System Monitor MCP Server

System Monitor MCP Server

Provides system monitoring and management capabilities for Claude CLI, allowing users to view system information, track resource usage, and manage processes through natural language commands.

Category
访问服务器

README

System Monitor MCP Server

A powerful MCP (Model Context Protocol) server that provides system monitoring and management capabilities for Claude CLI.

Features

System Information

  • OS Details: Get comprehensive operating system information
  • Hardware Info: CPU count, architecture, and specifications
  • Boot Time: System uptime tracking

Resource Monitoring

  • CPU Usage: Real-time CPU utilization with per-core statistics
  • Memory Stats: RAM and swap usage monitoring
  • Disk Usage: Storage information for all mounted partitions
  • Network Stats: Interface statistics and connection counts

Process Management

  • List Processes: View running processes sorted by CPU/memory usage
  • Process Details: Get detailed information about specific processes
  • Kill Processes: Terminate processes by PID (with optional force kill)

Installation

  1. Clone or download this repository:
cd system-monitor-mcp
  1. Install dependencies:
pip install -r requirements.txt
  1. Add to Claude CLI:
# Add as a local MCP server (use server_standalone.py)
claude mcp add system-monitor python /path/to/system-monitor-mcp/server_standalone.py

# Or with a specific Python interpreter
claude mcp add system-monitor /usr/bin/python3 /path/to/system-monitor-mcp/server_standalone.py

Usage Examples

Once installed, you can use the following commands in Claude:

Check System Status

"What's my system status?"
"Show me CPU and memory usage"

Monitor Resources

"How much disk space do I have?"
"What's using the most CPU?"
"Show me the top 10 memory-consuming processes"

Process Management

"List all running processes"
"Get details about process 1234"
"Kill the process using port 8080"

Network Information

"Show network statistics"
"What network interfaces are available?"

Available Tools

Tool Description Parameters
get_system_info() Get OS and hardware information None
get_cpu_usage() Get CPU usage statistics interval (float, optional)
get_memory_info() Get RAM and swap usage None
get_disk_usage() Get disk space for all partitions None
list_processes() List running processes sort_by (str), limit (int)
get_process_info() Get details about a specific process pid (int)
kill_process() Terminate a process pid (int), force (bool)
get_network_stats() Get network interface statistics None

Resources

The server also provides a resource endpoint:

  • system://status - Returns a formatted system status overview

Security Notes

  • Some operations may require elevated privileges (e.g., killing system processes)
  • The server respects system permissions and will report access denied errors appropriately
  • Use the force parameter with caution when killing processes

Requirements

  • Python 3.7+
  • psutil library

Note: This server includes a standalone MCP implementation that doesn't require the official MCP Python SDK.

Troubleshooting

Permission Errors

Some system information may require elevated privileges. Run with appropriate permissions if needed.

Process Not Found

Processes may terminate between listing and accessing. The server handles these cases gracefully.

Platform Compatibility

This server is designed to work on Linux, macOS, and Windows, though some features may vary by platform.

Contributing

Feel free to extend this server with additional monitoring capabilities or system management features!

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选