Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP App Test Value Picker Serverrun the value picker test"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP App Test Value Picker Server
A debug tool for platform developers building MCP Apps hosts. Use this MCP server to verify that your platform correctly implements the ui/update-model-context and ui/message protocols defined in the MCP Apps Specification.
Why Use This?
When building an MCP Apps host, you need to verify that:
Context injection works — Values selected in the UI iframe reach the AI model via
ui/update-model-contextMessage sending works — The UI can trigger follow-up messages via
ui/messageThe complete flow works — View → Host → Model communication is functioning end-to-end
This tool provides a simple "blind selection" test: the user picks a value in the UI, and the AI must correctly identify what was selected. If the AI knows the value, your platform is working. If not, something is broken in your ui/update-model-context implementation.
Installation
Via npm (Recommended)
Install from npmjs.com/package/mcp-server-value-picker:
Run the server:
Or run directly with npx (no install required):
Local Development
For modifying the example or contributing:
Default HTTP endpoint: http://localhost:3456/mcp
How the Test Works
Connect this MCP server to your platform
The AI calls the
pick_valuetool, which displays 10 selectable values in the UIUser clicks a value card
The UI sends
ui/update-model-contextwith the selection detailsThe UI sends
ui/messageasking "I have picked a value, can you tell me what it is?"If your platform works: The AI responds with the correct value
If something is broken: The AI won't know what was selected
Expected Model Response
The tool description explicitly tells the AI this is a debug test. A correct response looks like:
"You selected Alpha Protocol (id: alpha)."
If the AI elaborates extensively on the value meanings, the test still passed (context injection worked), but the AI didn't follow the debug instructions.
What This Tests
Platform Requirements Verified
Your Platform Must... | Protocol Message | Verified By |
Inject UI context into model |
| AI knows selected value |
Forward UI messages to conversation |
| AI receives follow-up prompt |
Deliver tool results to UI |
| UI renders value cards |
Pass tool arguments to UI |
| UI receives empty args |
Handle teardown gracefully |
| No errors on close |
Full Specification Coverage
Feature | Spec Section |
| UI Resource Format |
| UI Resource Format |
| Resource Discovery |
| Lifecycle |
| Data Passing |
| Data Passing |
| Notifications |
| Cleanup |
| Requests |
| Requests |
| Notifications |
| Theming |
| Theming |
| Custom Fonts |
| Container Dimensions |
| Data Passing |
Files
File | Purpose |
| MCP server with |
| View implementation ( |
| View styling with CSS variable fallbacks |
| HTML template with color-scheme meta tag |
| Entry point with STDIO/HTTP transport selection |
Implementation Details
Tool Registration with UI Metadata
Dual Content Model
Context Update
Message Sending
Host Context Handling
By Sebastian Whincop - https://github.com/MacJedi42