MCP App Test Value Picker Server
A debug tool for platform developers to verify that their MCP App hosts correctly implement protocol specifications like context injection and message sending. It provides a blind selection test to ensure seamless end-to-end communication between the UI, host, and model.
README
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-context - Message sending works — The UI can trigger follow-up messages via
ui/message - The 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:
npm install -g mcp-server-value-picker
Run the server:
# Auto-detects transport mode
mcp-server-value-picker
# Force STDIO mode (for Claude Desktop)
mcp-server-value-picker --stdio
# Force HTTP mode
mcp-server-value-picker --http
Or run directly with npx (no install required):
npx mcp-server-value-picker
Local Development
For modifying the example or contributing:
npm install
npm run build
npm start
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 UI - User clicks a value card
- The UI sends
ui/update-model-contextwith the selection details - The 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 | ui/update-model-context |
AI knows selected value |
| Forward UI messages to conversation | ui/message |
AI receives follow-up prompt |
| Deliver tool results to UI | ui/notifications/tool-result |
UI renders value cards |
| Pass tool arguments to UI | ui/notifications/tool-input |
UI receives empty args |
| Handle teardown gracefully | ui/resource-teardown |
No errors on close |
Full Specification Coverage
| Feature | Spec Section |
|---|---|
text/html;profile=mcp-app MIME type |
UI Resource Format |
ui:// URI scheme |
UI Resource Format |
_meta.ui.resourceUri linkage |
Resource Discovery |
ui/initialize / ui/notifications/initialized |
Lifecycle |
ui/notifications/tool-input |
Data Passing |
ui/notifications/tool-result |
Data Passing |
ui/notifications/tool-cancelled |
Notifications |
ui/resource-teardown |
Cleanup |
ui/update-model-context |
Requests |
ui/message |
Requests |
ui/notifications/host-context-changed |
Notifications |
HostContext.theme |
Theming |
HostContext.styles.variables |
Theming |
HostContext.styles.css.fonts |
Custom Fonts |
HostContext.safeAreaInsets |
Container Dimensions |
content + structuredContent dual model |
Data Passing |
Files
| File | Purpose |
|---|---|
server.ts |
MCP server with pick_value tool and UI resource |
src/mcp-app.ts |
View implementation (App class, handlers, context) |
src/mcp-app.css |
View styling with CSS variable fallbacks |
mcp-app.html |
HTML template with color-scheme meta tag |
main.ts |
Entry point with STDIO/HTTP transport selection |
Implementation Details
<details> <summary>Server-side implementation</summary>
Tool Registration with UI Metadata
registerAppTool(server, "pick_value", {
title: "Pick a Value",
description: "DEBUG/TEST TOOL: Tests MCP Apps communication between UI and model...",
inputSchema: {},
_meta: { ui: { resourceUri: "ui://pick-value/mcp-app.html" } },
}, async () => { /* handler */ });
Dual Content Model
return {
content: [{
type: "text",
text: `[MCP Apps Test] This is a debug tool...`,
}],
structuredContent: {
values: VALUES, // UI-only, not sent to model
},
};
</details>
<details> <summary>View-side implementation</summary>
Context Update
await app.updateModelContext({
content: [{
type: "text",
text: `The user selected "${value.label}" (id: ${value.id}).`,
}],
});
Message Sending
await app.sendMessage({
role: "user",
content: [{
type: "text",
text: `I have picked a value, can you tell me what it is?`,
}],
});
Host Context Handling
app.onhostcontextchanged = (ctx) => {
if (ctx.theme) applyDocumentTheme(ctx.theme);
if (ctx.styles?.variables) applyHostStyleVariables(ctx.styles.variables);
if (ctx.styles?.css?.fonts) applyHostFonts(ctx.styles.css.fonts);
if (ctx.safeAreaInsets) { /* apply padding */ }
};
</details>
By Sebastian Whincop - https://github.com/MacJedi42
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。