A reliable real-time remote Linux server monitoring system that provides comprehensive health and performance metrics, including CPU, memory, disk, network, and security statistics through SSH connections.

Installation

From Source Code

git clone https://github.com/yourusername/mcp-system-health.git
cd mcp-system-health
python -m venv venv
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate
pip install -r requirements.txt

Configuration

Claude Desktop

{
  "mcpServers": {
    "system-health": {
      "command": "/path/to/your/venv/bin/python3",
      "args": [
        "/path/to/your/system-health-mcp-server/src/mcp_launcher.py", 
        "--username=your_ssh_username", 
        "--password=your_ssh_password",
        "--key-path=~/.ssh/id_rsa",
        "--servers=server1.example.com,server2.example.com", 
        "--log-level=debug"
      ],
      "description": "System Health MCP Server for monitoring remote servers"
    }
  }
}

Server Configuration

{
  "hostname": "server1",
  "ip": "192.168.1.100",
  "ssh_port": 22,
  "username": "admin",
  "key_path": "~/.ssh/id_rsa"
}

Available Tools

Tool	Description
system_status	General system health status information
cpu_metrics	Detailed CPU metrics
memory_metrics	Memory and swap usage statistics
disk_metrics	Disk usage for all or specific mount points
network_metrics	Network interface statistics
security_metrics	Security-related metrics
process_list	List of processes consuming the most CPU
system_alerts	Current alerts based on threshold violations
health_summary	Comprehensive system health status summary

Features

• Comprehensive CPU, memory, disk, network, and security metrics collection
• Real-time monitoring with system status checks
• Multi-server support for monitoring multiple servers from a single instance
• Threshold-based alerts for automatic critical state detection
• SSH connection management with efficient pooling and reuse
• Security monitoring for tracking failed login attempts and suspicious processes
• Ready-to-use MCP integration for interaction with AI assistants

Notes

Requires Python 3.10+, SSH access to target servers, and currently supports Linux servers only. Alert thresholds are pre-set for CPU (critical ≥90%, warning ≥80%), memory (critical ≥95%, warning ≥85%), disk (critical ≥95%, warning ≥85%), and security metrics. It is recommended to use key-based authentication instead of passwords for security.