The demo profiles a Go app running bubble sort and Fibonacci and the result renders as an interactive flame graph directly inside the VS Code chat window. Not a link. Not a text summary. A live iframe you can scroll and query, sandboxed for the same reason you put a hamster in a cage: so it cannot chew up your VS Code settings or call external APIs.

The mechanism: an MCP tool returns both data and a resource reference pointing to a bundled HTML UI. VS Code fetches the HTML and renders it in a sandboxed iframe in chat. The app calls back to the server, the server returns fresh data, the UI updates. Shopify uses this pattern for checkout flows inside chat. Excalidraw uses it for interactive architecture diagrams you can drag and edit. Marlene and Liam walk through building one from scratch using a skill from the MCP repository.

Speaker info:
- https://x.com/marlene_zw
- https://www.linkedin.com/in/marlenemhangami/
- https://github.com/marlenemhangami

- https://x.com/liamchampton
- https://www.linkedin.com/in/liam-conroy-hampton/
- https://github.com/liamchampton

AI Engineer

A conference talk from GitHub/Microsoft developer advocates introducing MCP Apps — a feature that lets MCP server tools return rich, interactive HTML UI components rendered inside sandboxed iframes directly within VS Code's chat window. The talk covers the MCP architecture (hosts, clients, servers), explains why plain-text responses were limiting, and demonstrates a live flame graph profiler built with Go pprof and a React frontend served via an MCP server. Use cases discussed include data exploration, e-commerce checkout flows, and diagram generation (Excalidraw, Figma). Companies like Shopify are highlighted as early adopters building branded in-chat experiences.

Building Interactive UIs in VS Code with MCP Apps — Marlene Mhangami & Liam Hampton, GitHub