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.

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"
      ]
    }
  }
}

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"
      ]
    }
  }
}

• 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

1. Install dependencies:

   npm install

2. Build and start the server:

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

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

Exposes two tools demonstrating a polling pattern:

1. get-system-info (Model-visible) — Returns static system configuration:

   • Hostname, platform, architecture
   • CPU model and core count
   • Total memory

2. 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.

• 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)