server-monitor-mcp
Server Monitor MCP is a Linux server inspection service with web backend and MCP interface. It allows you to manage SSH hosts and query server metrics via natural language.
README
Server Monitor MCP
Server Monitor MCP 是一个面向 Linux 服务器的巡检服务,提供网页后台和 MCP 接口。你可以在后台维护多台 SSH 主机,用名称区分业务服务器,然后让机器人直接提问:
- 帮我看一下算力服务器的网络状态
- 帮我看一下算力服务器的处理器型号
- 帮我看一下算力服务器的硬盘使用率
功能概览
- 后台登录和服务器管理
- 支持 SSH 密码认证
- 支持 SSH 私钥和私钥口令
- 实时巡检 CPU、内存、磁盘、网络、系统信息
- 支持保存自定义 SSH 巡检命令
- 提供 MCP 工具给上游机器人调用
- 内置请求日志页面,可查看请求内容、返回内容和执行耗时
- 支持在后台配置小智接入地址和 Token
技术栈
- FastAPI
- Jinja2
- SQLite
- Paramiko
- FastMCP
快速部署
1. 安装依赖
pip install -e .
如果你不使用可编辑安装,也可以直接安装依赖:
pip install fastapi jinja2 itsdangerous mcp paramiko cryptography uvicorn websockets
2. 准备环境变量
复制 .env.example 到 .env,至少确认下面这些值:
APP_HOST=127.0.0.1
APP_PORT=8765
ADMIN_USERNAME=admin
ADMIN_PASSWORD=admin123456
APP_SECRET=
XIAOZHI_BRIDGE_ENABLED=false
XIAOZHI_ENDPOINT_URL=
XIAOZHI_RECONNECT_DELAY_SECONDS=5
说明:
APP_SECRET留空时,程序会在本地data/.app_secret自动生成XIAOZHI_ENDPOINT_URL可以先留空,之后在后台页面里配置
3. 启动服务
python -m uvicorn app.main:app --host 127.0.0.1 --port 8765
启动后访问:
- 后台首页:
http://127.0.0.1:8765/ - 日志页面:
http://127.0.0.1:8765/logs - 系统设置:
http://127.0.0.1:8765/settings - MCP 地址:
http://127.0.0.1:8765/mcp
使用方式
后台管理
登录后台后可以:
- 添加服务器名称、地址、端口、用户名
- 选择密码认证或私钥认证
- 保存备注和标签
- 对单台服务器执行实时巡检
- 为服务器配置自定义命令,例如
nvidia-smi
MCP 工具
当前提供的工具:
list_serversget_server_snapshotget_server_metricrun_server_custom_check
适合的提问方式:
- 查询某台服务器的完整巡检信息
- 单独查询 CPU、内存、磁盘、网络、处理器、主机名、系统信息
- 运行预先保存的自定义命令
小智接入
如果要接入小智:
- 打开后台的“系统设置”
- 填写 WebSocket 接入地址
- 填写 Token
- 保存并应用
Token 会加密存储,页面和日志只显示掩码。
运行说明
- 当前巡检逻辑面向 Linux 服务器
.env、数据库、运行日志不会提交到仓库- SSH 凭据会加密后写入 SQLite
- 生产环境建议放到反向代理后面,并启用 HTTPS
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.