# Hardware Monitor MCP Server

A local [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that exposes real-time system metrics to AI assistants like **Claude Desktop**.

Ask Claude about CPU, RAM, disk, and battery — no separate monitoring app needed.

## Features

- **CPU & RAM** — live utilization percentages
- **Disk** — usage and free space (Windows `C:\` drive)
- **Battery** — charge level and power source (laptops)
- **Alerts** — warns when CPU or RAM exceeds 80%

## MCP Tools

| Tool | Description |
|------|-------------|
| `get_system_metrics` | Full hardware snapshot |
| `check_performance_thresholds` | Performance warning if CPU/RAM > 80% |

## Quick Start

### 1. Install

```bash
git clone https://github.com/YOUR_USERNAME/cpu-mcp-server.git
cd cpu-mcp-server

python -m venv venv
venv\Scripts\activate        # Windows
# source venv/bin/activate   # macOS/Linux

pip install -r requirements.txt
```

### 2. Configure Claude Desktop

Edit `%APPDATA%\Claude\claude_desktop_config.json` and add:

```json
{
  "mcpServers": {
    "hardware-monitor": {
      "command": "python",
      "args": ["C:\\path\\to\\cpu-mcp-server\\server.py"],
      "disabled": false,
      "autoStart": true
    }
  }
}
```

Use the full path to `python.exe` (or your venv Python) if needed. Restart Claude Desktop.

### 3. Try it

- "Get my current system metrics"
- "What's my CPU usage right now?"
- "Check if my system performance is normal"

## Requirements

- Python 3.10+
- Claude Desktop (or any MCP client with stdio support)
- Windows (disk path is `C:\`; other metrics work cross-platform)

## Docs

- [Setup Instructions](SETUP_INSTRUCTIONS.md) — detailed Windows setup & troubleshooting
- [Platform Overview](PLATFORM_OVERVIEW.md) — features, use cases, tech stack

## Tech Stack

- Python · FastMCP · psutil · MCP stdio transport

## License

MIT (add a LICENSE file if you choose a different license)