dianed-square
3.0 KiB
sidebar_position, title, sidebar_label, description
| sidebar_position | title | sidebar_label | description |
|---|---|---|---|
| 1 | MCP-UI Extensions | MCP-UI Extensions | Learn how Goose can render graphical and interactive UI components from MCP-UI-enabled extensions |
import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; import GooseDesktopInstaller from '@site/src/components/GooseDesktopInstaller'; import CLIExtensionInstructions from '@site/src/components/CLIExtensionInstructions'; import { PanelLeft } from 'lucide-react';
Extensions built on MCP-UI allow Goose Desktop to provide interactive and engaging user experiences. Imagine using a graphical, clickable UI instead of reading text responses and typing all your prompts:
MCP-UI-enabled extensions return content that Goose can render as embedded UI elements for rich, dynamic, and streamlined interactions.
Try It Out
See how interactive responses work in Goose.
Add Enabled Extension
For this exercise, we'll add an MCP-UI-enabled extension that connects to MCP-UI Demos provided by Andrew Harvard.
1. Click the button in the top-left to open the sidebar 2. Click `Extensions` 3. Click `Add custom extension` 4. On the `Add custom extension` modal, enter the following: - **Extension Name**: Rich Demo - **Type**: Streamable HTTP - **Endpoint**: `https://mcp-aharvard.netlify.app/mcp` 5. Click `Add Extension` to save the extension 6. Navigate to the chatInteract in Chat
In Goose Desktop, ask:
Help me select seats for my flight
Instead of just text, you'll see an interactive response with:
- A visual seat map with available and occupied seats
- Real-time, clickable selection capabilities
- A booking confirmation with flight details
Ask questions to try out other demos:
Plan my next trip based on my moodWhat's the weather in Philadelphia?
Stay tuned as more extensions build with MCP-UI!
For Extension Developers
Want to add interactivity to your own extensions? MCP-UI extends the Model Context Protocol to allow MCP servers to return content that agents can render as UI components instead of text-only responses. Learn more: