huhabla/mcp-system-monitor

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

3 stars 6 forks Качество 61 Тренд 10MIT

A cross-platform MCP (Model Context Protocol) server that provides comprehensive real-time system monitoring capabilities for LLMs.

Обзор

A cross-platform MCP (Model Context Protocol) server that provides comprehensive real-time system monitoring capabilities for LLMs. Built with FastMCP for easy integration with Claude Desktop and other MCP-compatible clients. - : Real-time usage, per-core statistics, frequency, temperature, detailed processor information (model, vendor, architecture, cache sizes) - : Multi-vendor GPU support (NVIDIA with full metrics, Apple Silicon with comprehensive support including unified memory and core count, AMD/Intel with basic info) - : RAM and swap usage, availability statistics - : Space usage, filesystem information for all mounted drives - : Interface-level traffic and error counters - : Top processes by CPU/memory usage - : OS details, hostname, uptime, architecture - : Detailed disk I/O metrics, read/write rates, per-disk statistics, busy time analysis - : Load averages (1m, 5m, 15m), context switches, interrupts, running/blocked processes - : Detailed memory statistics including...

README

Показан фрагмент оригинального README. Открыть оригинал.

MCP System Monitor Server

Features

System Monitoring

Basic System Monitoring:

CPU Monitoring: Real-time usage, per-core statistics, frequency, temperature, detailed processor information (model, vendor, architecture, cache sizes)
GPU Monitoring: Multi-vendor GPU support (NVIDIA with full metrics, Apple Silicon with comprehensive support including unified memory and core count, AMD/Intel with basic info)
Memory Monitoring: RAM and swap usage, availability statistics
Disk Monitoring: Space usage, filesystem information for all mounted drives
Network Statistics: Interface-level traffic and error counters
Process Monitoring: Top processes by CPU/memory usage
System Information: OS details, hostname, uptime, architecture

Phase 1 Performance Monitoring:

I/O Performance: Detailed disk I/O metrics, read/write rates, per-disk statistics, busy time analysis
System Load: Load averages (1m, 5m, 15m), context switches, interrupts, running/blocked processes
Enhanced Memory: Detailed memory statistics including buffers, cache, active/inactive memory, page faults, swap activity
Enhanced Network: Network performance metrics with transfer rates, errors, drops, interface speed and MTU

MCP Tools Available

Basic System Monitoring (9 tools):

get_current_datetime: Get the current local datetime in ISO format
get_cpu_info: Get current CPU usage and statistics
get_gpu_info: Get GPU information for all detected GPUs
get_memory_info: Get RAM and swap usage
get_disk_info: Get disk usage for all mounted drives
get_system_snapshot: Get complete system state in one call
monitor_cpu_usage: Monitor CPU usage over a specified duration
get_top_processes: Get top processes by CPU or memory usage
get_network_stats: Get network interface statistics

Phase 1 Performance Monitoring (6 tools):

get_io_performance: Get detailed I/O performance metrics and rates
get_system_load: Get system load averages and process statistics
get_enhanced_memory_info: Get detailed memory statistics with caches/buffers
get_enhanced_network_stats: Get enhanced network performance metrics
get_performance_snapshot: Get complete performance monitoring snapshot
monitor_io_performance: Monitor I/O performance over specified duration with trend analysis

MCP Resources

Basic System Resources (3 resources):

system://live/cpu: Live CPU usage data
system://live/memory: Live memory usage data
system://config: System configuration and hardware information

Phase 1 Performance Resources (3 resources):

system://performance/io: Live I/O performance data
system://performance/load: Live system load data

Открыть полный README на GitHub

Установка

This server does not publish a one-line install command.

Open the repository installation guide Новичок в MCP? Начните с руководства на mcpskill.org →

Конфигурация

{
  "mcpServers": {
    "mpc-system-monitor": {
      "command": "cmd",
      "args": [
        "/c",
        "C:/Users/Sören Gebbert/Documents/GitHub/mcp-system-monitor/start_mpc_system_monitor.bat"
      ]
    }
  }
}