# What are MCP Apps?

MCP Apps is an official MCP extension that lets a tool return an interactive interface, such as a form, chart or picker, that the AI app shows inside the conversation instead of plain text.

## How it works

A tool declares a UI resource with a `ui://` address. The resource is bundled HTML and JavaScript that the host app fetches and renders in a sandboxed iframe, talking to it over `postMessage`. Hosts can review the HTML before rendering and ask for your consent before the interface calls a tool.

## Where it works

The announcement on 26 January 2026 named Claude (web and desktop), Goose, Visual Studio Code (Insiders) and ChatGPT. Since the 2026-07-28 release, MCP Apps is one of the spec's formal extensions.

## Sources

Official documentation, checked on 19 November 2026:

- [MCP Apps (MCP blog, 26 January 2026)](https://blog.modelcontextprotocol.io/posts/2026-01-26-mcp-apps/)
- [The 2026-07-28 specification release (MCP blog)](https://blog.modelcontextprotocol.io/posts/2026-07-28/)

## Related terms

- [MCP](https://ai-powered.com/academy/glossary/mcp): MCP (Model Context Protocol) is an open standard for connecting AI applications to outside tools and data. An AI app connects to small programs called MCP servers, asks each one what it offers, and calls those tools when a task needs them.
- [Tool call](https://ai-powered.com/academy/glossary/tool-call): A tool call is a structured request from an AI model to run one of the functions it was given, with arguments that match the function's input schema. The app runs the function, sends the result back to the model, and the model uses it to answer or to decide its next step.
