perspective, we want to build these ourselves. Yeah, but like they're like the person who built FastMCP, Jeremiah, like a company that offers like FastMCP Cloud, which is a little bit like that. You just like two commands and you have a running instance of an MCP server that talks stream over HTTP. And then a lot of enterprises use things like light LLM as a gateway. And then they can even do like just launch standard IO servers, attach them to the gateway, and the gateway does all the authentication, all the hard parts of MTP for them. And so there's a lot of ways to do this, but that's good infra you really want to have is just like make it trivial. Make it like one command to just launch an MCP server that was a standard I O server and suddenly it's a streamable HTTP server with authentication integrated. And you as an end developer only had to do the standard I O part.
- [30:01]
B
Yeah, I love calling that stuff out because people will take that and actually put this into Their companies. So yeah, otherwise also the alternative is chaos, reinventing everything. Shout out to Jeremiah. Actually I did invite him to do a workshop on FastMCP at my new York summit here recently.
- [30:21]
C
A very great blog post about a lot of the usage of MCP you're actually seeing is internally in companies. That's actually what we see at the moment too, which is really cool.
- [30:30]
B
In what companies?
- [30:31]
C
Internally in companies in big enterprises you see MCP everywhere and it's actually way growing way faster than you would think because it's mostly internal to companies and without people seeing it about discovery.
- [30:42]
A
So you launch a registry. Yeah, there were registry companies, there were gateway companies. The official registry now has other registries putting their own MCP in your official registry.
- [30:54]
C
We need more registries, man.
- [30:55]
A
I need just one more, bro.
- [30:58]
B
One more.
- [30:58]
C
Just.
- [30:59]
A
Yeah.
- [30:59]
C
What's the registry to rule them all?
- [31:01]
A
Any learning from that? Like launching a registry for like a new technology and like whether or not, you know, people like, you know, Smither is one example, right. If you go on the official registers, like all these Smither AI MCPs that you need to authenticate through them. So it's kind of like just a pass through registry in a way. How do you see, how is this going to shake out?
- [31:20]
C
I think we saw a lot of these like different registries come up and we really felt that there is a need for basically like an NPM PYPI kind of approach to this where like there's one more central entity that is the, where everybody can publish an MCP server to. And that's really where the original registry came from. And we really wanted to make sure that at least we're encouraging the ecosystem to have a common standard of what these registries can talk to. Because what we want to do, we want to live in a world where a model can auto select an MCP server from a registry, install it and then for the given task that you have at hand and then you just use it. Right. It should kind of feel magic, but for that you need like some form of standardized interface. And so we're going to do. And that was really the inflection point of like we started quite early working with the GitHub folks, even in April. And then I got distracted with other things like authentication and worked on that. And so what I want to see, and I think where we are slowly, but this is slowly heading is a world where we have the official registry where everybody can put their MCP server. But this is the equivalent to an NPM which has the exact same Problems of an npm, like everybody can put it there. There's basically, you don't know what to trust and what not to trust. You have supply chain attacks. These are just fundamental properties of public registries. I mean, that's why we have this concept of sub registries which then like the Smitheries and others hopefully can do, where they can filter and curate on top of it. And that's really the world we want to live in. I don't think we're quite there yet, but we're slowly getting there. Like the GitHub registry is curated off the, or speaks the same format as the official registry. And so what we want is like you as a company can have an internal registry that is a curated form of the official one, plus maybe you own ones. I mean, that's the one you trust and it speaks the same API than the official one. And if you have like a VS code or anything else that wants to talk to a registry, you just connect it to yours and you're good to go. And that's really what we want to do.
- [33:23]
A
It's interesting because npm, in a way, it's almost like a download gateway. You know, it's like I'm not really using NPM for discovery that often. I don't go to NPM and search for packages. It's kind of like I find them in other ways. And is this.
- [33:35]
E
You didn't.
- [33:35]
A
Yeah, yeah. I'm interested if you see like discovery as like a core piece of like the registry or like if you still assume that like there's going to be some other way that the agent discovers.
- [33:46]
C
I do think discovery is important in the, in the, in the model world, but I think that that's where it's different from npm because we are building like something for AI first and we can assume there's an intelligent model that knows what it wants. I think that's something that didn't exist before.
- [34:01]
B
Right.
- [34:02]
C
If you maybe, I don't know if you would build modern package management systems with models at heart, maybe you would do a similar approach of just like, here's what I want to build, just figure out, I don't care what packages you install, just do it. Right. I mean, that's the equivalent in the end of the day. But again, with the public registry, you should probably not do this because it's a dumping ground for everybody. You want to do it against a curated trusted registry.
- [34:28]
B
I like your phrasing that the model knows what it wants because I think there's a dream that Agents can use the MCP directories to discover new servers, install it for itself. That seems like very AGI if it works, but it may not work. And I wonder what needs to happen in order to do that.
- [34:47]
C
I do think we need a good registry interface on one hand and then the second part is just like we need to build for this and see how it works. And what does we need?
- [34:56]
B
Trust levels, maybe?
- [34:57]
C
You definitely need trust levels. You need trust levels. You might need some form of like. Yeah, you need trial snippets, you might need some form of signatures, for example. Like one of the ideas. I'm not sure if you're going to do it, it's just a random idea. But one of the ideas I always had is like you can attach signatures from different model providers that have scanned this MTP server and say, we trust this. Here's the signature from Anthropic that these tool descriptions are safe and here's the signature from OpenAI that these are trusted by us. And then you can decide, all right, so I think these distributed code signing it may be. And it's not just really distributed, it's just like central in a way. Right. But I think this is the kind of stuff you will require or. But I think in the simplest form what you can do where you probably see it first is in scenarios like internally to a company where you have inherent trust because they will use a private registry, they're effectively using private registries already for NPM, they're using for PyPi, and they will also do it for MCP servers in there you have implicit trust and then you can just search. Yeah, right. And I think that's really the interesting ground where we want to experiment and that's like we have our internal registry effectively because when you launch like via John's infrastructure, like an MCP server that gets registered. Right. And so we need to go in and experiment with that too.
- [36:16]
B
Okay. I actually wanted to also ask. You started running some events over in London. Yeah. You had the agents hackathon and you had Dev summit that you called on your timeline.
- [36:26]
C
Yeah.
- [36:26]
B
I just wanted to get anecdotal stories of stuff you learned as you saw the community spring to life.
- [36:33]
C
So we had two big summits this year. We had the MCP Dev Summit in San Francisco and the one in London too. Yeah, and the one in London. And I think what you learn is a few things. I think the one thing is that's very hard to get otherwise dislike these stories around how people use it internally in their companies. And there you see some of the struggles, but you see also some of the success stories. And one of the interesting bits which I really loved is particularly London. You had a lot of financial people there because it's clearly a financial hub. And it was actually the whole conference was in the financial district and learning just the kind of problems of things you need to enforce because you have legal contracts, because financial regulations. These were things that I did not know before and I learned a lot about. Like, okay, what does a thing like an MCP like communication layer need to look like? If you have these constraints that in a normal development world doesn't exist. Like I give you an example, like if you are in financial services and you're exposing some data, that data might be coming from a third party. And you must guarantee that you attribute that third party and that's a legal contract, right? You must, if the client displays this data to you, it must tell you this came from this third party. Right. And these are constraints that just like in the normal model world don't really exist. Right? But like in the financial industry this is like legally enforced. And so these are the things you're like, okay, how will this work in a world where fall for mcp? And so now that's when we started creating this financial services interest group that Bloomberg is heading up to figure out what are some of the things that a client must do if it wants to speak to a financial services MCP server, for example, and what are the things that need to be respected. And I think that's the kind of things you only learn on the ground in the conference is talking to people. So I think there was some of these learnings there. I think the other things that you just see is just how many people are building and just the excitement and the creativity that some people bring to this that I just love. Right. And from areas you didn't expect, right? Like I loved the guys at Turkish Airlines. I just built like the Turkish Airlines MCP servers. You can search for flights and stuff like that. So that was always fun. I love when people bring some really creative parts to the Ms. P ecosystem. So I love these community when they come together because you're just meeting things that are a little bit outside of your bubble and you just get some input. And I think there's a lot of learning there and some we're going to repeat it again. We're going to do New York in April, I think, or March or something like that. And then we're going to do it again six months later. And I absolutely love that.
- [39:18]
B
Any good sampling use cases that you.
- [39:20]
C
Found, not so much.
- [39:23]
B
And that's always the like, you know, last time we talked about this.
- [39:27]
C
Sampling a little bit, man, like we. I think one thing I learned from sampling, like everyone wants to use tools with sampling in tools that are not exposed via the MCP server. Like when you want to do something, you want to have a set of new tools that you only want to use during that sample call. And we just had no ability to do it and we just fixed this in this iteration. And so we hope to see a little bit more. Bit more sampling use cases. You will find every now and then an MCP server that does it. But particularly as MCP servers have moved away from more local to be more remote. In remote cases, it's probably always better for you to bring an SDK because you have full control. You can deploy it, you can deploy API keys and maybe even charge someone. In a local case where something is really powerful because you're shipping something to a lot of people and you don't know what is the model that they've configured, what is the application they plug it in. Might be vscope, might be cloud desktop. Right. And in those cases sampling is useful, but also like clients just don't support it. So sampling is one of these things. I'm like, I'm still sad about it. I still think it's a very powerful idea. But you know, you got to win some, you got to lose some, you know.
- [40:30]
B
No, no, no. You're also upgrading it and you know.
- [40:36]
C
My hopes are still up there. I'm spike.
- [40:37]
B
Yeah, yeah. Like my. In some ways, you know, when you get it right, this will be the real agent to agent protocol.
- [40:44]
C
Yes, yes.
- [40:45]
A
Are most of the use cases that you see still data consumption? That's been my use case for MCP mostly. It's like.
- [40:51]
B
Yeah, it's context engineering.
- [40:52]
A
If getting data well, the. The most action my NCP takes is like update the linear task status. Have you seen very complex like MCP taking action workflows or are still people mostly using it for.
- [41:05]
C
Most people use it for context. I think that's the vast majority of usage.
- [41:08]
A
It is in the name model context.
- [41:10]
C
Yeah. Yeah. And Nick Cooper from OpenAI always keeps telling me, rightfully so, that the name MCP was probably a little bit poorly chosen because it feels it restricts it a little bit, which I agree with. It's mostly data use cases. I've seen people doing deep research via it. I think people expose agents via it and so they are a little bit more complex but it's not super common. But people have experimented with it. The deep research use case I think is a good one. That is very, very, that's not too uncommon where people do custom research comfort. But beyond that, most of it is really data, beyond data and deep research aspects. Now you have also this new aspect where people expose like UI components or MCP UI or what we're going to call MCP apps in the future. And I think that's super, super promising and I think that's really quite fun. That's actually you see a lot now with ChatGPT apps, with MTPY in general that you see a lot.
- [42:14]
A
Yeah. And you have the tasks in the last task. Yeah, well, I mean I'm curious because like if most use cases are like context and then you build tasks, it's almost like people are not really using it for tasks. So I'm curious like how you design it, like what you expect people to use.
- [42:28]
C
We design tasks because people come to us and go like, okay, we really want long running operation which is basically agents. We want like a long, deep, deep research task that finishes in an hour. Or we want tasks that like might not finish within a day. Right. And people have like awkwardly tried to do this with our tools and you can, because tools are effectively just an RPC interface at the end of the day. But it gets very quickly awkward because now the model needs to understand, oh, I need to pull this. And it's just not very fun. It's just not a first class primitive and you run into a lot of limitations. But it's come from the fact that people want to have a long running agent and that's something we heard from so many areas and people trying to do this that we really felt we needed to do something that tasks on GitHub issues from big companies, everybody was like, we need something that long running operations is really top of mind. So I really think now we're going to see a lot of it now, but it's a little bit early to see how good it's going to go because it just landed in the SDKs and it needs to land in the clients and then we're going to see more of it. But I think you will see a lot of the custom research parts and others.
- [43:39]
B
Yeah, I'm very bullish on tasks. I think it was very important to get right. Basically every orchestration or protocol has a sync version and an async version.
- [43:47]
C
Yeah, exactly.
- [43:48]
B
Has an async version. Any design choices that you want to call out that there were two directions and you picked one in just the overall design of tasks.
- [43:58]
C
Yeah, in design there was a lot of conversations, like some were like, okay, is this just asynchronous tools? Do we do a different primitives? In the end of the day, it was important for me. My littlemus test for it was always it needs to be able to like, if I want to expose something like Claude code or like any other like coding agent as an MCP server, hypothetically, this needs to work and a pure asynchronous tool call would just not do this. You want some form of operation that can return, for example, intermediate results in the long term. You want like, okay, I got to this result by calling this tool this tool. This tool. I had this other input, I had this other tool, I did this and now this is the result. Right. That's really what you want to expose. Task is early and it doesn't do that just yet, but it's built in a way that it will be generic enough to be able to support this. That was the main constraint. The other constraint was making sure. It's not a copy of tools where you can think about like, okay, we just do tools again have slightly different semantics, but instead what it's doing is just like you can create a task by calling a tool with a certain set of metadata fields and then it automatically creates a task. So the task itself is just the concept of a container that can something asynchronously. Yeah, like just like you do something asynchronously from starting here and to ending here. And the thing we're doing is a tool call. I mean that opens the door to like later plug in other things and maybe even other tasks like observability as well. Yeah, potentially.
- [45:35]
B
Which is obviously going to be.
- [45:37]
C
So I think that was really the design goal, which makes it a little bit more abstract, a little bit more complicated to implement. But that goes away because the SDKs just do it for you and the SDK and over there you're just going to like async call this. Yeah, and you could charge something.
- [45:49]
B
I mean, there you start to overlap with other async like TRPC in JavaScript land or you know, whatever Go protobuf stuff that go. People have.
- [46:01]
C
In the end of the day, it's like it's designed like a classic RPC operating system interface. Like you create a task, you pull it until it's done and then you can make an optimization which we're going to do in the next Round, which we didn't get around is like, okay, instead of having to poll every minute or hour or whatever interval you choose, the server can service, call us events, call you like a webhook or something and go like, I'm done. Right. That's the optimization. But the actual core interface is always that the client can pull. And that's actually how like operating file system operations and an operating system can work is like you pull it, has the file changed, has the file changed. But you can also use like a modern interface on the kernel like Inotify or something like that, or uring or something like that. That tells you, oh, I'm done. Great. Yeah, the file has changed.
- [46:51]
B
There's a trick I learned where like servers can hold the HTTP connection until it's done and then they terminate. And that's the signal to the call back.
- [46:59]
A
Yeah.
- [46:59]
C
Which we do not necessarily want to do because it might take a few days and I don't know how people.
- [47:03]
B
It's very irresponsible, but it's cool.
- [47:05]
C
Yeah, yeah, yeah, yeah. There are plenty of ways. I think we were just going to go the webhook way. Honestly.
- [47:09]
B
Tasks are really interesting and we basically have to invent this. When we did this at did like the Devon API at Cognition. And I think that's also an interesting reinvention of like, well, everyone is going to need some kind of long running operation. Well, when you're calling an agent, you also need this.
- [47:29]
C
Yeah. But the interesting part for us, I think what MCP is always trying to do, MCP always tries to encapsulate what currently people trying to do. And we not want to be prescriptive what you're supposed to do in a year from now. We don't predict we did tasks because people are like, we need this now. Right. We needed this basically six months ago. And we're like, okay, I guess now it's time to do this. Right. Instead of trying to do being predictive of the future. Which is why we're trying to keep the protocol somewhat minimal and have I think to some degree achieve this. Although other people would think already there's too many primitives in the protocol, one minute thing.
- [48:03]
B
And so let's say super long running tasks. Lots of messages go back and forth. Anthropic actually was a kind of leader in context compression and compaction maybe let's just call it. And I think a lot of the other labs are also doing the same thing. Is there a way to handle that or do we just statelessly sort of cut Context and it's fine. Do you need a full log of everything that happens or.
- [48:27]
C
No, you just gotta stuff out.
- [48:28]
B
Yeah, right.
- [48:28]
C
No, no you don't. I think there's. This is the thing. We're very early in the industry still. We're learning a lot about what does the model need, what does not need. And even today some agents start to drop tool call results after a few rounds because they don't need it anymore. And I think that's very good. I think besides compaction, you will see just better mechanics of understanding what you need and what you don't need for a long asynchronous test. You might have a way where, okay, maybe for a while the model sees it, but once you get the result, you just drop everything else. Or you might even call a small model like a haiku model and go like what? All this I should retain? Tell me. You might be like the agipult approach where we just let the model figure out what it needs to retain. And so you can see both worlds in them. And I think there's just lots to learn. I think there's not the one answer yet because I think we're still figuring these type of things out and we're just improving. And compaction is a good step for it, but I don't think it's the last step there either. It is actually the most obvious one, but I don't think it's like. I think if you pay more attention to it, if you particularly think about like, okay, what could you train a model to do here? I think we get to much better ways of doing that, but they're all like, independent from how you obtain the context. And I think MCP I always see is like, back to like. It's an application layer protocol. That's just how you obtain the context, how you select the context. That's the problem for the application and that's the problem all the agent applications will have in the end of the day. And there will be a lot of different techniques. A year ago everybody would have told you it's rag style stuff, but now apparently dead right? And now we do use models and we use compaction. So I don't know what's going to happen in a year from now.
- [50:11]
A
Cool around mcps, another question I had is like, how do you see them as being used by developers to build AI apps versus being a protocol for AI consumers to plug things in? I think that's one of the main things people get wrong where it's like, well, I can just Use a REST API. Why do I need mcp? And to me it's almost like it's not really for the developers to use, it's for like people using AI tools to just plug things in.
- [50:35]
C
I get the comparison with the REST APIs quite a lot and I think there's interest. It's funny enough because there's two problems in general. Like the first one is REST does not tell you what to do on authentication. The second part is everybody complains to me about like tool bloat. Have you looked at like the average open API spec length? If you put that into a model, you will have a lot of bloat there too. Actually way worse. And funny enough, when people try to map one to one things, often the model gets slightly confused because you have search by name, search by id, search by something and suddenly you have five tools that look very similar to each other and the model goes which one do you want? I have no clue anymore. So anyway, that side note to REST versus mcp, but I do think MCP I want to live in a world where it's like very much like a consumer focused thing, but something consumers shouldn't know about for them. What I want is I want a world where you go to your application, you say do this and it should just do the thing and it should just connect to the right services. That MCP is under the hood is a detail or that the developer needed to know about because that's the communication channel that they're talking about. But in the end of the day you just get the tasks done right. And I, and I actually prefer a world where nobody of like my mom should not know what MCP is right if she wants to use cloud at the end of the day. But I do think it's very focused on that pluggability of like an external like service and in that regard more like on the consumer focused side. And there's still use cases for developers in general like first of all as builders but also like I still love my playwright MCP serverman.
- [52:13]
A
Well I doubt Chrome Developer Tool, the new Chrome one is like the new, the new meta.
- [52:18]
C
I also understand like for developers, right? Like that run like cloud code locally, you know, like things like Elis can be better approached, right to some degree. And that's okay.
- [52:27]
A
I'm curious about the MCP apps UI with what you're talking about where it's like every client like ChatGPT has their own right? So it's like if I'm used to the MCP app of this product. But then if I go in ChatGPT, there's like a different version that they curated. It's kind of like a different experience. So I'm curious how you feel about that, especially now that you have OpenAI in the foundation, right. Do you feel like all of this will be MCP backed in the same structure?
- [52:54]
C
There's two influences, right? Like MCP UI existed as a project which had a lot of really good ideas. OpenAI took some of them and really improved upon them. And now one thing we just announced three weeks ago on the MCP blog is that we're actually working with all, all two of them together to build like a common standard. And so we're really hoping that we're getting back to the world where you build for one platform, but you can use it across all of them. You build for great ones, run everywhere for ChatGPT, and you might be able to use it in Claude or in the Goose or whatever it might be that the program of your choice that implements this. But I think the general promise, what we have is I think that there are certain problems like if you, if you think about a modern AI application, everything is very text based and that's okay, it's nice. But there's things that as a human you're just way better suited to do in visual, right? The most basic example is like you want to like book a flight seat selection, right? Like you now get select, like you want to do seat selection in text. It's like here's like the 25 seats you have available. Like nobody fucking wants to do that, right? Like I have no clue where these seats are.
- [54:02]
A
Even as you based drawing.
- [54:04]
C
Yeah. And of course an application that you can select with. Or it might be like a theater that you want to book for or something like that. It's so obvious that you do want to have some form of like an application and a user interface that the model can navigate and that the model can interact with, but you as a human can also interact with at the same time. And I think that's what we're looking for. And so I think it's just this next iteration of like building richer interfaces because the pure text interface is just somewhat limited and there's very natural things. And you like, you see this in music production, you will see it of course, or you will have like certain brands that will deeply care about presenting their interface. Shopping is a good example, man. Like, like shopping has like 20 years of like a B testing what's the best way to sell you Something. Right. And so, and, and shopping interfaces are super complicated actually. And you just want a way for, for displaying that to the user so that it's familiar to them and that they. They can interact with it. And that's what MCP apps is in the end of the day. Yeah.
- [55:01]
B
And technical direction wise is the iframe the way they were.
- [55:05]
C
Yeah, it's an iframe. It's, it's. You are serving basically raw HTML over. Over an MCP resource. It goes into an iframe and then it talks to the outside rear. Post messages over a specific interface. And so what you can do now you can. Because it's raw HTML and you're not really like loading some external content. You're going to get. You can analyze it in advance if you wanted to with security. And because you have an iframe, you can like the external application can just speak like a very clear bounded or like security bounded. Yeah.
- [55:37]
B
And this has been in browsers forever. I think I'm scared of it only because I hate CORS issues. And iframes always have CORS issues.
- [55:46]
C
Yeah. But this again, this does not load anything external. It should not. Right. There probably are restrictions that we then iterate and iterate and then in five years maybe it has 25 course headers and whatnot. Whatever. Right. Um, but I think at we were starting small again with like pure raw HTML you should probably not have external references so you don't run into these issues. But you're right.
- [56:08]
B
And can I inherit styles? No, because iframe.
- [56:13]
C
Yeah, I think you need to put it in line.
- [56:15]
B
Yeah. Obviously like you will want it and I feel like this is really minor, but UI people care about this, which is you have. It should look like ChatGPT.
- [56:24]
C
Yeah.
- [56:25]
A
Yeah.
- [56:25]
B
Inside of ChatGPT should look like cloud and insist like cloud.
- [56:27]
C
I think that's a very good question. I'm 100% agree with you. Like brands and others who are deeply, deeply care about designers. Oh, 100%. And that's something we need to figure out. And that's where you need to get it out of the door and see how people use it and then iterate on it.
- [56:41]
B
That's why I don't think it should be an iframe long term. I don't know what the solution is, but we need new iframe that lets some permeability because of this stuff.
- [56:51]
C
I think that's sensible. Yes. Well, I don't know. But, but the other solution to the problem is the AGI build approach of. I just Give it a tool that says, give me a style sheet and the model can call you and tell you what you're supposed to look like.
- [57:04]
B
Okay. Should an MCP app know what it's being used, what the parent application is? You know what I mean?
- [57:12]
C
It might be like the application also exposes tools. Right. That the model is free to call it.
- [57:17]
B
Right, right, right. Okay, so maybe standard as an interface for people to pass down styles.
- [57:20]
C
Maybe.
- [57:21]
B
Yeah, maybe.
- [57:21]
C
I don't know. But it's a very good question. Let me ask the team. I'm just like, I'm mostly directionally there. I'm like, not in the width of doing everything there.
- [57:29]
B
Yeah, it seems like a little bit of a surprise to me. I never really paid any attention to MCP ui and then suddenly you guys all adopted it and I was like, okay, well, I guess this is a part of MCP now. And it went from a purely backend concern to now front end.
- [57:44]
C
It's also like notable as technically an extension to mcp. Like it's not MCP mcp, that's a pure technicality because it's a governance thing, right? Yeah, it's mostly like if you are a client that can render HTML, then you might want to consider implementing it, but you're still an MCP client if you don't. And the reality is your average CLI agent can't do it. Right. So they will never do it. And so I think that's fine.
- [58:10]
B
Are there any other extensions that are similar?
- [58:12]
C
We kind of look into financial services as an extension. Okay. You might end up in a world where in a year from now there might be clients that have like certifications that they are on Ampliq and get like a signature that they are like financial services MCP clients and they can prove it for the server. And only then the server allows connections because it knows they are respecting attributions. These daily contracts that you put into place and you will see this everywhere. If you want to deal in the long run with a public service and public clients that do, like deal with HIPAA data, like healthcare data, you will have to have guarantees. Isn't it part of just us or not necessarily. Like, I give you an example. Like, if I have, the client might need to have five servers installed and if there's one healthcare server, that healthcare server might tell you, you are not allowed in this session to use any of the other MCP servers because this data I'm giving you cannot leave you. Right. You must guarantee that this data doesn't go anywhere. Else because it's HIPAA data, because it's financial data, whatever it might be. This is a good example and that might be some of the enforcements you need to do because you just like, yeah, you don't want to have your, or your Social Security number or your healthcare data show up and then you're backside and. Right, yeah, awesome.
- [59:29]
A
We're gonna transition and have the rest of the AAIF group join. But any final call to action, like either people that should join your team, people that should contribute to the MCP spec or anything else, I think the.
- [59:45]
C
Most important part is still building with MCP on a day to day basis for people to just go out, build really good MCP servers. I think we see a lot of mediocre MCP servers, I mean some very, very good ones and just building good MCP servers, looking at how to use them, I think that's super important. The second aspect to that is like we're fully open community and we're running it as a traditional open source project that is based purely on what people are able to put in terms of effort and time. And so just like being an active partner, either giving us feedback, being in the discord channel, talking with us, giving us ideas, while also just helping us, implementing like the types of SDKs, the Python SDKs. You're always looking for new SDKs, right? Like we have active go SDK development, but like we don't have a Haskell SDK. I don't know if you're a Haskell developer, maybe you want to write, right? Yeah, there you go. And so I think there's a bunch of stuff you can do and be part of it. And I think I don't understand how much you can just be part of the community, but also just go and build. And I think there's so much opportunity now, particularly to build amazing clients. Now that we have understood progressive discovery better, now that we have understood code mode better, there's just this next iteration of clients to build and the next iteration of servers to build that I'm just to going, looking forward for people to do.
- [60:59]
B
Yeah, my last question or call out is I wanted people to hear directly from you. I sense the energy. I'm very excited by everything that you're doing. But a lot of people are anxious about MCP joining the Linux Foundation. They're like, oh, is this anthropic taking his eye off the ball. Can you address those concerns?
- [61:18]
C
Yeah, I love that you asked me that. I can totally see why people think that. But it's Actually quite the opposite. The commitment of Anthropic is the same, right? I'm still, we still have the same people helping with the SDKs. We're still super committed in our products to MCP. I'm still the lead core maintainer. Nothing has actually changed. What really is the main part of the foundation is two things. The number one is making sure that the whole industry knows that this will stay forever open, that this cannot be taken away. And there have been. Anthropic would never do this, I think. But there have been histories of companies going, taking an open source project and suddenly making it proprietary again. We have protocols that are proprietary. Look at hdmi. Look at like, what's the problems of HDMI and Linux?
- [62:03]
B
What's wrong with HDMI?
- [62:05]
C
HDMI 2.1. HDMI forum does not want to allow the AMD to develop open source Linux drivers for HDMI 2.1. Really? There's some. Look it up. Wow. So, you know, there's people. I keep a very close tap on it and what this does is like, no, this is now owned by a neutral entity. It will always stay open. You can use the word mcp. Nobody's going to sue you over it. So there's a bunch of that. Just giving the ecosystem and the industry that confidence that this stays neutral. I think that's important. The second part to that is that I think one thing, if anything I'm the most proud of is that I think we have set the tone for open standards in the industry and being able to now use that momentum to build like community in a space where people can come and bring really well done, well supported, well maintained projects and have them part of this foundation. I think that's the other part to that. But the funny part is like our bar for the foundation is gonna be like, it needs to be really well maintained. It's not like you're taking the ball off. It's actually exactly that what we don't want. And so we will not do that. For us, MCP is still core to the product and still super important philanthropic. And so we're still just as much as committed as we've ever been.
- [63:28]
B
Amazing.
- [63:29]
A
Awesome. Thanks for joining, David.
- [63:31]
B
And we're here in the studio with core team members of aaf. It's the biggest panel we've ever had on the podcast. So welcome guys. Maybe we'll go left to right and introduce everyone and also identify the voices for people listening on audio.
- [63:44]
D
I'll start. I'm Jim zelmelin. I'm the CEO of the Linux Foundation. I've been working there 22 years and I was the person who helped facilitate the launch of the foundation. But take no credit for any of the technology work that that's to my, my left.
- [64:01]
F
I'm Nick Cooper from OpenAI. I've been there just over two years now. I think I'm generally OpenAI's like head of a lot of protocol things and very interested in the open ecosystem and our representative for AAIF as well as a core contributor to ncp.
- [64:17]
B
Got it. What's another protocol that might fall under that umbrella?
- [64:20]
F
Agents nd just in general, like not just the protocols but also the product experiences of where OpenAI products intersect with other SaaS, provider things and other systems.
- [64:31]
C
I'm David Soriapara, I am working at Anthropic, member of technical staff there. I'm the co creator of mcp. And yeah, at Anthropic I mostly lead all the MCP efforts. Great.
- [64:44]
E
And I'm Brad, I'm the principal engineer at Block. So by day I build AI products and by night I work on open source like Goose and the original author of Goose.
- [64:53]
A
It's great to see everybody come together. I think when I heard about the news I didn't really expect it. It wasn't on my bingo car. So maybe let's have a little bit of inside baseball. So you obviously have open Anthropic and yesterday at the launch event you were joking on how you didn't know that the two companies even talked to each other and then. Yeah. How did the conversation start?
- [65:13]
C
The conversation started out of two things. The first one is that on the MCP side we always knew that we wanted to find a neutral home for MCP to make sure that the industry understands that this stays open, that this is something safe to adopt. And then very early in the process as we were looking around like what to do about this, should this be a project in a foundation, should this be inside its own foundation which is like these common patterns you see for this kind of work. And we got approached by our friends at Block to discuss because they were looking into donating Goose, I think at the time. And so there was a question around doing something together. Then we approached OpenAI and they were very, very welcoming and very open to the idea as well. And it's slowly formed and I think the timeframe of this is like a few months. These things are not happening out of thin air in a week or so. And so just a lot of conversation like what do we want to do? What are the kind of constraints we want to have and what is the thing we want to build. And of course we were looking for where to put this kind of stuff. And that's where the Linux foundation comes in as I think the biggest foundation of its kind and certainly has like, like decades of experience helping companies through a process like this. I'm building what is a tech is technically called a directed fund within the Linux foundation to build these kind of things out.
- [66:42]
F
I think David said basically all the story from my side as well, which is so we saw this need to connect systems and then MCP gained such very large developer traction and we at OpenAI we were very excited to use and then contributed and actively participate in this. And from my point of view it was always very natural that this would grow into something bigger and move to a neutral place. And MCP has always been a foundation for communication between agents and context. In a similar way, the Agentic foundation is, well, it's a foundation, but also it's like the starting point where I really look forward to other contributions like starting with Goose, our own agents MD where we're really open for a lot of technical contributions to build out a really full agentic ecosystem.
- [67:30]
A
I'm curious Jim. You know, I've been to Linux foundation events before, I spoken to them. It's almost like is an MCP so early that like how do you even structure it in a way? I'm curious because so many of the technologies that the foundation supports are kind of like core pillars of infrastructure and the Internet. This is probably like the youngest technology that you brought in as a foundation. What are the goals of it?
- [67:51]
D
Yeah, I mean, I think what's interesting here is even though it's young, I think if you, I think AI years are kind of like dog years.
- [68:03]
B
Absolutely.
- [68:04]
A
Do you use this metaphor?
- [68:06]
B
But yeah, totally. This is why I run three conferences a year.
- [68:08]
D
Yeah, exactly.
- [68:09]
B
You can't do annual.
- [68:10]
D
I think last night someone was asking what do you, what do you see a year from now? And I'm like, well, if I dial the clock back a year would have I anticipated where we're at right now?
- [68:20]
C
There's no way.
- [68:21]
D
And so I think part of the thing with MCP is that we're just living in this kind of dog years velocity. In the past, I think things took a lot more time to coalesce. And what is clear is that a lot of people are adopting mcp. You see it in commercial products that companies are rolling out. You see a lot of usage in the enterprise already and there still is a ways to go in terms of the technology becoming mature. But I think the, the same thing held in Internet protocols, you know, that took a little bit longer to mature and the Internet matured over time. But I think the thing I'm most excited about, it's becoming clear that MCP will be a key protocol for this technology movement. And I think, you know, David and these folks were all pretty wise to realize that, you know, if Internet protocols had been owned by a single entity, he'd still be calling it American Online. America Online. It like, you know, it would be, it wouldn't work. And I think that this has got all of the underpinnings to be a huge movement. At the Linux foundation we ask three questions for every project. Will this be meaningful and impactful for industry and society? The second question is, do you need more than one organization to collaborate to do it? Otherwise you don't need us. This case clearly we've got that. And three, can we get the resources and build an ecosystem around it? And 50 companies on day one, you know, a huge set of folks in line to participate and join my L inbox.
- [69:57]
B
I'm sure your guys are too like.
- [70:00]
D
Full in 24 hours. How do I participate? We want to contribute. How do I get in there? I've never seen that kind of inbound interest starting any project at the Linux foundation in 22 years.
- [70:13]
A
How do you pick? You got all these people reaching out. You know, there's good and bad.
- [70:18]
F
It's a really good question, I think, like how to pick how we expand the foundation itself from like a governance standpoint, but also like technical contributions and how can the foundation best support them as well. That's like really top of my mind. It's like the first thing we need to like define some structure and work out what we like, how to bring it all together. But I think even before like those details, there's such value in establishing this one forum that people can come to like even having a list of eager technical participants and potential opportunities. That's a huge opportunity in front of us to like distill what's truly meaningful to developers, users and everyone and very appreciate Balloons foundation for acting as like sort of a galvanizing rod for this like attention.
- [71:04]
B
Brad, on the sort of block and Goose side, it's an interesting, the involvement that you guys have had and the sort of engagement that you guys have had. What was your calculus in joining the aif?
- [71:15]
E
So for us, I think it's like in developing something like Goose, I think the thing that I see it as being part of this umbrella is it's the most concrete piece. So you can actually download Goose and.
- [71:29]
A
Use it in a way that you.
- [71:30]
B
Can download an hsmd.
- [71:34]
E
Like what, what do those parts do together without having something that actually like connected to client CI, like a real client. And there's I think a lot of value in that because when you, you get into the protocol space, you want to add things to it, but you have to actually show like, what is enabling, like why are you making the protocol wider and putting it into like a reference implementation? Shows you like, oh, it's giving this value to people, like very concretely. And I think there's some like, for example, there's like a, a spec for MCP MCP apps that is brand new and we've been working on MCP UI for Goose. Yeah, so, so Goose has been like kind of a day one partner with the MCP UI team.
- [72:12]
C
Oh, I didn't know that.
- [72:13]
E
And so now we've got MCP apps. We'll go, we, we have opened an issue today about how we're going to go get that into Goose. And so that's something where I'm people, I think you hear something abstract like that, like what is send, what is the server sending an iframe to the client, like do. And I think Goozoo is a place where you can see it like, okay, you're going to build a dashboard or you're going to have this enhanced chat experience. And so this is something where I think we collaborate more and more to say, like, this is what it looks like and how you look at some of these abstract things and make them real.
- [72:42]
C
I think the other tidbit here, maybe like back to the history of both MCP and Goose, is like Goose was the first open source agent interface or agent that reached out to us and worked with us to integrate mcp. And I think Brad is actually technically the first non anthropic contributor to MCP ever on day two or something like that. Very, very early. So this goes all the way back to November last year to the partnership of having MCP inside Goose.
- [73:12]
E
Yeah, we had a version of Goose that was still. You can go check the GitHub history. It was there a little bit before MCP came out and we were sitting there with a plugin ecosystem system who were like, this is awful. Why would anyone, yeah, why would anyone come develop a plugin just for Goose? But we saw all these opportunities and so we started talking to Anthropic and we were like, I think that there's a space here for a protocol that they're like, well, let me tell you about. And it was really cool to see.
- [73:41]
B
You know, about the Z side.
- [73:42]
E
No, no, no, we didn't. We reached out before we heard the Z thing and so we were like, okay, like yes. We just want to, like, we want to pile onto something that has a chance of succeeding because as like a client, it's like an ecosystem, right. Like the more people are here using it, you get more value as a client than as a server because you know your servers are going to work with any client. And then as a client, you know, you have this giant library of servers. And so that's been like a big part of what Goose does is that it's not really like it is a coding tool. People use it as a coding tool, but you can turn off the code part and you can just connect to any MCP server. And so it can be like operating like, you know, a science experiment. I've seen that. Or like just like Google Docs or whatever. And I think that it kind of shows you how MCP goes beyond just.
- [74:26]
F
Like the VAT coding space. Yeah, I think as well, it's also the fact that it's concrete is so important, like for all these standards. Like there's a long history of standards throughout computing that like people like proactively write a standard and then when you know the it's actually tried out, it has problems. Yeah, but like for MCP and like all these new agentic standards we're coming with, we really want demonstrated utility. Like the most common thing on the call committee is like, there's a proposal and we come back to people saying like, have you tried it out? Does it work? But the protocol is about communication. So if you're trying something out, you need collaborators and you need like concrete open source projects like Goose and you need clients, you need a variety of servers because it's only with that sort of open ecosystem they can meaningfully understand if this is actually going to work.
- [75:17]
D
I totally agree with that. I mean, I think the world of standards and open source development are just merging. Right. You sort of co develop these things together. I think I was trying to figure out whether David is Vint Cerf or Linus Torvalds for agents. And I think maybe it's a little more, it leans a little more Vint Surf and then maybe Ghost is a little more Apache web server and my whole leanest part kind of falls apart at that point. But you do need something substantive to Try the protocols out in order to make sure you know how to improve them. It's that feedback loop that's so critical.
- [75:56]
B
OpenAI also has a coding agent that is open source, I think. What's the thinking there, apart from like, well, would Codex ever be donated to AIF or we just don't know yet?
- [76:09]
F
I think the short answer is we don't know yet, but it's sort of like a feedback loop which is in this open ecosystem. We don't want to have too much alignment all on one implementation. One thing, there's real value to users and developers or whoever's the participant to active competition in some parts. So there's this balance of we need openness to foster collaboration and experimentation. But I would like to see a variety of coding agents and each one might deliver unique value, different value and be free to explore independently. So it is sort of like a careful balance here. There's a bit of like a tastemaking approach to contribute things that benefit from being open. Like AgentsMD is an example which is open up any GitHub repository. It has this file, it works the same way. If everyone sort of did their own thing, there's. That's very low value, potentially damaging, but so there's commonality value. Whereas for actual concrete implementations and projects, it's great to have reference implementations in many ways or experimental grounds like Goose, but I really favor a huge variety of them because that way we'll see what comes to be the best.
- [77:24]
A
Is there a roadmap for what you want to add? For example, the Agenta commerce protocol like ChatGPT already uses, but that's not a part of it. There's no model as a part of the foundation. Do you already have a roadmap? Or like you said, you're just kind of like going month by month seeing what are people using and what should be in there.
- [77:42]
C
I think we don't have a roadmap in the sense of like projects lined up, but I think what we have is principles by which we will select projects to some degree. And I think the effort here is mostly around sitting together after the now that the foundation is created and then evolving these principles as we're seeing people going to ask us about the projects they would want to put in and then develop the foundation further as time goes. But at the moment, I think the most important part is that we have the principles in place and then you go and having the conversations with people who want to be part of this foundation.
- [78:23]
F
One principle that really comes to mind to me is Composability. I often use the analogy of Lego blocks sort of thing, which is agentic systems are a sum of many, many parks. And so something that I hope the foundation can evolve to do is have these interoperable composable bits that all work together pinkly. And so we don't have a roadmap of future contributions. But I welcome all contributions that play nice with other contributions and really create this potentially a future flexible open agentix stack to be like not a universal agent, but an agent that suits everyone's purpose or need.
- [79:04]
D
Yeah, it's tricky. It's a hard. And these guys have the harder job of early in innovation cycle. You don't want to restrict innovation by saying like, oh well, this is the one versus that one. But you also don't want to let every single random thing into an organization like this. And so I do think you need this. Tastemaking is a good way to describe it where a group of, you know, elite architects and developers, you know, folks like the three people sitting next to me are more curating and you know, some, some things can work, some things might not. But there needs to be a process which I think will define to do that, that curation that happens via tastemakers. And it's more of a, not just more, but essentially a technical effort. Not something where a committee of, you know, folks from vendors get together and say, well, my product should be in this roadmap and that guy's product should be in this roadmap that tends to not be very successful.
- [80:10]
C
Which leads to this other principle that we really want. Projects that are, have all the most traction, that are well maintained, that have, that are very, very healthy in the foundation. I think that's super important to us.
- [80:23]
B
Right?
- [80:24]
E
I think like you're looking for something to have already found a niche and to be established because you don't really want to be pushing like a speculative architecture. You really want to be embracing something that already works. And so I think a lot of the stuff that we're talking about, like payments or kind of, I really enjoy the interface to model architectures. I think those are really interesting. But it's not yet obvious that that pattern needs to exist. And so that's something where we can go see it and like try to make it work in some projects and then come bring that back if it really has a role.
- [80:58]
A
And on the opposite, what's my incentive to bring my project? I have a project with adoption. It's well maintained, it's healthy. What's the benefit that I get from donating it to the foundation.
- [81:12]
D
I mean, I can start that, but I'd love to hear from these guys as well. I think what you all technology is an implicit futures contract, right? And so if there's technology that has traction and that traction sort of wants to be built upon, having that technology at a neutral place like the agentic AI foundation, where the whole industry is making decisions about how to invest. And when, I mean, when I say investment, I don't mean like becoming a member of the foundation because you don't need to become a member to participate on the technical side. It's decisions about, hey, I'm gonna, you know, assign 10 of my company's engineers to co develop this with your organization, the contributing organization. And you know that that's a way that we can all essentially co develop together. And, and that will provide better support, more development velocity, higher code quality because more people are participating in it. And that's a massive incentive if you want your technology to actually be used and adopted in industry and get more feedback and kind of a positive feedback loop of great project that gets great products in the market, that market feedback then allows companies to make money off of them and pay engineers to improve the project. Better products, more profits, better project. And you know, that's the incentive, which is pretty high.
- [82:42]
F
One could add a technical sort of spin, which is none of these things are built on a vacuum. Like all these projects build on lessons and learnings or practical code from other projects. And that's a big opportunity. Like any technical contribution will bring its own unique value to the foundation. At the same time, it then gets to learn the lessons that all the other participants in the foundation do. And like, I found it really valuable over this past year working with David and others on the MCP committee about like, is it actually that communication thing that makes our ideas more robust, makes the implementation better? We can be sure it's secure and safe and actually works. This requires communication. And that sort of the foundation is the natural, like town square for this in a way.
- [83:30]
E
So one last angle on this. I think if you're working on a standard or a protocol, this is such an obvious decision, right? Like the value in the protocol is about how many people are adopting it. So being a part of this, like, gets you that reach. But I will say, as someone who's working on a client and not a protocol, I think there's value there too, right? Like, we want this to be part of the foundation because we like develop these ideas together to your point. And so it makes it better like we're donating goose because we think it's going to make it a higher quality tool.
- [83:59]
B
I actually have a follow up question on just the LF side. LF has many other funds and organizations including Data and AI foundation as well as dedicated like Pytorch and all the other ones, I guess. Why a new foundation?
- [84:15]
D
Well, because everyone's special. No, I think that the way we look at in this space and you know, I'll, I'll put aside the projects in semiconductor tech and operating systems and stuff but in AI we think of it sort of like how the market has evolved. You know it started with tools like Pytorch and you know that transformer tech that is used to create LLMs. The, the Linux foundation kind of took a pass on like Frontier model world because in the open source space having connection to an intern, the Internet and some intelligence and a computer that sort of entry in the world of Frontier LLMs it's a computer connection to the Internet, some intelligence, $2 billion with the GPUs and a ton of data. Harder for consortiums to do that kind of work. So pass. Then you look at how you know, reasoning models have come out, need to be, you know, in inference world things need to be scalable. Okay, now you've got interesting technology, Vllm, Ray, things like that, they have to be deployed on something. Kubernetes is sort of that these are all distinct components. Agents are a distinct enough set of technology that it merits its own community.
- [85:35]
B
Separate from data in AI.
- [85:36]
D
Yeah, because like a Pytorch dev isn't really doing a ton of stuff in agent land. Right. You know, somebody working on Dockling maybe is a little more adjacent. Right. But not quite the same as somebody who's like working on Transformer Tech or Vllm. And so they are logical categories. I mean sometimes stuff comes in over time and you know, we sort things out later. We had early on in the telecommunications sector, you know, a software defined networking effort, a network function, virtualization organization, orchestration effort, a whole bunch of stuff, all separate entities. And I was like, let's just bring all these things together because the technology is now mature, we're taking all this money in, but we don't really need the resources anymore because the market's already mature. And so it took me a year to get all these companies to decide to bring all these things together and not pay all these separate fees and have all these separate orgs. I have a little folder in my inbox that says, you know Convincing people not to give me money. But in this world I think it's a different kind of audience. I think it's narrow enough, I think it's specific enough to agents where it merits its own entity.
- [86:50]
F
I think as well it dovetails somewhat with the earlier thought, like with a taste making aspect to this. For these organizations to be effective they really need a focus like something that brings them together. And ultimately you can imagine an alternative where we snowball and there's only the Linux foundation, this Uber do everything remotely connected to a computer and that wouldn't be that effective. So there's a tastemaking here as well which is going to be focused on the gentic systems and how they connect together. Hence the Gender Ki Foundation. But like everything's about growth and evolution. So there's a possibility that later down the line we recognize some natural affinity. We have something new, something old and then they can be brought together. But, but the focus helps the beginnings.
- [87:34]
A
Hopefully what's going to be the actionable outcomes. So obviously you have the funds to direct. I know a lot of the Linux foundation does events. There's also like eventually like certification, things like that. What's the split of the foundation investments? Is a lot of it going back to different projects individually? Is it about the community building? And then from people that have not been involved from the outside it's like this just seems like a nice blog post and a bunch of logos. But like in reality how are things going to be actioned?
- [88:05]
D
Yeah, I mean 50 companies coming in to fund a bunch of blog posts seems like overkill, right?
- [88:10]
A
Exactly.
- [88:11]
D
So I think there's a couple of things. One, the intellectual property assets now are owned by this entity. That entity is responsible for making sure that you know, that IP is managed effectively, that licenses are complied with, that intellectual property problems are dealt with. Some funding goes to that. There's a leadership function where you know, to help bring consensus across the industry and within developer communities. You have to have a special kind of someone to do that. And I think they need to be technically knowledgeable but humble enough to know that they're, that the community is the one who makes the technical decisions. So kind of just, just you know, sort of lead through influence to kind of help people organize things effectively. So you, you hire some people to do that. You hire people to do like developer outreach, community engagement because you want more developers coming into the community. So funding to go to that and then there's a huge convening function. The Linux foundation hosts 50,000 plus virtual meetings a year. So we have this like, I think we're probably like one of the largest users of Zoom. I know for sure. We're the largest Slack user in the world. And so that convening function is critically important. Make it as seamless and easy as possible to convene and then, yeah, we hold events because I think, you know, to your point, developer engagement, face to face, being the town square where you physically get together means something. So I think you guys have been to Kubecon, you know, we have easily 10,000 people that come to that conference twice a year. In Europe this summer, there were 13,000 folks there who, you know, come in and they exchange ideas. The core maintainers get together and make real decisions. And then the last thing we spend resources on, and you can go, even just check these out for some of our other projects, is we have a whole platform that enables, you know, maintainers to look at their community and understand, you know, like, what's our velocity, how many developers are we adding? Like, what's the social media scuttlebutt around this project? What are leading indicators of adoption? How's our security doing? Like, you know, do we have good practices about application security? And those are all things that we, you know, invest in to help make these communities, you know, better commercially adopted so that we get that positive feedback loop of like, adoption begets more investment in the form of developers providing input and that that virtuous cycle kicks off. That's where the funding goes for these kind of things.
- [90:55]
B
I put in that question into our doc because it says it's a directed fund. So my cheeky question was, well, what are you directing them to?
- [91:01]
D
So, I mean, that's, it's kind of. So directed fund gets into like the, they are direct nerdiness of this. Yeah. So, but it's the reason we structure it that way is somebody has to own everything. The Linux foundation is actually ownership vehicle. And remember, we separate technical governance from the governance of actually how money gets spent because we don't want this sort of pay to play aspect of technology that tends to screw everything up. And so the directed fund is really like, you know, real stakeholders who, who really care about this tech, put money in and use it in a way to help build the market and the community and all the things I just talked about and just let developers do what they're super good at, get together, solve tough problems, be, you know, taste makers. That, that's something that we separate.
- [91:51]
A
Yeah. I think there's a great essay by Rich Huggy who created Closure about Open source, it's not about you. Just because something in open source I don't owe to respond to your issue and to pull requests. And I think some of the worries sometimes that people have about the groups is like, well, you know, if not you're a part of this thing, am I supposed to also listen to your thing and implement the thing that you said? So I think that's going to be a super interesting thing in a technology that is so new. You know, I feel like everybody, because there's so much venture money in like early stage companies and like obviously the foundation model apps have raised so much money that they need to be on top of it. There's a lot more pressure I think from the community to try and be a part of it and put their stake and be like, yeah, we contributed that or whatnot. So I just think it's like a unique compared to the cncf, for example, where the hyperscalers are kind of like around the cloud and we all know what those workloads look like and nobody's really trying to influence. There's not like a OpenAI preferred thing versus an anthropic preferred thing.
- [92:50]
D
But it wasn't always so. So when we started cncf, I got a call from, I think it was Urs Holzel and Brian Stevens who were over at Go Google. It was 2014, I want to say, and you know, they're competing. Well, they had, they weren't even competing. They weren't in the cloud business and they wanted to be in that business. Amazon was, you know, hosting virtual machines on EC2 and they were the de facto leader. They said, we will give away Kubernetes, which was kind of the Borg and they renamed it Kubernetes to the Linux Foundation. And we, you know, because we've never run a virtual machine, we think containers are a better way to scale cloud applications. We'll give you this tech and it'll be helpful to us if the entire industry adopts containers and Kubernetes as the way to build and deploy applications. So that was the strategy out of Google and they contributed some serious IP that we all know today is awesome. But at the time, remember, Mesos was still a thing, like paas was still a thing, right? Like, you know, Heroku, Cloud foundry, even OpenStack, like virtual machines were still kind of a thing. So it wasn't clear what the abstraction layer for cloud computing was. But once the market started sort of piling on to Kubernetes, you know, like, oh, now Microsoft Joined cloud Native Computing Foundation. They're investing in Kubernetes and creating Kubernetes services. Oh wait, Amazon's now investing in this then the consensus was really coming and built up here. I think there's a somewhat similar situation here with the caveat of saying like 10 times faster, right? Like just day one, so much momentum around MCP, so much interest in this. And then also 10 years of CNCF to sort of teach the developer community and the vendor community how to do this well, where, where investment is not mutually exclusive to great technical outcomes I think has been super positive. So I think this thing's going to move super fast.
- [94:52]
A
Awesome. We don't want to keep you guys too long. I'm sure you've been on a media tour this week. What's maybe from each of you one thing you look forward in the new year from the foundation.
- [95:03]
F
So I don't really know what it's going to be look like, but I really look forward to the next step as as David mentioned, like it's been months of development and discussion or whatever to bring us to this and there's this sense of I guess, relief achievement that was like, you know, you made a foundation, we're collaborating, we created this open space. It's great. But the what next? I'm super excited for the next technical contribution for the first AAIF event or night or conference or whatever form it ends up taking. Because there's another world where bodies and foundations are created and then eventually they get forgotten. And this is not that. This is really a beginning and so I want to see it be healthy and grow and I just don't know what comes next. So I'm most excited to see that.
- [95:51]
D
In the new year.
- [95:52]
C
I think I'm most excited if I really take a neutral look at what just happened in the industry with creating this. It's like you have Google, Microsoft, Amazon blog, Bloomberg, Cloudflare, OpenAI, Anthropic. Just a platinum member create a foundation. I think it's just like this is actually quite cool and quite substantial. And now it's just like now we had this starting point of like, what can we do with this? And to Nick's point, I think there's a lot of things we don't know yet and things we need to figure out for Anthropic. This is the first big foundation we are recreating and we have to learn a lot here. But I think it's just such an interesting starting point and I'm just super excited for these new when you start something new of what you can build with it and it's in a way of building something that I'm not familiar with. So I'm super excited to learn about this and seeing what we can do with this. I feel quite unique vehicle now and really driving the agentic AI open source community forward and focusing on what we're. Some of these companies who are very competitive with each other, have common ground and where we can build things together that is just benefiting and uplifting every user in the market and every developer in the market, every builder in the market, significantly. That's what I'm really excited about to see.
- [97:15]
E
I definitely agree with both. I think there's a lot of opportunity to figure out what the structure does. But let me give you something more specific that I think is like already in coming up, which is I want to see how agents become asynchronous and I'm really tired of reading through chat sessions and I want this to be a thing where I can go have 20 agents working for me and actually see that come together. So I think that MCP is starting to approach that answer and then we want to figure out how to make those reference implementations and show people how, how they can actually get another order of magnitude out of what AI can do for them.
- [97:51]
C
You don't enjoy pressing yes every five.
- [97:54]
E
Approve every three seconds, bypass, bypass dangerously, skip permissions. Yeah, turn it off.
- [98:01]
D
I'm with you on that one. I think what I look forward to is the success stories of the organization that's implemented agentic technology in that way and hearing how it works really impacted their business. I'm looking forward to stories about MCP startups that made a ton of money. I'm looking forward to stories like, like in CNCF this year, CVS Pharmacy joined the Cloud Native Computing Foundation. Right. Like, you know, a pharmacy company that's really a user and adopter of technology, sort of, you know, the late majority. I think we're going to start seeing organizations really, really use this tech impactfully, provide feedback back to the community and like it. It just the potential of the technology. I don't need to tell this crowd how huge it is, but we'll start to see that truly manifest that that is going to be cool.
- [99:03]
A
Well, thank you all so much for joining and congress on the launch. Thanks for having us.