Watch

Anton Pidkuiko 37aab03de0

docs: add tool visibility and restructure _meta.ui (#131 )

* docs: add tool visibility and restructure _meta.ui

- Restructure tool metadata: `_meta["ui/resourceUri"]` → `_meta.ui.resourceUri`
- Add `visibility` array field: ["model"], ["apps"], or ["model", "apps"]
- Default ["model"] preserves standard MCP behavior
- ["apps"] enables widget-only tools hidden from agent
- Add McpUiToolMeta interface for type safety
- Add Design Decision #4 explaining approach vs OpenAI's two-field model

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* address PR review comments

- Change default visibility to ["model", "apps"]
- Add deprecation notice for flat ui/resourceUri format
- Add McpUiToolMeta and McpUiToolVisibility to spec.types.ts
- Improve tools/list and tools/call behavior wording

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* chore: regenerate schemas for McpUiToolMeta types

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat: tool visibility and nested _meta.ui format

- Rename visibility "apps" → "app" in McpUiToolVisibility type
- Add _meta.ui.resourceUri nested format (deprecate flat format)
- Add getToolUiResourceUri() utility with backward compatibility
- Add visibility demo to system-monitor-server:
  - get-system-stats: visibility ["model"] with resourceUri
  - refresh-stats: visibility ["app"] (app-only polling)
- Update all example servers to use new _meta.ui format
- Add 11 unit tests for getToolUiResourceUri()

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* chore: regenerate schemas with updated dependencies

* feat: export McpUiToolMeta type and add type annotations

- Export McpUiToolMeta and McpUiToolVisibility types from types.ts
- Export corresponding Zod schemas (McpUiToolMetaSchema, McpUiToolVisibilitySchema)
- Add `as McpUiToolMeta` type annotations to all example servers
- Update docs/quickstart.md with proper typing

Ensures type safety for `_meta.ui` tool metadata across the codebase.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat: add server helpers and optional connect() transport

Add `src/server/` with convenience functions for registering MCP App tools
and resources:

- `registerAppTool(server, name, config, handler)`
- `registerAppResource(server, name, uri, config, callback)`

The `transport` parameter in `App.connect()` is now optional, defaulting to
`PostMessageTransport(window.parent)`.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update src/server/index.ts

Co-authored-by: Jonathan Hefner <jonathan@hefner.pro>

* feat: update McpUiAppToolConfig to support both _meta.ui and flat formats

* refactor: simplify server helper imports

* docs: add deprecation notice and improve resourceUri documentation

* feat: add backward compat normalization in registerAppTool

- If _meta.ui.resourceUri is set, also set legacy flat key
- If legacy flat key is set, also set _meta.ui.resourceUri
- Preserves existing visibility when merging
- Does not overwrite if both formats already set

* refactor: avoid mutating config arg in registerAppTool

* style: format with prettier

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Olivier Chafik <ochafik@anthropic.com>
Co-authored-by: Jonathan Hefner <jonathan@hefner.pro>

2025-12-16 21:47:40 +00:00

3.2 KiB

Raw Permalink Blame History

Example: Customer Segmentation Explorer

A demo MCP App that displays customer data as an interactive scatter/bubble chart with segment-based clustering. Users can explore different metrics, filter by segment, and click to see detailed customer information.

Features

Interactive Scatter Plot: Bubble chart visualization using Chart.js with configurable X/Y axes
Segment Clustering: 250 customers grouped into 4 segments (Enterprise, Mid-Market, SMB, Startup)
Axis Selection: Choose from 6 metrics for each axis (Revenue, Employees, Account Age, Engagement, Tickets, NPS)
Size Mapping: Optional bubble sizing by a third metric for additional data dimension
Legend Filtering: Click segment pills to show/hide customer groups
Detail Panel: Hover or click customers to see name, segment, revenue, engagement, and NPS
Theme Support: Adapts to light/dark mode preferences

Running

Install dependencies:
```
npm install
```

Build and start the server:

npm run start:http  # for Streamable HTTP transport
# OR
npm run start:stdio  # for stdio transport

View using the basic-host example or another MCP Apps-compatible host.

Architecture

Server (`server.ts`)

Exposes a single get-customer-data tool that returns:

Array of 250 generated customer records with segment assignments
Segment summary with counts and colors for each group
Optional segment filter parameter

The tool is linked to a UI resource via _meta.ui.resourceUri.

App (`src/mcp-app.ts`)

Uses Chart.js bubble chart for the visualization
Fetches data once on connection
Dropdown controls update chart axes and bubble sizing
Custom legend with clickable segment toggles
Detail panel updates on hover/click interactions

Data Generator (`src/data-generator.ts`)

Generates realistic customer data with Gaussian clustering around segment centers
Each segment has characteristic ranges for revenue, employees, engagement, etc.
Company names generated from word-list combinations (e.g., "Apex Data Corp")
Data cached in memory for session consistency

3.2 KiB Raw Permalink Blame History