Watch

History

Repository files (latest commit first)
Filename	Latest commit message	Latest commit date
Olivier Chafik 8e7206cb15 chore(deps): npm audit fix — sdk 1.29.0, systeminformation 5.31.5, +13 transitives (#585 ) Clears all 15 npm audit findings (8 high / 6 moderate / 1 low): - @modelcontextprotocol/sdk 1.25.2 → 1.29.0 (GHSA-345p-7cg4-v4c7 cross-client data leak via shared transport reuse). Root had it pinned exact in devDependencies which blocked audit fix. - systeminformation 5.30.6 → 5.31.5 (GHSA-5vv4-hvf7-2h46, GHSA-9c88-49p5-5ggf command injection) - hono, undici, rollup, picomatch, minimatch, lodash-es, svelte, devalue, ajv, brace-expansion, markdown-it, yaml, qs — lockfile bumps via npm audit fix		2026-04-02 04:25:00 +01:00
..
src	Separate static and dynamic data in system-monitor-server tools	2026-01-28 11:04:35 -06:00
.gitignore	Improve consistency and organization of examples for AI learning	2026-01-13 20:48:02 -06:00
grid-cell.png	feat(basic-host): URL params, fullscreen mode, unified layout (#266 )	2026-01-14 22:09:41 +00:00
main.ts	Refactor server startup functions	2026-01-24 09:27:54 -06:00
mcp-app.html	Add color-scheme meta tag to all example apps	2025-12-15 11:42:18 -08:00
package.json	chore(deps): npm audit fix — sdk 1.29.0, systeminformation 5.31.5, +13 transitives (#585 )	2026-04-02 04:25:00 +01:00
README.md	Use `apps.extensions.modelcontextprotocol.io` domain for docs URLs	2026-02-24 11:38:54 -06:00
screenshot.png	feat(basic-host): URL params, fullscreen mode, unified layout (#266 )	2026-01-14 22:09:41 +00:00
server.ts	Separate static and dynamic data in system-monitor-server tools	2026-01-28 11:04:35 -06:00
tsconfig.json	Add system-monitor-server example	2025-12-04 14:32:41 -06:00
tsconfig.server.json	feat: compile example servers to JavaScript for npm consumption (#259 )	2026-01-14 23:46:17 +00:00
vite.config.ts	Add system-monitor-server example	2025-12-04 14:32:41 -06:00

README.md

Example: System Monitor App

A demo MCP App that displays real-time OS metrics with a stacked area chart for per-core CPU usage and a bar gauge for memory.

MCP Client Configuration

Add to your MCP client configuration (stdio transport):

{
  "mcpServers": {
    "system-monitor": {
      "command": "npx",
      "args": [
        "-y",
        "--silent",
        "--registry=https://registry.npmjs.org/",
        "@modelcontextprotocol/server-system-monitor",
        "--stdio"
      ]
    }
  }
}

Local Development

To test local modifications, use this configuration (replace ~/code/ext-apps with your clone path):

{
  "mcpServers": {
    "system-monitor": {
      "command": "bash",
      "args": [
        "-c",
        "cd ~/code/ext-apps/examples/system-monitor-server && npm run build >&2 && node dist/index.js --stdio"
      ]
    }
  }
}

Features

Per-Core CPU Monitoring: Stacked area chart showing individual CPU core utilization over a 1-minute sliding window
Memory Usage: Horizontal bar gauge with color-coded thresholds (green/yellow/red)
System Info: Hostname, platform, and uptime display
Auto-Polling: Automatically starts monitoring on load with 2-second refresh interval
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 two tools demonstrating a polling pattern:

get-system-info (Model-visible) — Returns static system configuration:
- Hostname, platform, architecture
- CPU model and core count
- Total memory
poll-system-stats (App-only, visibility: ["app"]) — Returns dynamic metrics:
- Per-core CPU timing data (idle/total counters)
- Memory usage (used/free/percentage)
- Uptime

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

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

Receives static system info via ontoolresult when the host sends the get-system-info result
Polls poll-system-stats every 2 seconds for dynamic metrics
Uses Chart.js for the stacked area chart visualization
Computes CPU usage percentages client-side from timing deltas
Maintains a 30-point history (1 minute at 2s intervals)