| Filename | Latest commit message | Latest commit date |
|---|---|---|
9f09932baf* build app-with-deps
* make registerAppTool more interchangeable w/ server.registerTool
* feat: use structuredContent in all example servers
All servers now return structuredContent alongside JSON text content.
All mcp-apps now read structuredContent directly (no JSON.parse fallback).
Updated servers:
- basic-server-vanillajs
- budget-allocator-server
- cohort-heatmap-server
- customer-segmentation-server
- integration-server
- scenario-modeler-server
- system-monitor-server
- threejs-server
- video-resource-server
- wiki-explorer-server
* feat: add outputSchema to all example servers
Define output schemas for structuredContent validation:
- basic-server-vanillajs: { time: string }
- budget-allocator-server: BudgetDataResponseSchema
- cohort-heatmap-server: CohortDataSchema
- customer-segmentation-server: customers/segments schema
- integration-server: { time: string }
- scenario-modeler-server: templates/defaultInputs schema
- system-monitor-server: SystemStatsSchema
- threejs-server: { code, height }
- video-resource-server: { videoUri, description }
- wiki-explorer-server: { page, links, error }
* prettier:fix
* make registerAppTool more interchangeable w/ server.registerTool
* feat: use structuredContent in all example servers
All servers now return structuredContent alongside JSON text content.
All mcp-apps now read structuredContent directly (no JSON.parse fallback).
Updated servers:
- basic-server-vanillajs
- budget-allocator-server
- cohort-heatmap-server
- customer-segmentation-server
- integration-server
- scenario-modeler-server
- system-monitor-server
- threejs-server
- video-resource-server
- wiki-explorer-server
* feat: add outputSchema to all example servers
Define output schemas for structuredContent validation:
- basic-server-vanillajs: { time: string }
- budget-allocator-server: BudgetDataResponseSchema
- cohort-heatmap-server: CohortDataSchema
- customer-segmentation-server: customers/segments schema
- integration-server: { time: string }
- scenario-modeler-server: templates/defaultInputs schema
- system-monitor-server: SystemStatsSchema
- threejs-server: { code, height }
- video-resource-server: { videoUri, description }
- wiki-explorer-server: { page, links, error }
* prettier:fix
* revert: remove unrelated workflow, version, and arch changes
* chore: update package-lock.json
* refactor(basic-server-vanillajs): address PR review comments
- Simplify server.ts to return plain time string in text content (not JSON),
matching the quickstart guide pattern
- Add defensive coding in mcp-app.ts with optional chaining and fallback
to handle potential type mismatches gracefully
* refactor: restore rich text formatting for LLM-readable content
Restore the human-readable text formatting functions that were removed,
providing meaningful summaries in the text content while keeping
structuredContent for programmatic UI consumption:
- budget-allocator-server: formatBudgetSummary with config overview
- cohort-heatmap-server: formatCohortSummary with retention stats
- scenario-modeler-server: formatScenarioSummary with financial metrics
|
||
| .. | ||
| src | ||
| mcp-app.html | ||
| package.json | ||
| README.md | ||
| server-utils.ts | ||
| server.ts | ||
| tsconfig.json | ||
| vite.config.ts | ||
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-hostexample 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 consistency across requests