MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef

频道: AI Engineer
视频: https://www.youtube.com/watch?v=-jY2T2PiJBE
原文语言: en
统计: 共 27 轮 · Ido Salomon 1 · Liad Yosef 1

[0:01]

[music]

[音乐]

[0:12] Ido Salomon

Hi. So, hi everyone. We built this talk yesterday, so it might be out of date. I'm Ido Sadan, I am the creator of MCPY and co-creator and maintainer of MCP apps in the MCP steering committee. I also created Adam Craft if you were in the talk yesterday.

大家好。这个演讲是我们昨天才赶出来的，所以内容可能已经过时了。我是 Ido Salomon，MCP UI 的创建者，也是 MCP steering committee 里 MCP Apps 的联合创建者和维护者。如果你昨天听了那场演讲的话，Adam Craft 也是我做的。

[0:30] Liad Yosef

I'm the Adi. I work with Ido on MCPY. I'm also the co-creator and maintainer of the MCP apps spec and recently co-founded Aura, which is a research lab for the agentic web. And we're going to talk a little bit more about it later.

我是 Liad。我和 Ido 一起做 MCP UI，同时也是 MCP Apps 规范的联合创建者和维护者。最近我还联合创办了 Aura，一个专门研究 agentic web 的研究实验室，这个后面会再多讲一点。

[0:45]

So, MCP apps are all around us. You might not even realize it, but all the fancy apps you have today in ChatGPT and VS Code and Slack are actually all based on MCP and the MCP app spec.

MCP Apps 其实已经无处不在了。你可能都没意识到，今天你在 ChatGPT、VS Code、Slack 里用到的那些花哨的 app，底层全都是基于 MCP 和 MCP Apps 规范做出来的。

[1:01]

And if we take a step back and we ask, why do we need MCP apps? What's the idea behind MCPY or MCP apps? So, when we work with chats, when we chat client clients, we used to text because that's the natural interface, but text is really the worst way to convey a lot of information, right? Because we don't want walls of text. And actually, this is the main blocker from companies to build an MCP server. They don't want to be reduced to a textual database. They don't want to lose their brand identity in the process. They don't want their data that they work so hard on um building the UX for to look something like this. So, instead of this, what if the apps could just send their UI to the chat, right? What if every service and every brand could just send their user interface to the chat? So, instead of us looking at something like this, we could just have the apps send their own identity, their own UI chunks into the chat, and then we take a look and we see, "Okay, yeah, I know this is Shopify in the middle. I know this is Hugging Face. I know this is Monday." And what if we don't want to do it only as a visualization? We also want to do it interactive. So, we want the users to be able to actually interact with Hugging Face, for example.

我们退一步问一句：为什么需要 MCP Apps？MCP UI 也好、MCP Apps 也好，背后的想法到底是什么？我们跟 chat client 打交道的时候，一直用的是文本，因为文本是最自然的界面。但要传递大量信息，文本其实是最糟糕的方式——谁都不想面对一整屏的文字墙。而这恰恰是企业不愿意做 MCP server 的头号阻力：他们不想被降级成一个纯文本数据库，不想在这个过程里丢掉自己的品牌识别，更不想让自己辛辛苦苦打磨 UX 的数据，最后呈现出来是这个样子。那么与其这样，如果 app 能直接把自己的 UI 发到 chat 里呢？如果每个服务、每个品牌都能把自己的用户界面直接发进 chat 呢？这样我们看到的就不是刚才那一坨东西，而是各家 app 把自己的身份、自己的那块 UI 片段送进 chat——我们一看就知道：哦，中间这块是 Shopify，这块是 Hugging Face，这块是 Monday。那如果我们不只想要展示呢？我们还想要可交互。比如说，我们希望用户能真的在里面跟 Hugging Face 交互。

[2:18]

And for Hugging Face to actually do something with it.

而 Hugging Face 那边也能真的对这个操作做出响应。

[2:22]

So, we don't have to imagine the future as we said with MCPUI, which I created in May last year, and took that, which is essentially like an open protocol for interactive applications over MCP. So, it's not only how you transmit UI, but also how that UI, that application connect connect communicates with the host. And just a few months ago, we partnered with Anthropic and OpenAI to create the official extension to MCP, which we call MCP apps based on MCPUI, MCP SDK, and other solutions in the field. Their launch was pretty cool with Claude and VS Code supporting it to begin with, but now obviously also OpenAI and others have adopted it.

所以这个未来我们不用靠想象——就像刚才说的 MCP UI，我去年 5 月做的，它本质上是一个跑在 MCP 之上、面向交互式应用的开放协议。它规定的不只是 UI 怎么传输，还包括这个 UI、这个应用怎么跟 host 通信。就在几个月前，我们和 Anthropic、OpenAI 一起，基于 MCP UI、MCP SDK 以及这个领域里的其他方案，做出了 MCP 的官方扩展，也就是我们说的 MCP Apps。发布的时候阵仗挺大，一上来 Claude 和 VS Code 就支持了，现在 OpenAI 和其他家显然也都跟上了。

[3:13]

Yeah, and there are a lot of early adopters to MCPUI. 11 Labs, Shopify, Postman. Those were one of the first first companies to support it back like a year ago. They were the one believing in this spec, in this vision. And Goose also supported it. And it's a it's a funny anecdote because today Block released their agentic commerce solution that is based on MCP apps. So, a year ago Goose was the first client to support MCPUI, and now it is part of Block's product uh product. And today we have a lot more clients that are supporting MCPUI. We We Cursor, and we have co-pilot and GitHub ChatGPT support MCP apps. ChatGPT apps that you know are actually based on MCP apps and open eye actually recommend using MCP apps as the protocol to build ChatGPT apps. Postman and a lot more and obviously Cloud supports MCP apps. But we also have a lot large community around it, right? So people start to to build plugins to MCP apps and um integrations to different agents and also courses on how to build MCP apps. This is by integration for MCP apps. So we have a lot community around it. Um There's a repo X app which is the repo for MCP apps where everyone can just come and propose PRs and ideas of how to how to extend this spec and we have a work group in the MCP committee and we're convening every 3 weeks. We have a tri-weekly meeting on the future of the protocol and how to make the spec not just serve the bigger apps but also the community. So it's an open working group with Anthropic, Open AI and all the partners in in the MCP apps protocol.

MCP UI 也有一批很早的采用者：ElevenLabs、Shopify、Postman，这几家差不多一年前就是最早支持的一批公司了，是他们最先相信这份规范、相信这个愿景的。Goose 当时也支持了。这里有个挺有意思的花絮：就在今天，Block 发布了他们基于 MCP Apps 的 agentic commerce 方案。一年前 Goose 是第一个支持 MCP UI 的 client，而今天它已经成了 Block 产品的一部分。现在支持 MCP UI 的 client 就多得多了：有 Cursor，有 Copilot、GitHub，ChatGPT 也支持 MCP Apps。你们知道的 ChatGPT Apps 其实就是基于 MCP Apps 做的，而且 OpenAI 官方就推荐用 MCP Apps 这个协议来做 ChatGPT Apps。还有 Postman 等等一大堆，Claude 当然也支持 MCP Apps。除此之外，围绕它还长出了一个很大的社区——大家开始给 MCP Apps 写插件，给各种 agent 做集成，还有人开了怎么做 MCP Apps 的课程，这个就是给 MCP Apps 做的一个集成。所以社区非常热闹。MCP Apps 有一个公开仓库，任何人都可以过来提 PR、提想法，讨论这份规范该怎么扩展；我们在 MCP 委员会下面还有一个工作组，每三周开一次会，讨论协议的未来，讨论怎么让这份规范不只服务大厂的 app，也服务社区。这是一个开放的工作组，Anthropic、OpenAI 以及 MCP Apps 协议的所有合作方都在里面。

[4:58]

Okay, so let's look at a few of the core concepts of MCP apps. The first and most obvious one is how do we even transmit UI over MCP? So if we look at this example of Cloud like you know agent times like a few months ago and I would ask something best case scenario it would reach out to my MCP server and it would get back a textual response which is obviously suboptimal. So let's say I do want to get some something better. So now I can use existing MCP primitives like a resource and now return HTML. And I can take that HTML and since Cloud supports MCP apps it can turn it into an interactive application of the best soundtrack in the world. And what if you wanted to be really interactive, right? This is nice because it shows the best soundtrack in the world. What if I want to favorite one of the songs there? I want interaction. I want communication between the app and the host. So, when the user clicks on the favorite button, MCP apps actually standardizes this flow. So, instead of the app sending a message to to the backend, to Spotify's backend, it's actually sending a message to the host saying, "Hey, user clicked a button. Do something with it. I recommend you to call a tool in Spotify's MCP server." And the host decides what to do. The host keeps this control of the flow. In this case, the host can decide to actually call the favorite favorite tool. And MCP apps standardizes this flow.

好，我们来看几个 MCP Apps 的核心概念。第一个也是最直白的一个：UI 到底是怎么在 MCP 上传输的？看这个 Claude 的例子——就是几个月前那个 agent 阶段——我问一个问题，最理想的情况是它去调我的 MCP server，然后拿回一段纯文本响应，这显然不够好。那假设我想要更好的东西，现在我就可以用 MCP 已有的原语，比如 resource，让它返回 HTML。因为 Claude 支持 MCP Apps，它就能把这段 HTML 变成一个可交互的应用——世界上最好的原声带。那如果你想要真正的交互呢？现在这个界面挺好，它把世界上最好的原声带展示出来了，但如果我想给里面某首歌点个收藏呢？我要的是交互，是 app 和 host 之间的通信。所以当用户点下收藏按钮时，MCP Apps 把这条链路标准化了：app 不是直接给自己的后端、给 Spotify 的后端发消息，而是给 host 发一条消息，说『嘿，用户点了个按钮，你处理一下，我建议你去调 Spotify MCP server 里的某个 tool』。然后由 host 决定怎么做——host 始终掌握着流程的控制权。在这个例子里，host 可以决定真的去调那个 favorite tool。MCP Apps 标准化的就是这条链路。

[6:35]

Okay, so seeing is believing. So, let's see an example from Claude. Yeah. Uh so, let's say that I'm a product manager to understand the status of my funnel. So, I would go to Claude and I would ask what's the status? In the again, old world of a few months ago, uh I would get back the textual response. Let's say that it's PostHog. So, it reached out to the PostHog server, got back the textual response. It's factually correct, but it's useless. I mean, how do I even take that and understand quickly what's going on? I would have to read, which I don't want to do. Uh and it's pretty challenging. Uh but luckily, because both PostHog server and Claude as a host support MCP apps, I can just say, "Show me." And now, instead of getting that block of text, I can actually get something useful, uh which is this interactive um widget that you would get, you know, on the PostHog uh uh server. And when you have that, you can at a glance see what's going on. And as you can see, it's branded PostHog. So, you're actually getting the PostHog experience within ChatGPT or Claude, etc. Uh but it doesn't really end there. As we said, MCP apps is also like an interactive photo call. So, not only can I see and and interact with it, I can also do stuff like ask him to explain what a funnel is. I might not even know that. So, again, instead of getting that huge wall of text explaining what a funnel is, I can just get this generative UI answer from Claude, which uses MCP apps. It streams like the HTML inside, and now I can get this nice interactive experience of learning.

眼见为实，我们看一个 Claude 上的实际例子。假设我是个产品经理，想搞清楚我的漏斗现在是什么状况。我去问 Claude：现在情况怎么样？在几个月前那个旧世界里，我拿回来的是一段纯文本。就说是 PostHog 吧——它调了 PostHog 的 server，拿回一段文字。这段文字事实上没错，但没用。我拿着它怎么快速看出到底发生了什么？我得一行行读，可我不想读，而且读起来也挺费劲。好在 PostHog 的 server 和作为 host 的 Claude 都支持 MCP Apps，所以我可以直接说一句：给我看看。这时候我拿到的就不是那一大段文字，而是真正有用的东西——一个可交互的 widget，就是你在 PostHog 上会看到的那种。有了它，你一眼就能看出发生了什么。而且你能看到它是带 PostHog 品牌样式的——你其实是在 ChatGPT、Claude 这些地方里获得了 PostHog 的体验。但事情还没完。刚才说了，MCP Apps 同时也是一个交互协议。所以我不光能看、能点，我还可以让它解释一下什么叫漏斗——我可能压根就不知道。这时候我拿到的也不是解释漏斗的一大堵文字墙，而是 Claude 用 MCP Apps 生成的 generative UI 回答：HTML 是流式渲染出来的，我就得到了一个很舒服的、可交互的学习体验。

[8:15]

And not only is it visually nice and helps me understand, but it's also fully interactive. And when we say interactive, it actually means that clicking it would help me communicate with the host. So, let's say that I want to understand like a particular step in the funnel. Uh I just go and I click on it, and since it's an MCP app, it can send a prompt back to the uh model and say, "Okay, explain this specific step to me." And I can advance the flow. Uh so, this is a like an example of of how that uh looks. So, how does it actually work? If you look at the architecture of it, uh so, we started by prompting. So, we type something in. Uh we asked for the funnel information. A tool call went out. Since our server supports MCP apps, that tool call is actually linked to a resource. And if you look at the uh code here, then, you know, it's it's a it's just a resource with a uh some prefix. Uh we take that. It's pretty simple code. I could just add the but it's still the the resource with the HTML, and you're done. Uh that resource is then um consumed by the host. In practice, it's usually consumed beforehand, like it's preloaded. Uh but imagine that it's just consumed in real time. That same HTML then passed to the host that also supports MCP apps. MCP apps basically if you look at the MCP UI SDK, just a React component or a web component that just accepts that resource plus a callback which is how we implement that communication protocol as I said earlier.

它不光好看、帮我理解，而且是完全可交互的。我们说可交互，意思是点它就能跟 host 通信。比如我想搞清楚漏斗里某一步是怎么回事，我点一下，因为它是个 MCP app，它可以把一条 prompt 送回模型，说『给我解释一下这一步』，这样流程就往前推进了。这大概就是它的样子。那它到底是怎么跑起来的？看一下架构：一开始是 prompt，我们输入内容，问漏斗的情况；然后发出一个 tool call。因为我们的 server 支持 MCP Apps，这个 tool call 实际上是关联到一个 resource 的。你看这里的代码，其实就是一个带特定前缀的 resource，代码非常简单——就是那个装着 HTML 的 resource，齐活了。这个 resource 接着被 host 消费。实际工程里通常是提前消费的，也就是预加载，但你就当它是实时消费的。然后同样这段 HTML 被交给同样支持 MCP Apps 的 host。所谓 MCP Apps，你去看 MCP UI SDK 就知道，其实就是一个 React component 或者 web component，它接收那个 resource，再加一个 callback——这个 callback 就是我们刚才说的那套通信协议的实现方式。

[9:51]

And renders it in a sandbox. So, like we said, not only is it presentational, I can click. So, what happens when I click? So, we click on it, it sends back through that callback the event all the way up. The model takes that event and then it can send out a tool call or call a resource or anything else that's completing the agentic flow.

然后把它渲染在一个 sandbox 里。就像刚才说的，它不只是展示用的，我还能点。那点下去会发生什么？我们一点，事件就通过那个 callback 一路往上传。模型接到这个事件，就可以发出一个 tool call、去调一个 resource，或者做任何别的事情，把整个 agentic loop 走完。

[10:14]

And this architecture actually brings a new philosophy or a new vision to the web. So, instead of us thinking of the web as tabs or services that we need to consume using a browser, we're now consuming it using our own personal assistants, right? What does it mean? It means that if I want to accomplish a task, for example, plan a um anniversary. So, up until now I had to open 20 tabs in the browser and I had to try to convey my intent to each of those services. And by saying conveying my intent, it means that I have to interact with the dashboards or the UIs of those companies. So, just to plan an anniversary, I need to convey my intent to Google Calendar and Amazon and Booking and Booking again and Amazon again and all and I don't need 99% of the UI that is shown there because this UI doesn't know me. It doesn't have the context on me. What if we could just take these UIs and just break them into atoms? And those atoms can be composed by my own personal assistant, right? Because I don't need the the UI. I need those atoms. So, if we can take these atoms and have my cloud or ChatGPT or OpenCloud just use them using MCP UI, we can have this flow. So, my proactive assistant can say, "Yeah, I know. I see that you have an anniversary coming and instead of just showing me data from Google Calendar, it can display a Google Calendar chunk. Now, for me it's good because I know Google Calendar, I trust Google. For Google it's good because it maintains their brand and identity and for the host it's good because they don't need to develop these capability themselves. And it goes even deeper because if I'm interacting with Amazon, instead of Amazon being reduced to just a list of items or or text, I can see Amazon. I can I can know that this is this is Amazon and I can complete my entire flow without even leaving my assistant. And this is the agentic web. This is how we're going to consume the web because my assistant

这套架构其实给 web 带来了一种新的哲学、一种新的想象。以前我们理解的 web，是一堆需要用浏览器去消费的标签页和服务；而现在，我们是通过自己的私人助理来消费它。这意味着什么？意味着如果我要完成一件事，比如安排一个纪念日，放在以前我得在浏览器里开 20 个标签页，然后挨个向这些服务表达我的意图。所谓表达意图，就是我得去操作这些公司的 dashboard 和 UI。就为了安排一个纪念日，我得向 Google Calendar 表达一遍意图，再向 Amazon 表达一遍，再向 Booking，再回到 Booking，再回到 Amazon……而且那些界面上 99% 的东西我根本用不着，因为这些 UI 不认识我，它没有关于我的 context。那如果我们能把这些 UI 拆成一个个原子呢？这些原子可以由我自己的私人助理来组合——因为我要的不是整个 UI，我要的就是那几个原子。如果我们能把这些原子拿出来，让我的 Claude、ChatGPT 或者开源客户端通过 MCP UI 直接用起来，就能得到这样的流程：我的助理会主动说『我看到你有个纪念日快到了』，而且它不是干巴巴地把 Google Calendar 的数据念给我听，而是直接渲染出一块 Google Calendar 的界面。这对我好，因为我认识 Google Calendar，我信任 Google；对 Google 也好，因为它的品牌和识别度保住了；对 host 也好，因为这些能力它不用自己再开发一遍。而且还能更进一步：我跟 Amazon 交互的时候，Amazon 不再被降级成一串商品列表或者一段文字，我看到的就是 Amazon，我知道这是 Amazon，我整个流程都不用离开助理就能走完。这就是 agentic web，这就是我们以后消费 web 的方式——因为我的助理

[12:11]

will have the context on me. It It will know to pull the the map from booking.com. I don't need to know that, right? So, this is going to be the shift that we're going to see very soon where websites are going to shift into small chunks of UIs inside inside personal assistants. Um [snorts] and with that come new interaction mindset because um if I click on something in the Shopify's MCP app, then Shopify doesn't control my journey anymore. The host does. Um and no application will control the user journey anymore. So, Amazon won't be able to know to see my flow. It everything will go through the chat for auditability. Um and MCP apps actually standardizes it by defining this three level of control over the user journey. So, an app can notify the chat that something happened or an app can actually ask the chat to run a prompt and and releasing all responsibility to the chat. So, MCP apps actually standardizes it and this is the new software flow, the new flow of interaction that we're going to see between applications, the chats, and the users. Um in 2026, we had we had an amazing year of standardizing MCP UI and 2026 is going to be the year where it's going to be a global standard for UI.

会掌握关于我的 context。它知道该去 booking.com 把那张地图拉过来，这些我不需要自己操心。所以我们很快就会看到这个转变：网站会碎成一块块小的 UI 片段，长在个人助理里面。伴随而来的还有一种新的交互心态：如果我在 Shopify 的 MCP app 里点了什么，掌控我这段旅程的就不再是 Shopify 了，而是 host。以后没有哪个应用还能控制用户旅程——Amazon 没法再看到我的完整路径，所有东西都要经过 chat，因此是可审计的。MCP Apps 把这件事也标准化了：它定义了对用户旅程的三个层级的控制权。一个 app 可以只是通知 chat『发生了某件事』；也可以直接请求 chat 去跑一条 prompt，把责任全部交出去。所以 MCP Apps 把这套东西标准化了，这就是新的软件流程，是以后应用、chat 和用户之间会出现的新的交互方式。2025 年我们用了一整年把 MCP UI 标准化，而 2026 年将会是它成为全球 UI 标准的一年。

[13:23]

Yeah.

是的。

[13:23]

But, it's still evolving. There's a lot of stuff going on. Even in these past few months, these are some of the things that are already in or already contributed or proposed uh, by the community. Uh, so you still have a lot of time and a lot of room to influence how this future will look like. Uh, so you can go to X apps. Uh, that's the official SDK and spec is also hosted there. It's under the official model context protocol uh, repository. There will be a QR code later. Uh, so you don't have to uh, to uh, photograph it. Uh, and also um, the the cool thing about using X apps in particular is that because it's maintained by us directly, uh, all changes to the spec are immediately uh, reflected in the SDK. So, if you use that SDK, then you automatically get all the new stuff out of the back. Uh, these are some of the issues that we have. So, please feel free to come and uh, contribute. So, what's next? Um, there's a bunch of stuff coming up. Uh, the first thing uh, that we get a lot of uh, uh, of asked for is kind of reusable views. So, if you have uh, um, companies like Autodesk that have really heavy apps like they have in, you know, the entire 3D render there. They don't want to keep re-rendering that over and over again because it just it takes time, it's inefficient. Uh, that is the way that we had to do it uh, for the MVP. But we are working on thinking of maybe we can pass some identifier from the server uh, in a way that would help the model actually keep updating the same view.

不过它还在演进，还有很多事情在发生。光是过去这几个月，屏幕上这些就是已经进了规范、或者已经由社区贡献、提案的东西。所以你还有很多时间、很大的空间去影响这个未来长成什么样。你可以去 MCP Apps 的仓库，官方 SDK 和规范都托管在那儿，就在官方的 model context protocol 仓库底下。后面会有二维码，所以你现在不用急着拍照。另外，用这套官方 SDK 有个特别的好处：因为它是我们自己直接维护的，规范一有改动就会立刻反映到 SDK 里。所以你只要用这个 SDK，新东西就自动到手了。这些是我们现在挂着的一些 issue，欢迎大家来贡献。那接下来会有什么？有一堆东西在路上。第一件被问得最多的，是可复用的 view。比如像 Autodesk 这种公司，他们的 app 很重，整个 3D 渲染都塞在里面，他们不想每次都把那个东西重新渲染一遍，因为又慢又低效。MVP 阶段我们只能这么做，但我们正在琢磨：也许可以让 server 传一个标识符过来，让模型能一直更新同一个 view。

[14:56]

Uh, the other way to do this is

另一条路子是——

[14:59]

Um, app tools, which is something uh, if you've heard of web MCP, which is Google standard of how agents will interact in with web views. So, in MCP us, we actually standardize it into app tools. So, up until now we saw the flow where users does something in the app and the app talks to the host. But what if the host or the chat wants to speak to the app? If the user writes something, uh, fill out this form for me and the chat will fill out the form for the user. So, MCP apps actually standardizes this this flow which we call view tools. That's actually that's in the spec right now. It's also it's going to be released very soon. And we're working on this generative UI spectrum where you have predefined UI. That's MCP apps. That's like the black box iframe that renders all trace UI in that example. But you also have other things on this spectrum like declarative UI like JSON render or A2UI. These specs that say yeah, the the app just returns an instructions on how to build the UI, but the chat will actually build the UI. And you have fully generative UI on the other end of the spectrum. And if you know cloud apps, yeah, MCP apps is agnostic to the way the UI is generated. And if you know cloud apps imagine feature where you can just ask cloud to generate a UI for you.

app tools。如果你听说过 WebMCP——Google 那套关于 agent 怎么跟 web view 交互的标准——我们在 MCP Apps 里把它标准化成了 app tools。到目前为止，我们看到的都是这个方向：用户在 app 里做点什么，app 去跟 host 说话。但反过来呢？如果 host、也就是 chat 想跟 app 说话呢？比如用户说『帮我把这个表单填了』，然后 chat 替用户把表单填好。MCP Apps 把这条链路也标准化了，我们把它叫做 view tools，现在已经写进规范了，很快就会正式发布。另外我们还在做一个 generative UI 的谱系：一端是预定义好的 UI，那就是 MCP Apps——像个黑盒 iframe，在刚才那个例子里渲染的就是 Autodesk 的 UI。但这条谱系上还有别的东西，比如声明式 UI，像 JSON render 或者 A2UI 这类规范——app 只返回一份『UI 该怎么搭』的说明，真正把 UI 搭出来的是 chat。谱系的另一端则是完全生成式的 UI。MCP Apps 对 UI 是怎么生成出来的这件事是不关心、不绑定的。如果你用过 Claude Apps，想想 Imagine 那个功能——你可以直接让 Claude 帮你生成一个 UI。

[16:12]

That's actually based on MCP apps. So, this is an MCP app behind the scenes, but it supports generative UI. So, we're working on interoperability with those other standards. And actually just a few days ago we released a guide on how to do A2UI versus a generative UI standard and MCP apps which is the standard. How to do interoperability. How can a server can write A2UI and ship it to Gemini, but also wrap it as an MCP app to ship to ChatGPT and vice versa. An MCP app is supported everywhere. So, it can run everywhere. If you build it once, it runs in Libra Chat which is an open source MCP app supported in ChatGPT. That's the same app that you're seeing the same code base that runs in in both which is pretty cool. Yeah. Yeah.

那个功能其实就是基于 MCP Apps 做的。所以它背后是一个 MCP app，但它支持 generative UI。所以我们也在做和这些别的标准之间的互操作。就在几天前，我们还发了一份指南，讲怎么在 A2UI（生成式 UI 那套标准）和 MCP Apps（这套标准）之间做互操作：一个 server 怎么写一份 A2UI 发给 Gemini，同时又把它包成一个 MCP app 发给 ChatGPT，反过来也一样。MCP app 是到处都被支持的，所以它到哪儿都能跑。你只要写一次，它既能跑在 LibreChat——一个支持 MCP app 的开源客户端——上，也能跑在 ChatGPT 里。你看到的是同一个 app、同一套代码库在两边跑，这挺酷的。

[17:01]

So, this isn't just a technology or a cool feature. This is an entirely new way to distribute applications. So, if you look just a few months back then someone said that ChatGPT in particular has 800 million weekly users which is 10% of the entire world population. That's insane. So, if you think about the web in general, it took around 13 years to get to that number of users. So, if you look at that and you think that in the last few months we actually had a growth of over 1 billion. Just that we have like 170 times the total addressable market of the Apple App Store when it launched. So, MCP apps are everywhere. So, actually to list them, it is called cloud, open AI, etc. It's already there. So, how do you get started? You can clone those you can go to the X apps. As a host also go to X apps or the MCP website.

所以这不只是一项技术，也不只是一个很酷的功能，这是一种全新的应用分发方式。往回看几个月，有人说光是 ChatGPT 就有 8 亿周活用户，那是全球人口的 10%，太夸张了。你想想整个 web，大概花了 13 年才做到这个用户量。再看看最近这几个月，我们的增长其实已经超过了 10 亿。光这一点，就相当于 Apple App Store 刚上线时可触达市场的 170 倍。所以 MCP Apps 已经无处不在了。真要列的话——Claude、OpenAI 等等，都已经支持了。那怎么开始？你可以直接把这些 clone 下来，去 MCP Apps 的仓库；如果你是做 host 的，同样去 MCP Apps 仓库，或者 MCP 官网。

[17:59]

Please visit the official repo.

欢迎大家去官方仓库看看。

[18:01]

[laughter]

[laughter]

[18:01]

The X apps repo to get involved. And yeah.

去 X apps 那个 repo 就能参与进来。差不多就这些。

[18:05]

So, embrace the new web. It's awesome. With MCP apps you can write once and run it everywhere. And the future is looking bright. Not quite Travis, but with MCP and MCP apps we're close.

所以，拥抱这个新的 web 吧，它真的很棒。有了 MCP apps，你只要写一次，就能到处跑。未来一片光明。虽然还没到 Travis 那种程度，但有了 MCP 和 MCP apps，我们已经很接近了。

[18:17]

And come talk to us afterwards.

散场之后欢迎来找我们聊。

[18:18]

Yeah, thank you.

好，谢谢大家。

[18:36]

[music]

[music]