| Filename | Latest commit message | Latest commit date |
|---|---|---|
Rename `startServer` to `startStreamableHTTPServer` and add a new `startStdioServer` helper to make the transport type explicit. Remove the `ServerOptions` interface in favor of reading `PORT` directly from the environment inside the function (defaulting to `3001`). Also update Python examples to default to port `3001` for consistency. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> |
||
| .. | ||
| src | ||
| .gitignore | ||
| grid-cell.png | ||
| main.ts | ||
| mcp-app.html | ||
| package.json | ||
| README.md | ||
| screenshot.png | ||
| server.ts | ||
| tsconfig.json | ||
| tsconfig.server.json | ||
| vite.config.ts | ||
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"
]
}
}
}
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-hostexample or another MCP Apps-compatible host.
Architecture
Server (server.ts)
Exposes a single get-system-stats tool that returns:
- Raw per-core CPU timing data (idle/total counters)
- Memory usage (used/total/percentage)
- System info (hostname, platform, uptime)
The tool is linked to a UI resource via _meta.ui.resourceUri.
App (src/mcp-app.ts)
- Uses Chart.js for the stacked area chart visualization
- Polls the server tool every 2 seconds
- Computes CPU usage percentages client-side from timing deltas
- Maintains a 30-point history (1 minute at 2s intervals)
- Updates all UI elements on each poll


