One Year of MCP — with David Soria Parra and AAIF leads from OpenAI, Goose, Linux Foundation

(upbeat music) - Hey everyone, welcome to The Lid and Space Podcast. This is Salacio from The Recurnal Labs, and I'm joined by SWIX, editor of Lid and Space. - Hey, and here we are joined finally in the studio for the first time. Welcome back, David, from Entropic Slash MCP. - Yeah, hey, well, nice to finally talk to you in person, like last time, like a year ago, it was over BC, and this is Wafelon. - I watched the 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, at least the public announcement. - Yeah. - And also last night, or yesterday, it was the eGent to K.I. - On the show on the launch. - Oh, yeah, that was nice. It was nice, it was nice to see the Anthropoc office. - Yeah, and I'm Ben. - You like Ben? - Yeah, it's very good food. I would say, in terms of my food bench, and Anthropic does regover openly, I. - Yeah, so at least that's what we have go for us. (laughing) - Awesome, Ben, do you wanna give just a quick overview of what's happening with MCP, and now 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 joining us to do more of the high double. - Yeah, and 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 like crazy growth, and like adoption, you know, through initially, through like Thanksgiving and Christmas very early, with a lot of like builders building MCP, and then you know, you had like the first big clients coming in like cursor and VS code, and then like you had this like inflection point around April with like some old man, and Satya, and Sundar and all, I'm posting about like MCP, and that they're gonna adopt MCP at Microsoft, at Google, at OpenAI, and that was really like the big inflection point, so, you know, 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, we 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 server, so connect like really about like to a remote server, and introduce like the first iteration of authentication, and then in June, we revisited that, and like improved it quite a little bit, so that it works better for, you know, or enterprises in particularly, and we were very, very lucky that in that time for March like June, we're like able to like have absolute industry leading experts that literally work on OAuth itself to help us with some of the pieces, right? I mean, how to get it right? And then we focused a lot of on like security as practices and this type of work, and now we like, I feel we have a really solid foundation, and we're doing, we just launched like, and our end of like November, then the recent iteration of the protocol, finally like the next bigger improvement of the protocol, which is like long running tasks, to really allow for like, you know, deep research type of task, and like, you know, maybe even agent-to-agent communication, and so I think we're just stepping into like this territory now with like, okay, we have really solid foundations, we have like one more big premise if we wanna have, we wanna make like, a little bit more scalability, things work, and then we're, you know, gonna get into a phase where it's probably, it becomes a bit more stable. And so yeah, it's been, it's been absolutely crazy here, man. - You just say the agent-to-agent, so there is a two-way protocol. I'm curious when the Agent-to-Ga Engineering Foundation got formed, or just Agent-to-GaF Foundation. Was there any discussion about, and you've decided protocols being a part of it, or, you know, Sean Road or Post-Cole, YMTP-1? - Yeah, I'm already, so only my favorite Post-Cole, maybe it was already to go with that. - It was, and it was before, seven, and all the other guys. - Yeah, yeah, you were right, all right. - But what, I mean, I think it was just obvious that was going to happen, so. - Yeah. So we, of course, have conversations around like, what is else was in the market, like the 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 have an anthropic, have an open source foundation, so this is all new to us. We really want to start it small and making sure we're learning along the ways and being able to like, like, shepherd this, and the way we feel is best for the industry, together with OpenAI and Block. But the second part of that is also like, we really felt like we wanted to see things that have a lot of adoption or effect to like, at least on the protocol side, like a de-factor standard. 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're like super open. As long as they're like, complimentary to what's in the foundation. On the application side, we're a little bit more flexible and we're like more open. But on the protocol side, I think we really want to make sure that we're not like offering like, the foundation doesn't encompass us like five protocols, for the same like communication there. And so yeah, there was a discussion, but I think for now, we just want to start it small. - Is there a role, like a double hat that you have now with the foundation, or are you more focused on MCP? - I am still mostly focused on MCP. It'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, one understand. Because the rest of it is like, okay, how do we use the budget of the foundation for events and things that are like quite dry. And then the technical parts to like MCP, they stay actually the same. Like on the way we govern MCP, nothing has really changed. And so that's really still my job is to lead core maintainer of like, shepherding the processes, shepherding the protocol forward. And then beyond that, now the additional double rollers, like I'm also going to be on the technical steering committee of the foundation, which I 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 to something we would want. Is this something that we feel is like well maintained? As a lot of adoption is not going to go away. We want to make sure the foundation is have like super interesting and important project and not like a dumping ground. Like if, you know, some foundations might have ended up with. Yes, 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. Yeah, you've covered a lot. There's been four spec releases. That's a lot. Yeah, so people may have missed some of them. This is what I'm saying, right? And I think it's really interesting how you continue to work on like really important parts. Like I always think like it's very hard to follow up a major success with a sequel. Because the sequel usually is hard to repeat that impact. But I think every single time you've actually managed to focus on something important. Yeah, so maybe we can cover, I guess maybe we'll start with the March May 1, which is HTTP streaming, which is good, and the off spec, right? Any other, I don't know if you want to highlight any others, but we'll just catch people up on that stuff. Yeah, so that was, I think that was really a, that was such an important one. It was the number one requested thing. Yeah, it was like, it really opened up this remote thing. And we were, we already knew actually in December, in November, that the next big thing will be like, how can you do this over the, you will over remote? An 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, it's like, you need to do all, 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, the streaming properties that we require. And then how do we do authentication very early? Authentication. In the first iteration, I think we did a 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, 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 you know, I have my set of experiences of like, what I'm good at. And enterprise authentication turns out it's not one of them, right? But they're way better to the people for that. And so that's when we like, I feel that's March. I saw, I saw you post that, but I didn't really dig into the details. Was it like the typical Samuels type of authentication issue? The main issue we did is in auth, there are two components. There's an authentication server who gives you the token. And then there's the resource server. It takes the token and gives you the resource and return. And in the first iteration of our authentication respect, we combine them to gather into the MCP server, which if you were building an usable, yeah. It's kind of usable if you build like an MCP server, like as like a public server. As you start up, 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 have some ID, IDP provider or an IDP. And you go up to, and also, yeah. For most people, they don't even notice this happening. All they know is like, oh, in the morning, I'm going to go long, it was a go-go for, and they're going to access to all my work stuff, right? But that's effectively the IDP, right? And if you combine these into the same server, you just can't do this anymore. And so all we need 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 separate. And that's what happened then in the June spec, where we separated this out and worked with all of these like, okay, now how do you do dynamic client registration and 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 that fixing it in June. - Yeah, what's the state of agents authenticating on my behalf? Because even today with the OAuth, I still have to log into linear and whatnot. - Yeah. - OAuth 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 barrel token. And so we're not very prescriptive of what like, agent to agent authentication would look like or on behalf of agents. They are ideas that we're looking at 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't technically, as a moment here 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 when, or 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. - Yeah. And then yeah, on the remote thing, you went from local servers like SSC and then streamable HTTP, any learnings you wanna call out there, any regrets for learnings, for others. - Simhan, transport. The one discussion that has never stopped on 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 March, we wanted to get a transport going that basically retains a lot of the properties we had from standard IO, because we really, and I still believe just until today, that the 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 clients and the server. And so we always looked for something like that. We also knew that we looked into alternative, 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 I was able to be upgraded to like a full bi-directional stream if you need it because you really have like complex agents to communicate with each other. That's where streamable HTTP was born with that intent. And I think there's something that in retrospectively, 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 get wrong that we made a little things optional for the clients to do. Like you can, the client can connect and open this return stream from the server, but it doesn't have to. And the reality is, is no client does it? Because it's all legal. And so a lot of the bi-directionality goes away. And so features like elicitations and sampling are just not available to the servers because they don't have that stream open because the client, the client implementers like, yeah, that's the minimum viable project from product for me. I don't have to do it. And so that, 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 transfer 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 and a container or something like that. Well, now if you get like true call and then elicitation and the 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 in effect, if you need some form of shared, like the red is memcache, whatever you want. Like some form usually pops up or something like that. One, 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 doing MCP at a scale that I can't tell you the numbers, but it's like in a million requests. And so now it becomes a problem, right? And so now we are sitting here like, okay, how do you build an iteration of the protocol that allows for basically these principles of like, making as simple as possible for a simple TPS server, 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 complicated, yeah. Because a lot of the technology today is really just, it is very little like that. People either do the simple thing and then you do like something like REST or you do like a full bidire stream and then you're just gonna do like web sockets or like GRPC and so on. And we need kind of both. - Was 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 in this? - It's watch fun. - Yeah, I got to work with some of the best engineers in the industry, like it's insane. - Okay, well who decides, you know, usually there's, - 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 what are the real problems which we all agree on? What are the things where we nest not necessarily agree on? And what are the, you know, and then within those bounds, like the best solution and it takes a while and 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 a Microsoft and a lot of it comes from just the ways of building things and then the problem from Anthropics look 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. - Yeah, it's very a lot of this kind of stuff. And when a standard works, this is the, you know, and these people are all amazing. I'll just learn from all my peers so much. So I'm very grateful to be in the situation. - Yeah. - This reminds me of the IETF standards process. Is there some discussion about how this works as a private group versus something more traditional? - It's an interesting one. Like it does look a little bit like the IETF. The IETF is very slightly different. The IETF is like an open forum where everybody can go. And the result of that, it's like the IETF is very consensus based. And by accident, not by, like, not necessarily because they want to be, but by accident quite slow in the processes, which is very good in many ways. - You know, the undone, right? - Right. - Once it's up to you. - Yeah. And like, for example, when you look at like, you all have to put one spec, it's been in the work for like three years or four years and they're just not done with it, right? And that's like, that's the length of which IETF standardization works. Like these things can take a long, long time. And I think that's good for certain pieces, but I think in the eye at the moment, it's just so much fast moving. You're just somewhat forced to find a smaller group. And so that's where we run an MCP as like a really traditional open source. I'm project with like a core maintainer group of like eight people, the basic data side, 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. How do you balance the influence of like the model improvements with out-of-shape the protocol? Because obviously, you know, you haven't tried picking up any eye. You guys are doing posturing 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? - I'm not 100% familiar. Like 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 at last, that we are like having in our model card of like making sure that like real, 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 like improvement and that we're relying to some degree of mechanics that you can put into the model training. I'm gonna get more concrete here. So for example, people have at 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, I throw them into the context window. You just get a lot of blood. It would be just 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 blood. 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 add, give the model some information and let the model then decide to gain more information. And of course here is where we're like, some of the fourth side that we see because we are 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. And any model can do it as 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 this 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. That makes sense. - Yeah, and I think the context for our point is important. And I think down there's the MCP versus code mode. And then it's like, well, if on tropics says code mode and on tropic made MCP, maybe instead of as with-- - So the block was actually called the code mode. That's the call fair term. - Well, yeah, but like people call it, we call it pregurmatic MCP and other call it code. But in the end of the day, what it boils down to is just like, okay, and here's the interesting part, like the first of all, MCP is a protocol between their eye application and like server, 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, well, it's a really good writing code. What if I take this and treat it like API calls and you give it to the model and now the model generates code. And what you effectively doing is this composability that the model would have done anyway by like call tool A, get the result, go back to inference to call burby and then combine it into call free. Now you're 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 the 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, right? You're just using it at a different rate. So I'm always a little bit confused when people go like, but MCPs, why does it tell me that does it mean MCPs users? No, it's still just a different use, right? And I think you will see evolutions as we're getting better of like how we use these models. And the infrastructure around it gets a bit more mature. You suddenly can assume that most model like AI applications will have some form of like sandboxing for execution. You can do a lot more fun stuff like that. But I don't think that the value of like 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. This is a good time to bring up skills. It's always. So awesome. So skills is a more recent concept. Yeah, 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. Skills can also create skills which is very fun. Yeah. 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? Yeah, I agree. I think that's the interesting part is they're not overlapping. I think they solve different things. I think skills are super great. And I think that the first that really like they've been built from the principle was 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 like a specific set of tasks? 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 connectedness of the actual actions that you can take in with the outside world. And so I think there's somewhat orthogonal and like in terms of like the skills really gives you just domain knowledge, just like kind of vertical. And then like MCP gives you this horizontal of like, OK, give me that one action. And of course, skills can take actions. They can take actions because you can have code and the drips 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 use the way to act your machine. Yeah. 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 CLIES, 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 that regard. And so what I think MCP brings is the authentic authentication piece. It brings the piece that you don't have to this like an external like person like for example, if you have like 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 in the server. And so if you build a web application or like a mobile application, these things come 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 like different functions, different like, you know, the account and the engineer, the data scientist, and then use MCP server to connect these skills to the actual like 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. Yeah. So MCP is the connectivity layer. I think it's the word that you choose. Communication layer. Communication layer. So is it architecturally I'm wondering if it's like the MCP's client inside of each skill or is there a shared client that can discover skills? 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 discovery things, you can do things like, OK, I have connection pooling, I can do an 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 when you do it. But I think both works in the end of the day. But this is things to experiment with. I do want to highlight for people who might have missed it. You say we do blah, blah, blah. Actually, I think nobody understands enough how much anthropic dog foods MCP. And I only understood this when I watch John Welsh do his talk at AIE, where he was like, yeah, we have MCP gateway, everything goes through this. Yeah. And like, yeah, what can you say more about that? Yeah, I mean, like, you know, we use both, right? We use a lot of skills internally. We use a lot of MCP servers internally because we have, it obviously, you know, you want to make it very easy for people to deploy MCP. You want to have some form of integration with UIDPs and so on. So we have a gateway that we build custom purpose for ourselves. And you just got to like deploy your MCP servers. It's all internal apps, it's all internal stuff. Yeah. Some of them are like external things, like, technically external things, but in the lack of them offering a first party one, we have our own, like, we have a Slack MCP server, which I love to use that have Claude, like, summarized my Slack for me. And so there's quite a lot of usage for that. Like, we even have like an MCP server, we're like, we're doing like a semi-bi-annual, like, survey, for example, around like how we feel like about the company, about the future, about the AI, about safety, these type of things. And we have an MCP server for that. And I can ask Claude questions about the results, which is really fun. Is it your team maintaining it? No, we maintain it the same way. But like, I think one of the fun part is like, when we started MCP, it was always like MCP before we even open-source 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 sort 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 largest story of MCP. And so it's fun to see a year later. Like, that's what's actually going on. And it's like people build MCP server for themselves. I probably don't even know 90% of the MCP server is that anthropic, because they might be in research, and I might not even see them, or I just don't know, because people build for themselves. But do they host it themselves? Do they remotely? They effectively have a command to launch it. And just launch it in a Culean's cluster for them. So it's like, actually-- Yeah, that's good for anyone at a large company to build any platform for-- And there are platforms that offer that to you for us from security perspective, you want to build these ourselves. But they're the person who built a fast MCP, Jeremiah. I see the company that offers fast MCP 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 to people with HTTP. And then a lot of enterprises use things like light LLAM as a gateway, and then they can even do just launch standard IO servers attached to the gateway, and the gateway does all the authentication, all the hard parts of MCP for them. And so there's a lot of ways to do this. But if that's good infrastructure, you really want to have is just make it trivial, make it like one command, choose a launch MCP server that was a standard IO server, and suddenly the stream of HTTP server was authentication integrated. And you as a developer only had to do the standard IO part. 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. No, no, no, reinventing everything. Shout out to Jeremy, I actually did invite him to do a workshop on the fast MCP at my New York summit. Yeah, he recently are a very great blog post about like a lot of the usage of MCP you actually seeing as internaling companies. And that's actually what we see at the moment too. It's really cool. Like in what companies? Internally in companies. In big enterprises, you see MCP everywhere. And it's actually way growing way faster than he would think because it's mostly internal to companies and without people seeing it. About discovery, so you launch a registry. There were registry companies, there were gateway companies. The official registry now has other registries putting their own MCP in your official registry. Any more registries, man. I mean, just one more, bro, one more. Yeah, what's the registry to rule them all? Any learning from that? Like launching a registry for like a new technology and like, whether or not, you know, people, like, you know, Smithery is one example, right? If you go on the official registry, it's like all these Smithery 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 does this kind of shake out? 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 MPM pipeline kind of approach to this where like there's one more central entity that is the where everybody can publish an MCP server too. And that's really where the original registry came from. And we really want 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 all the given tasks 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 gonna 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 work on that. And so what I want to see and I think where we slow slowly but this is slowly adding is a world where and we have the official registry where everybody can put the MCP server but this is the equivalent to an MPM which has the exact same problems of an MPM. Like everybody can put it there, 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 separate registries which then like the smitherees 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 still getting there. Like the GitHub registry is curated off the or speaks the same form 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, us maybe your 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 your registry, you just connect it to yours and you're good to go. And that's really what we want to do. - 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. There's kind of like I find them in other ways. And this is what you do. - Yeah, I'm interested if you see like discovery it's 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 HN discovers. - I do think discovery is important in the model world, but I think that's where it's different from NPM because we're building like something for AI first and we can assume that's an intelligent model that knows what it wants. I think that's something that didn't exist before, right? 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, is what I want to build, just to 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, the public registry should probably not do this because it's a dumping ground for everybody. You want to do it against a curated trusted registry. - I like your phrasing that the model knows what it wants. Because I think that there's a lot of, 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. - Yes. - But it may not work. And I wonder what needs to happen in order to do that? - I do think we need a good registry interface, one hand, and then the second part is, it's like, we need to build for this and see what works and what that. - We need trust levels, maybe. - You will definitely need trust levels. - You need trust levels. You might need some form of, like, yeah, you need trust levels. You might need some form of signatures. For example, like one of the ideas, I'm not sure if we're gonna do it. It's just a random idea. But one of the ideas I always had is like, you can attach like signatures from like different model providers that have scammed the MCP 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, oh, well. - Well, I think these distributed cool signing. - It made us feel like it's not just really distributed. It's just like central and away, right? But I think this is the kind of stuff you will require. Or, but I think in a 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 effectively using private registries already for MPM, they're using for PyPy and they will also do it for MCP servers. In there, you have implicit trust and then you can just search, right? And I think that's really the interesting ground where we wanna experiment. And that's like, we have our internal registry effectively because when you launch via Johns, infrastructure like an MCP server, you have to get registered, right? And so we need to go and engage experiment with that too. - Okay. - I actually wanted to also ask, you started running some events over in London. You had the agents hackathon and you had Dev Summit that you called on your timeline. - Yeah. - I just wanted to get anecdotal stories of stuff you learned as you saw the community swing to life. - So we had two big summits this year, we had the MCP Dev Summit in San Francisco in the one in London too. - In the one in London. And I think what you learn is a few things. I think that the one thing is that you, that's very hard to get otherwise, just like 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 that what I really loved is like particularly in London, you had a lot of financial people there because it's like really a financial hub. And it was actually the whole conference was in the financial district. And learning just like the kind of problems of like things you need to enforce because you have legal contracts because the like financial regulations, these were things that were that I did not know before. And I learned a lot about like, okay, what does like a thing like an MCP like a communication there need to look like if you have these like constraints that in a normal like 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 it's a legal contract, right? You must, like the client has placed this data to you, it must tell you this came from the third party, right? And these are constraints that just like in a normal model world don't really exist, right? But like in a financial industry, this is like a legally enforced. And so these are the things you like, okay, how will this work in a world where I'm sick will fall off MCP? And so now that's when we like started like creating this financial services interest group that Bloomberg is heading up to like figure out like what are some of the things that you like a client must do if it wants to speak to our 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, right? So I think there was some of these learnings there. I think the other things that you just see is like just how many people are building and just the excitement and like the creativity that some people bring to this. Like that I just love, right? Like from the average you didn't expect, right? Like I love the guys on 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 like people bring some really creative parts to the MCP 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 so we're gonna repeat it again. We're gonna do in New York in April I think or March or something like that. And then we're gonna do it again six months later and I absolutely love that. - Any good sampling in these cases that you found? - Not so much. - Okay. - And that's always the, like you know, that's the time we talked about this. - Yeah. - We should use it more. - Big sampling a little bit, man. Like we, I think one thing I learned from sampling, like everyone's to use tools with sampling in tools that are not exposed via the MCP server. Like when you want to do sampling, 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 it in this iteration. And so we hope to see a little bit more, a bit more sampling use cases. You will find every now and then on MCP server it 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 an API case and maybe even charge someone. In a local case where sampling is really powerful because you're shipping something to a lot of people and you don't know what is there, what is the model that they've configured, what is the application they've plugged in? It might be VS code, might be called desktop, right? And in those cases, sampling is useful, but also like clients just don't support it. So something 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've got to win some, you've got to lose some, you know? - No, no, no, you're also upgrading it. And I hope there's still up there. - Yeah, yeah. - Like in some ways, you know, when you get it right this will be the real agent agent protocol. - Yes, yes. - Are most of the use cases that you see still data consumption? That's been my use case for MCP, mostly it's like-- - Yeah, it's context-adding hearing if you're getting data. - Well, the most action MCP 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? - Most people use it for context. I think that's the vast majority of usage. - It is in the name, my local context. - Yeah, yeah, and Nick Cooper from OpenEI always keeps telling me rightfully so that the name MCP was probably a little bit poorly chosen. Because it feels restricted a little bit, which I agree with. It's mostly data use cases. I've seen people doing deep research. - Be aware. I think people like exposed agents wear it. And so they are a little bit more complex, but it's not super common. It's what people like to have experiment with it. Like the deep research use case, I think it's a good one. That's not too uncommon where people do custom research. I'm for it. But beyond that, yeah, 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 through MCP UI or what we're gonna call MCPIs in the future. And I think that's super, super promising. And I think that's really quite fun. That's actually a lot now, with chatchip T apps, with MCP Y in general, that you see a lot. - Yeah, and you have the tasks, in the last. - I agree. - Yeah, well, I mean, I'm curious, because 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 do you expect people to use that more? - We design tasks, because we keep it come to us and go like, okay, we really want long running operation, which is basically agents. We want like a long deep research task that finishes in an hour. We want tasks that like we're not finished within the day, right? And people have like awkwardly tried to do this, we are tools, and you can, because tools are effectively just an RPC interface in the end of the day, but it gets very quickly awkward, because not 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 agents, and that's like something we heard from so many areas, and people trying to do this, that we like, we really felt we needed to do something like a task, like 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 gonna see a lot of it. Now, but it's a little bit early to see how good it's gonna go, because it just landed in the SNF case, and it needs to land in the clients, and then we're gonna see more of it. But I will definitely, I think you will see a lot of the custom you research parts, wait, and others. - Yeah, I'm very bullish on tasks. I think it was very important to get right. Basically, every orchestration or protocol needs, has a sync version and a sync version. - Yeah, exactly, a sync version. Any design choices that you wanna call out, that there are two directions, and you picked one in just the overall design of tasks. - Yeah, and design, there was a lot of conversations like, somewhere like, okay, it's just asynchronous tools, do we do a different primitives. In the end of the day, it was important for me. My luck most test for it was always, it needs to be able to like, if I want to expose something like Cloud Code, or like any other 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 he wants to expose. I'm tasked, it's 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. So that was the main constraint. The other constraint was making sure it's not a copy of tools. Well, you can think about like, okay, we just do tools again, have slightly different semantics, but instead what it's doing is like just like, you can trade a task by calling a tool with a certain set of like metadata fields, and then it automatically creates a task. So the task itself is just a concept of like a container that can do something, it doesn't exist. Yeah, like just like, we do something that's interesting from starting here into any year. 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, potential, which is obviously going to be a problem. So I think that was really the design goal, which makes it a little bit more abstract, and a little bit more complicated to implement, but that goes away because the SDKs just do it for you. And the SDK, and then over there, you just go like, he's saying call this and you return something. I mean, there you start to overlap with other things, like TRPC and JavaScript plan, or whatever goal, part of stuff that goal people have. 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 is we didn't get around. It was like, okay, instead of having to pull every minute or hour or whatever you interval you choose, the server can service all us events. Concal, you're like a webhook, where something and go like, I'm done, right? That's the optimization. But the actual core interface is always that the client can't pull. And that's actually how operating system operation and an operating system can work. It's like, you pull, it has to file change, it has to file changed, but you can also use like a modern interface on the kernel, like I notify you or something like that, the tell or u-ring or something like that to tell you, oh, I'm done, right? Yeah, the file has changed. - There's a trick I learned where servers can hold the HTTP connection until it's done and then they terminate, and that's the signal to think about that. - Yeah, which we do not necessarily want to do, because it might take a few days and I don't want to have people. - It's very responsible, where it's cool. - Yeah, yeah, yeah. Yeah, that's plenty of ways. I think we were just gonna go the webhook way honestly. - TAS are really interesting. And we basically have to invent this when we did this at the Devon API, a cognition, and I think that's also like, an interesting reinvention of like, well, everyone is going to need some kind of long-running operation. And this is, well, when you're calling an agent, you also get this. But the interesting part for us is I think what MCP's always trying to do, MCP always tries to encapsulate what currently people are trying to do, and you're not gonna be prescriptive what you're supposed to do in a year or so. We don't predict, we did tasks, because people are like, we need this now, right? We need it 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 it, what do we call it? - One minute thing. And so let's say this is a super long-running task, a lot of messages go back and forth. And topic actually was a kind of leader in context compression or in compaction, maybe with that's who's called it. And I think a lot of the other labs also do 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 now you just ask the full, yeah, right? No, you don't. I think there, just to think, well, it'd be very early in the industry still, we're learning a lot about what does the model date, what does not need, right? And even today, some agents start to drop two core results after a few rounds because they don't need it anymore. And I think that's very, very good. And so I think besides compaction, you will see, I'm just better mechanics of understanding what you need and what you don't need. For a long, asynchronous task, you might have a way where like, 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 like a small model, like a haiku modeling or like, what all this I shall retain, you'll tell me, right? You might be like the agi-plot approach will be just like let the model figure out what it needs to retain, right? 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. 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's 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 it, 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 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 not fairly dead, right? And now we do use models, we use compaction. So I don't know what's gonna happen in a year from now. Cool. - Around MCP's another question I had is like, how do you see them as being used by developers to build AI apps versus being a protocol or 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 whether I need an MCP and to me it's almost like it's not really for developers. The use is for like people using AI tools to just plug things in. - I get the comparison with the REST APIs quite a lot. And I think it's interesting, 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 already complains to me about like tool bloat. Have you looked at like the average open API spec lengths, if you put that into a model, like you will have a lot of bloat there too, right? It actually way worse. And funny enough when people try to like map one to one things, the often the model gets slightly confused because you have like search by name, search by ID, search by something, right? And like some of you have like five tools that look very similar to each other and the model goes like which one do you want, right? 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. Well then what I want is I want a world where you go to your application, you say do this and you should just do the thing and it should just connect with 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 they're talking but in the end of the day you just get the test done, right? 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 or 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 focus side. And they're still use cases for developers in general, like most of all it's builders but also like I still love my play right MCP's ever man. - Yeah. - But I don't know from the developer tool, the new Chrome one is like the new right, the new meta. - I also understand like for developers, right? Like they run like cloud code locally and all like things like a PLI is can be better approved, right? With some degree and that's okay. - I'm curious about the MCP apps UI with what you're talking about where it's like every client, like ChatRubyD has their own, right? - ChatRubyD. - So it's like if I'm used to the MCP app of this product but then if I go and ChatRubyD, there's like a different version that they curate it. It's kind of like a different experience. So I'm curious how you feel about that. Like especially now that you open it in the foundation right, you feel like all of this will be MCP backed in the same structure. - These two influences, right? Like MCP UI existed as a project which are a lot of really good ideas. I'm opening it, I 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 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 and you can use it across all of them. You build for everyone's run everywhere. - What ChatRubyT and you might be able to use it in cloud or in the goosle, whatever it might be that the program of your choice that implements this. But I think the general problem is what we have is I think that there are certain problems like 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 an visual, right? The most basic example is like you want to like book a flight, seat selection, right? Like you now get selected. 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 either. - As you based drawing. - Yeah, of course you want 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 in the user interface that the model can navigate and the model can interact with, but you as a human can also interact at the same time. And I think that's what we're looking for. And so I think it's just the 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. And like shopping has like 20 years of like A/B testing, what's the best way to sell you something, right? And so and shopping interfaces are super complicated actually. And you just want a way for displaying that to the user so that it's familiar to them and that they can interact with them. And that's what MCP apps is in the end of the day. - Yeah, in technical direction wise, is the iframe, the way there was, - Yeah, it's an iframe. It's you are serving basically raw HTML over an MCP resource. It goes into an iframe and then it talks to the outside. We are 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 gonna 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 like can just speak like a very clear boundary, like security bounded. - Yeah, and this has been in browsers forever. I think that I'm scared of it only because I hate course issues. And I think it's always the course issues. - Yeah, but this again, this does not load anything external. It is surely, like it should not, right? Like that probably are a risk of chance that we'd like then iterate and iterate and then in five years maybe it has the 25 course headers and whatnot, whatever, right? But I think at the, we were starting small again, it was like pure raw HTML, you should probably not have external references. We don't run through these issues. But you're right. - And can I inherit styles? - No, I think you need to put it in mind. - Yeah, obviously, like you will want it and then I feel like this is really a minor, but UI people care about this, which is you have, it should look like chat GBT. - Yeah, like chat GBT, you should log in since that cloud. - I think that's a very good question. I'm 100% agree with you, like brands and others who are deeply, deeply care about the app. - Designers will follow what I'm saying. (laughing) 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. - That's why I don't think it should be an reframe long term. I don't know what the solution is. - Okay. - But we need like new reframe that let some permeability because of this stuff. - Well, I think that's sensible, yes. - Well, I don't know. - But the other solution to the problem is the IGI pull the approach of I just give it a tool that says, give me a star sheet. - And well, so okay. - The model can call you and tell you what you're supposed to look like. - Okay. - This should an MCP app be, no, what it's being used, what the parent application is, is, you know what I mean? Like, it might be like the application all fixes tools, right? Then the model is free to call it. - Right, right, right. - Okay, so maybe standard is interface for people to pass down styles. - Yeah. - And they say, I don't know. But that's a very good option. - Yeah, let me ask the team. I'm just like, I'm mostly like, directly there, I'm like, not in the weeds of doing everything there. - Yeah, it seems like a little bit of a surprise to me. I never really paid any attention to the MCP UI. And then suddenly, you guys all adopted it. I was like, okay, well, I guess this is a part of the MCP now. - Yeah. - And it went from a purely back end concern to now, front end. - 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 still an MCP client if you don't. And the reality is it's like, you average like CLI agent can't do it, right? So they will never do it. And so I think that's fine. - Are there any other extensions though, similar? - We gotta look into like financial services as an extension, we're like, okay, you might end up in a world where you're from now, there might be clients that have like certifications that they are an amp like and get like a signature that they are like financial services MCP clients, and they can prove it with a 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 the server where you will, if you wanna deal and long run with a public service and public clients that do like deal with HIPAA data, like kind of like healthcare data, you will have to have guarantees. - Isn't it part of just authored? - And not necessarily, like I give you an example, like if I have declined might need to have a 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 social security number or your healthcare data, show up and then your back's in it, right? - Adam, we're gonna transition and have the rest of the AIF group join, but any final call to action, like either people that should join your team, people that should contribute to the MCP's pack or anything else. - I think the most important part is still building with MCP on a day-to-day basis for people to just go out and build really good MCP servers. I think we see a lot of mediocre MCP servers and it's some very, very good ones. And it's building good MCP servers, looking at how to use them. I think that's super important. The second aspect to that is we're a friendly 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, or being in the Discord channel, talking with us, giving us ideas. But also just helping us implement the types of SDKs, the Python SDKs. You're always looking for a new SDKs, right? Like we have active Go SDK development, but we don't have a Haskell SDK. I don't know if you have Haskell developer, or maybe you want to write it, right? Yeah, there you go. And so I think there's a bunch of stuff we can do and be part of it. And I don't understand how much you can just be part of the community, but also just like going build. And I think there's so much opportunity now, particularly to build like amazing clients now that we have understood progress of discovery better, not do we have understood code mode better. There's just this next iteration of clients to build a next iteration of servers to build that I'm just looking forward for people to do. Yeah. My last question I'll call out is, I want 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 joining the NCP joining the Linux Foundation. They're like, oh, is this the topic tickings I off the ball? Can you address those concerns? Yeah, I love that you ask me that. Like I think, yeah, I can totally see why people think that, but like it's actually quite the opposite. Like the commitment of anthropics is the same, right? I'm still, we still have the same people I'm 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 like two things. The number one is like making sure that the whole industry knows that this will stay forever open. That this cannot be taken away. And they have been, they have been like, I'm probably would never do this, I think. But they have been histories of like companies going like 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. Wait, what's my HDMI? 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. - I love it. - So there's people like keep a very close tap on it. And what this does is like, no. This is now owned by 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, like 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 that I'm, 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 will be don't want. And so we will not do that for us. MCP is still a core to the product and still super important to the topic. And so we still just as much as committed as we've ever been. - Amazing. - Awesome. Thanks for joining us. - And we're here in the studio with core team members of EAF. 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. - I'll start. I'm Jim Zomel and I'm the CEO of the Linux Foundation. I've been working there 22 years. And I was the person who helped so let's say the launch of the foundation, but take no credit for any of the technology work that's to my left. - I'm Nick Cooper from OpenAI. I've been there just over three years now, I think. - I'm generally OpenAI's head of a lot of protocol things and very interested in the OpenEka system and our representative for AIF as well as a core contributor to NCP. - What's another protocol that might form the NetNombrilla? - 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. - I'm David Zorriapara. I am working at Anthropic. I'm a rough technical staff there. I'm the co-creator of MCP. And yeah, the Anthropic and mostly lead all the MCP efforts. - Great. 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. - It's great to see everybody come together. I think when I heard about the new site, they 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 OpenAI and 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? - The conversation started out of two things. The first one is that on the MCP site, we always knew that we wanted to find a neutral home for MCP to make sure that the industry understands that this is 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. It in a foundation should this be inside its own foundation, which is like the 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 like 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 like very open to the idea as well. And it slowly looked formed. And I think at the time from this is like a few months, these things are not happening out of thin air in like a week or so. And so just a lot of conversation like what do we want to do? What are the kind of like 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 the like decades of experience helping companies through a process like this. I'm building what is a tech, this technically called a directed fund within the Linux foundation to build these kind of things out. - I think David said basically all the story from my side as well, which is, so we saw this like need to connect systems and then MCP gained such very large developer traction. And we had opened our very excited to like use and then contributed and actively participated 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 like MCP's always been like a foundation for like communication between agents and contexts. And a similar way the agentic foundation is, well, it's a foundation. But also it's like the starting point where we really look forward to other contributions like the starting of goose, our own agents empty, where we're really open for like a lot of technical contributions to build out like a full agentic ecosystem. - I'm curious to him, you know, I've been to the next foundation events before I spoke to them. - It's almost like it's 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 like 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? - 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. - Absolutely. - Do you use this metaphor, man? But yeah, totally. This is where I run three conferences a year. - Yeah, exactly, you can't do annual. - I think last night someone was asking, what do you see a year from now? And I'm like, well, if I dial the clock back a year, what have I anticipated where we're at right now? There's no way. 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 pull it less. And what is clear is that a lot of people are adopting MCP, 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. I think the same thing held in internet protocols, you know, that took a little bit longer to mature in 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 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 online. 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 asked 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? It's a case clearly we've got that. Then 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. I in my L inbox, I'm sure your guys are too. Like, 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. How do you pick? You get all these people reaching out, you know, there's good and mad. It's a really good question. I think it's like, how do we expand the foundation itself from a government standpoint? But also, like, technical contributions and how can the foundation best support them as well? That's like really tough in my mind. It's like the first thing we need to 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 a 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 develop as users and everyone. And very appreciably, and so are Disha Racting, is like, sort of a galvanizing rod for this, like, attention, all right. Brad, on the, sort of, block and goose side, it's an interesting, the involvement that you guys have had in the engagement that you guys have had. What was your calculus in joining the AIF? 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, like, download goose and use it in a way that you can download an age of SMD. Yeah, right, right, right. Like, what are those parts do together without having something that actually, like, connects it to clients, yeah, exactly, like a real client? And there's, I think, a lot of value in that because when you get into the code 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 spec for MCP, MCP apps that is brand new and we've been working on MCP UI. For goose? Yeah. So goose has been, like, kind of a day one partner with the MCP UI team. Oh, they don't know. And so now we've had MCP apps. We'll go, 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, what is the server sending an iframe to the client, like, do? And I think goose 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. Yeah, I think the other tidbit here, maybe look back to the history of both MCP and goose is like, goose was the first open source agent into phase or agent that reached out to us and worked with us to integrate MCP. And I think Radis actually, like, technically, the first non-entropic contributor to MCP ever on, like, day two or something like that, like, very, very early. So this goes all the way back to, like, November last year to, like, the partnership of having MCP inside goose. 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, like, a plug-in ecosystem who were like, this is awful. Like, why would you, why would anyone want to write? Yeah, why would anyone come develop a plug-in just for goose? But we saw all these opportunities. And so we started talking to Anthrophic. And we were like, I think that there's a space here for a protocol. And they're like, well, let me tell you about-- and it was really cool to see you know what this is. No, no, no, we didn't. We reached out before we heard the zet thing. And so we were like, OK, yes, we just want to-- 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 you're using it, you get more value as a client that is a server. Because your servers are going to work with any client that has a client, either 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 a science experiment. I've seen that or like, just like Google Docs or whatever. And I think that kind of shows you how MCP goes beyond just like the vet coding space. Yeah, I think as well. It's also the fact that it's concrete is so important. For all these standards, there's a long history of standards throughout computing that people proactively write a standard. And then when it's actually tried out, it has problems. But for MCP and all these new agentex standards we're coming with, we really want demonstrated utility. The most common thing on the core committee is like, as a proposal and we come back to people saying like, have you tried it out as a 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. So it's only with that sort of open ecosystem that you can meaningfully understand if this is actually a bit of work. I totally agree with that. I mean, I think the world of standards and open source development or disemerging right, you sort of could develop these things together. I think I was trying to figure out whether David is vent surf or Linus Torvalds for agents. And I think maybe it's a little more, it leads a little more vent surf and then maybe ghost is a little more Apache web server and my whole Linus 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. - Albany, I also has a coding agent that is open source. I think what's the thinking there apart from like, well, wouldn't codex ever be donated to AIF? Or we just don't know yet. - I think the short answer is we don't know yet, but like it's sort of like a feedback loop, which is in this open ecosystem, like we don't want to have too much alignment all on like one implementation, one thing. There's like real value to users and developers or whoever's the participant to like active competition in some parts. So there's this balance of like we need openness to foster like collaboration and experimentation, but like 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. This bit of like a taste making approach to like contribute things that benefit from being open. Like agents and days, an example, which is open up any GitHub repository, it has this file, it works the same way. Like if everyone sort of did their own thing there, that's very low value, potentially damaging to the way. 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 'cause that way we'll see what comes to the be the best. Is there a roadmap for why you want to add? For example, the agent to commerce protocol like judgeability over users, 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 kinda like going month by month in what are people using them? Why should we be in there? - I think we don't have a roadmap in the sense of like, projects lined up, but I think what we have is principles but which we will select products, I'm to some degree. And I think the effort here is mostly around sitting together after 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 they develop the foundation further as time goes. But in the moment, I think the most important part is that we have the principles in place and then going having a conversation with people who want to be part of this foundation. - One principle that really comes to mind to me is composability, like our thing is the analogy of like Lego blocks sort of thing, which is agentic systems are some of many, many parks. And so like something that I hope the foundation can evolve to do is have these interoperable, composable bits that will work together painfully. And so we don't have a roadmap of like feature contributions, but like I welcome all contributions that play nice with other contributions and like really create this potentially like a future flexible open agentech stack to be like not a universal agent but an agent that suits everyone's purpose or need. - Yeah, it's tricky, you get, it's a hard, and these guys have the harder job of early in innovation cycle. You don't want a restrict innovation by saying like, oh, well, this is the one versus that one. But you also don't wanna let every single random thing into an organization like this. And so I do think you need this at taste making is a good way to describe it, where a group of elite architects and developers, folks like the three people said next to me are more curating. And some things can work, some things might not, but there needs to be a process which I think will define to do that curation that happens to be a taste makers. And it's more of a, not just more, but essentially a technical effort not something where a committee of 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. - Which leads to this other principle that we really want projects that are have a little traction that are well maintained that are very, very healthy in the foundation. I think that's super important to us. - Right, 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 like kind of I really enjoy the like 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 can bring that back if it really has a role. - 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 to the foundation? - 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, you know, 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 Agente K.I Foundation, where the whole industry is making decisions about how to invest, and 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's a way that we can all essentially co-develop together. And that will provide better support, more development, plus 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, it gets great products in the market, market feedback, then, you know, allows companies to make money off of them. They then pay engineers to improve the project, better products, more profits, better project. And, you know, that's the incentive, which is pretty high one. - Co-ed out a technical sort of span, which is none of these things they built out of vacuum. Like all these projects build on lessons and learnings or practical code from other projects. And that's the 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 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's sort of the foundations, the natural like town square, but this in a way. - And 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. - I actually have a follow-up question on just the LF side. LF has many other funds and organizations, including data, data and AI foundation, as well as like dedicated like PyTorch and the other ones. I guess why a new foundation? - Because everyone's special. (laughing) No, I think that the way we look at in this space, I'll put aside the projects in semiconductor tech and operating system and stuff. But in AI, we think of it sort of like how the market has evolved. It started with tools like PyTorch and that's the transformative tech that is used to create LLMS. The Linux Foundation kind of took a pass on a frontier model world because in the open-source space, having connections to 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 reasoning models have come out, need to be 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. - Is that like you're from data in AI? - 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 working on transformer tech or VLLM. And so they are logical categories. I mean, sometimes stuff comes in over time and we sort things out later. We had early on in the telecommunications sector, a software-defined networking, effort, a network function virtualization, orchestration, effort, a whole bunch of stuff. All separate entities. And they, I was like, let's just bring all these things together because the technology's 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 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. - I think as well, doptails 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, learners. And ultimately, like you can imagine an alternative or we snowball on this only the Linux foundation as this Uber do everything remotely connected to a computer. And that wouldn't be that effective. So there's a taste-making here as well, which is wouldn't be focused on the genetic systems and how they connect together and the gender AI foundation. But like everything's about growth and evolution. So there's a possibility that later on the line, we recognize some natural affinity. There's something new, something old, and then they can be brought together. But the focus helps the beginning so. - What's gonna be the actionable outcomes? So obviously you have the funds to interact. I know a lot of the Linux foundation, those 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 that about the community building, and then from people that have not been involved from the outside, it's like, there just seems like a nice blog post and a bunch of blog posts, but like in reality, how are things gonna be actioned? - Yeah, I mean, 50 companies coming into fund a bunch of blog posts seems like overkill. - Right, exactly. - 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 the community is the one who makes the technical decisions, so kind of just, you know, sort of lead through influence to kind of help people organize things effectively. So 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, but 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 that 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 scuttle butter 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 that gets 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. - I put in that question into our doc because it says, this is a directed fund. So my cheeky question goes, well, what are you directing them to? - So, yeah, I mean, that's, it's kind of, that's a directed fund gets into like, they are doing the dirtiness of this, yeah. So, but it's, the reason we structure it that way is somebody has to own everything. 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 really care about this tech, put money in and using 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, tastemakers, that's something that we separate. - Yeah, I think there's a great essay by Rich Higee, who created Closure about open source, it's not about you. Just because something in open source, I don't know the respond to your issue into poor 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. I'm as opposed to also listening to your thing and implement the thing that you said. So, I think that's gonna 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 Labs 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 like, but there's stake and be like, yeah, we've contributed that or whatnot. So, I just think it's like a unique, compared to like the CNCF, for example, where the hyper scalers are kind of like around the clouds. And we all know what those workloads look like. And like, nobody's really trying to influence. There's not like an opening I prefer thing versus like an anthropic preferred thing. - But it wasn't always so. So when we started CNCF, I got a call from, I think it was Erzholz Solit and Varrain Stevens, who were over at Google at this 2014, I want to say. And, you know, they're competing, well, they weren't even competing. They weren't in the cloud business. And they wanted to be in that business. Amazon was 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 the Kubernetes to the Linux Foundation. And 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 Mezos was still a thing. Like Paz was still a thing, right? Like, you know, Hiraoku, 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 the 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 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, you know, investment is not mutually exclusive to great technical outcomes. I think it's been super positive. So I think this is going to move super fast. Awesome. We don't want to keep you guys too long. I'm sure you've been on a media to work this week. What's maybe from each of you like one thing you look forward in the new year from the foundation? So I don't really know what it's going to be looked like. That I really look forward to like the next step. Like as David mentioned, like it's being the moms of development and discussion or whatever to bring us to this. And this is sense of, I guess, relief achievement. It 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 that ends up taking. Because there's another world where like bodies and foundations are created and then like eventually they get forgotten. And this is not that. This is really a beginning. And so I want to say it be healthy and grow. And I just don't know what comes next. So I'm most excited to see that in the new year. Yeah, I think you're most excited. If I really take a new to look of like what just happened in the industry, it was creating this. It's like, you have Google Microsoft Amazon. Block, Bloomberg, Loudfair, OpenAI, Anthropic, just to plot the member of Creative Foundation. I think it's just like, this is actually quite cool and quite substantial. And now it's just like, now we have this like starting point of like, what can we do with this? And to next point, we don't, I think there's a lot of things we don't know yet and like things we need to figure out. Like for Anthropic, this is the first big foundation. We're creating and we have to learn a lot here. But I think it's just such an interesting like starting point. And I'm just super excited for these like new, when you start something new, like 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. Like I feel like quite unique vehicle now and like really driving the agenda AI, open source community forward and focusing on what we are. Some of these companies who are competitive with each other have coming ground and where we can build things together that is just benefiting and uplifting every user in the market and every developing the market, every building the market. The meaning that's what I'm really excited about to see. I definitely agree with both. I think there's a lot of like 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 like reading through chat sessions. And I want this to be a thing where I can go have like 20 agents working for me and actually see that come together. So I think that MCP is starting to like approach that answer and then we want to like figure out how to make those reference implementations and show people how they can actually get like another order of magnitude out of what AI can do for them. - You don't enjoy pressing yes every five. - The approved every three seconds. - Bypass, bypass. - Daniously skip permission - Yes, turn it all. - I'm with you on that one. I think what I look forward to is, you know, the success stories of, you know, the organization that's implemented, the agent technology in that way and hearing how it 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 in CNCF this year, CVS pharmacy joined the Cloud Native Computing Foundation, right? Like a, 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 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 is going to be cool. - Well, thank you all so much for joining and Congress on the launch. - It's a day, thank you. - Thanks for coming. (upbeat music)