Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

FastMCP 3.2 is out with full MCP Apps support. Create interactive tools, replace your team's dashboards, and use your MCP server as a complete backend for your app. You can even let agents generate UIs on the fly:

Jeremiah Lowin

12,976 subscribers

15,594 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Jeremiah Lowin6 months ago

FastMCP 3.2: Show, Don't Tool

Ido Salomon6 months ago

So cool

Michael Grinich6 months ago

great ship

Boston6 months ago

This is amazing @jlowin. Is it possible to persist these views? I'm thinking of where users can create their own persisted live dashboards? Or do they need to re generate every time?

Jeremiah Lowin6 months ago

MCP Apps are bound to the conversation, but Prefab apps (the UI framework) can be run totally independently -

tharshan6 months ago

If we already use a FastAPI server, can we run a FastMCP sever on a route?

Jeremiah Lowin6 months ago

Yup:

ST24 🖥️6 months ago

This is amazing

Rohit Ganguly6 months ago

hell yeah

StartupHub.ai6 months ago

Submit your startup or investor profile now via MCP on 🦸‍♂️

Related Videos

Ship your API to every MCP client in minutes 🚢 Upload your OpenAPI spec to Stainless → Generate an MCP Server → Your users can access your API in Claude Code Community, Cursor, and VS Code Watch me use the Replicate MCP Server to create a logo for my upcoming AI Podcast Generator, all with a single prompt! Now any MCP client can generate images and videos directly

Adam Anzuoni

22,423 views • 1 year ago

Your dev experience now has full MCP support Use the the Shopify Dev MCP server to set up, code, and validate your app Demo with Darius Gai

Your dev experience now has full MCP support Use the the Shopify Dev MCP server to set up, code, and validate your app Demo with Darius Gai

Shopify Developers

23,238 views • 10 months ago

Introducing the Conductor MCP! Your Claude, Codex, Cursor agents can now use Conductor alongside your humans. It comes with all the tools your agents need to create and manage cloud sessions. ```get-started.txt Add the Conductor MCP at and and authenticate with OAuth. ```

Introducing the Conductor MCP! Your Claude, Codex, Cursor agents can now use Conductor alongside your humans. It comes with all the tools your agents need to create and manage cloud sessions. ```get-started.txt Add the Conductor MCP at and and authenticate with OAuth. ```

Charlie Holtz

23,871 views • 2 months ago

Anthropic released interactive apps for Claude. Interactive apps can respond with interactive UI Widgets to enable additional usecases. "MCP Apps is a new extension to MCP that lets any MCP server deliver an interactive interface within any supporting AI product"

Anthropic released interactive apps for Claude. Interactive apps can respond with interactive UI Widgets to enable additional usecases. "MCP Apps is a new extension to MCP that lets any MCP server deliver an interactive interface within any supporting AI product"

🚨 AI News | TestingCatalog

52,554 views • 9 months ago

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 views • 1 year ago

Analyzing your marketing data just became easier with Datagran. Use Claude, Replit, Cursor or any other platform that supports MCP to query your ad insights and create apps or dashboards. To start using it, just add our MCP URL which you can find on our website.

Analyzing your marketing data just became easier with Datagran. Use Claude, Replit, Cursor or any other platform that supports MCP to query your ad insights and create apps or dashboards. To start using it, just add our MCP URL which you can find on our website.

Carlos Mendez

188,283 views • 10 months ago

AI Agents can now run your channels for you Grow and scale your channels, without the extra workload Connect your favorite tools, MCP servers, and workflows. Let your agents handle the rest Live now

AI Agents can now run your channels for you Grow and scale your channels, without the extra workload Connect your favorite tools, MCP servers, and workflows. Let your agents handle the rest Live now

robin

86,308 views • 8 days ago

The Stripe MCP server is now available in Notion Custom Agents. Your agent can now create customers, generate payment links, and fetch Stripe details - right inside your docs. Try the template →

The Stripe MCP server is now available in Notion Custom Agents. Your agent can now create customers, generate payment links, and fetch Stripe details - right inside your docs. Try the template →

Stripe Developers

22,143 views • 8 months ago

⚡day 5 of launch week: from (zero) MCP server to ChatGPT app this is peak developer experience 🤌🏼 1. define your UI in a single react file. 2. test it instantly with hot reload in the built-in Inspector 3. deploy it in one click on mcp-use Cloud 4. ship it directly to ChatGPT with: npx create-mcp-use-app@latest my-server --template apps-sdk you can go from zero to a deployed mcp server with apps sdk widgets in just 5 minutes here's how 🧵

⚡day 5 of launch week: from (zero) MCP server to ChatGPT app this is peak developer experience 🤌🏼 1. define your UI in a single react file. 2. test it instantly with hot reload in the built-in Inspector 3. deploy it in one click on mcp-use Cloud 4. ship it directly to ChatGPT with: npx create-mcp-use-app@latest my-server --template apps-sdk you can go from zero to a deployed mcp server with apps sdk widgets in just 5 minutes here's how 🧵

pederzh

22,647 views • 1 year ago

MCP tools have only ever returned text for the model to read. Now they return interactive UI. 🪄 TanStack AI's new MCP Apps support renders ui:// widgets right in the chat - static or fully interactive, with a client/server bridge.

MCP tools have only ever returned text for the model to read. Now they return interactive UI. 🪄 TanStack AI's new MCP Apps support renders ui:// widgets right in the chat - static or fully interactive, with a client/server bridge.

TANSTACK

133,087 views • 4 months ago

Deciding between A2UI and MCP Apps for your agentic interfaces? You don't have to choose 💫 This guide breaks down 3 architectural patterns for combining the best of declarative and custom UIs, including how A2UI and MCP Apps can seamlessly interact with each other.

Deciding between A2UI and MCP Apps for your agentic interfaces? You don't have to choose 💫 This guide breaks down 3 architectural patterns for combining the best of declarative and custom UIs, including how A2UI and MCP Apps can seamlessly interact with each other.

Flutter

20,344 views • 3 months ago

OpenAI just dropped the Apps SDK, built on MCP. This is the future of how users will interact with your apps. You won’t need to build a chatbot anymore. OpenAI is the chatbot. You just expose your tools through MCP. Exciting progress toward Jarvis!

OpenAI just dropped the Apps SDK, built on MCP. This is the future of how users will interact with your apps. You won’t need to build a chatbot anymore. OpenAI is the chatbot. You just expose your tools through MCP. Exciting progress toward Jarvis!

Kent C. Dodds 🏹

152,179 views • 1 year ago

I'm still picking my jaw off the floor with this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:

I'm still picking my jaw off the floor with this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:

Santiago

215,882 views • 1 year ago

Did you know you can expose your Flutter app as a MCP server? 👀 Here is Google Antigravity controlling the running app! 💙

Did you know you can expose your Flutter app as a MCP server? 👀 Here is Google Antigravity controlling the running app! 💙

Rody Davis

16,955 views • 9 months ago

Building a Crypto Wallet MCP server to integrate with AI tools? ⚙️🤖 Don’t leave your private keys exposed on local setups. With Phala Cloud & NEAR Protocol MCP, you can deploy your Wallet MCP server inside a TEE—secure, verifiable, and easy to launch. Here’s how 🧵

Building a Crypto Wallet MCP server to integrate with AI tools? ⚙️🤖 Don’t leave your private keys exposed on local setups. With Phala Cloud & NEAR Protocol MCP, you can deploy your Wallet MCP server inside a TEE—secure, verifiable, and easy to launch. Here’s how 🧵

Phala

21,706 views • 1 year ago

OpenAI, Anthropic and Microsoft all back the same standard for running apps inside AI chats. Booking .com, Figma, and Canva are already using it. Still, most developers have never heard of it. It's called MCP Apps. So, why does it matter? The next time someone buys from your website, they may never visit it. They'll ask ChatGPT or Claude, and the model decides how your product shows up. Usually as plain text, sometimes wrong, with none of the experience you built. That's the next shift in how people find you: - SEO was about Google finding your page. - AEO was about AI citing you. - MCP Apps are about your actual product showing up inside the chat. An MCP server returns data. An MCP App returns data plus an interactive UI, like hotel cards or an add-to-cart flow, right inside the chat. The model even knows what the user clicked. In this episode, we build an MCP app from start to finish with Julien, the lead maintainer of Skybridge, an open-source framework that lets you turn any React app into an MCP app. Chapters: 0:00 - Intro 2:44 - MCP servers vs MCP Apps 5:12 - Live demo: Booking .com in ChatGPT 9:24 - How MCP Apps work: context and shared state 15:43 - Skybridge and its devtools 17:48 - Live demo: an e-commerce app in ChatGPT 24:49 - Code walkthrough: MCP tools to React views 28:10 - Syncing UI state: "What's in my cart?" 32:16 - Agent skill to turn any React app → MCP App 37:52 - Outro Link to Skybridge GitHub repo: MCP Apps bring your website into the chat. WebMCP does the reverse and lets AI agents use your website through tools it exposes. I've also written a full article on it, quoted below.

OpenAI, Anthropic and Microsoft all back the same standard for running apps inside AI chats. Booking .com, Figma, and Canva are already using it. Still, most developers have never heard of it. It's called MCP Apps. So, why does it matter? The next time someone buys from your website, they may never visit it. They'll ask ChatGPT or Claude, and the model decides how your product shows up. Usually as plain text, sometimes wrong, with none of the experience you built. That's the next shift in how people find you: - SEO was about Google finding your page. - AEO was about AI citing you. - MCP Apps are about your actual product showing up inside the chat. An MCP server returns data. An MCP App returns data plus an interactive UI, like hotel cards or an add-to-cart flow, right inside the chat. The model even knows what the user clicked. In this episode, we build an MCP app from start to finish with Julien, the lead maintainer of Skybridge, an open-source framework that lets you turn any React app into an MCP app. Chapters: 0:00 - Intro 2:44 - MCP servers vs MCP Apps 5:12 - Live demo: Booking .com in ChatGPT 9:24 - How MCP Apps work: context and shared state 15:43 - Skybridge and its devtools 17:48 - Live demo: an e-commerce app in ChatGPT 24:49 - Code walkthrough: MCP tools to React views 28:10 - Syncing UI state: "What's in my cart?" 32:16 - Agent skill to turn any React app → MCP App 37:52 - Outro Link to Skybridge GitHub repo: MCP Apps bring your website into the chat. WebMCP does the reverse and lets AI agents use your website through tools it exposes. I've also written a full article on it, quoted below.

Akshay 🚀

18,064 views • 24 days ago

Introducing the official Supabase MCP Server! Supabase MCP Server allows you to read and write to your database, create new projects, apply migrations, and more, right from your favorite AI tools! You can start using them in Cursor or Windsurf today!

Introducing the official Supabase MCP Server! Supabase MCP Server allows you to read and write to your database, create new projects, apply migrations, and more, right from your favorite AI tools! You can start using them in Cursor or Windsurf today!

Supabase

193,350 views • 1 year ago

Google has released its own MCP server for Stitch, which can be used to generate UI designs on the fly and fetch code directly from your IDE.

Google has released its own MCP server for Stitch, which can be used to generate UI designs on the fly and fetch code directly from your IDE.

🚨 AI News | TestingCatalog

110,726 views • 9 months ago