Skip to main content
Glama
nikolapP1

MCP Server Health Monitor

by nikolapP1

MCP Server Health Monitor

一个 MCP(模型上下文协议)服务器,让 LLM 能够监控服务器基础设施。将其连接到 OpenCode、Claude Code 或任何兼容 MCP 的客户端,即可用自然语言询问服务器的健康状况。

功能

你可以向 LLM 询问以下内容:

  • "我的 Web 服务器是否在响应?"

  • "我还剩多少磁盘空间?"

  • "哪些进程占用的内存最多?"

  • "3306 端口是否开放?"

Related MCP server: System Monitor MCP Server

工具

工具

描述

check_http_endpoint

检查 URL 是否返回 200 OK

check_disk_usage

获取磁盘空间信息

check_memory_usage

获取内存和交换分区使用情况

check_cpu_usage

获取每个核心的 CPU 使用率

check_port

检查 TCP 端口是否开放

list_processes

列出正在运行的进程,支持可选过滤

资源

资源

描述

system://info

操作系统、主机名、运行时间

system://health

汇总的健康状态

技术栈

  • Python 3.12+

  • MCP Python SDK v2

  • psutil(系统指标)

  • httpx(HTTP 检查)

设置

  1. 安装依赖:

uv sync
  1. 运行服务器:

uv run mcp-server-monitor

或者直接运行:

uv run python -m mcp_server_monitor

使用 MCP Inspector 进行测试

uv run mcp dev src/mcp_server_monitor/server.py

这将在浏览器中打开 MCP Inspector,你可以在其中交互式地调用工具。

连接到 OpenCode

添加到你的 opencode.json

{
  "mcpServers": {
    "server-monitor": {
      "command": "uv",
      "args": ["run", "--project", "C:\\Users\\nikol\\Documents\\mcp-server-monitor", "mcp-server-monitor"]
    }
  }
}

运行测试

uv run pytest

项目结构

src/mcp_server_monitor/
├── __init__.py          Package metadata
├── __main__.py          Entry point
├── server.py            MCP server setup
├── tools/
│   ├── http.py          HTTP endpoint checking
│   ├── system.py        CPU, memory, disk
│   ├── network.py       Port checking
│   └── processes.py     Process listing
└── resources/
    └── status.py        System info and health

许可证

MIT

F
license - not found
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides read-only server monitoring and diagnostic tools for AI assistants to manage Linux and Unraid systems via SSH. It enables natural language interactions for container management, storage health checks, and system log analysis while keeping credentials secure.
    17
    ISC
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables LLMs to securely manage Virtual Private Servers via SSH, with features including command execution, file operations, system monitoring, and service management.
    MIT

View all related MCP servers

Related MCP Connectors

  • Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.

  • Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.

  • Uptime, SSL, DNS and domain monitoring you can talk to from Claude or any MCP client.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nikolapP1/mcp-server-monitor'

If you have feedback or need assistance with the MCP directory API, please join our Discord server