Sentinal MCP
Sentinal
面向 AI 助手的基础设施监控工具。一套代码,多平台支持。
通过自然语言对话,让你的 AI 助手检查 Redis 健康状况、检查 BullMQ 队列、诊断慢查询。
平台
平台 | 分发方式 | 安装 |
Claude, Cursor, Copilot, Cline, Warp, Gemini CLI | MCP Server (npm) |
|
OpenClaw | ClawHub |
|
ChatGPT | GPT Store | 即将推出 |
Raycast | Raycast Store | 即将推出 |
Related MCP server: BetterDB MCP
模块
模块 | 状态 | 监控内容 |
Redis | ✅ 就绪 | 服务器健康、内存、慢查询、客户端、BullMQ 队列 |
Docker | 🔜 计划中 | 容器健康、日志、资源使用情况 |
Kubernetes | 🔜 计划中 | Pod 状态、重启次数、资源限制 |
GitHub Actions | 🔜 计划中 | 工作流运行、失败、重新触发 |
Vercel | 🔜 计划中 | 部署状态、回滚 |
MCP Server
适用于任何支持 Model Context Protocol 的 AI 工具 —— 包括 Claude Desktop、Claude Code、Cursor、GitHub Copilot、Cline、Warp、Gemini CLI、Continue 等。
安装
添加到你的 MCP 客户端配置中:
{
"mcpServers": {
"sentinal": {
"command": "npx",
"args": ["@md-musaraf/sentinal-mcp"],
"env": {
"REDIS_URL": "redis://localhost:6379"
}
}
}
}工具
工具 | 描述 |
| 测试与 Redis 实例的连接 |
| 全面健康报告 —— 服务器、内存、客户端、慢查询、BullMQ 队列 |
| 深度内存分析及碎片诊断 |
| 检查慢查询 |
| 列出所有 BullMQ 队列及其各状态下的任务数 |
| 检查失败的任务,包括负载和堆栈跟踪 |
| 特定任务的详细信息 |
| 查找卡在活跃状态的任务 |
使用示例
只需询问你的 AI 助手:
“检查我的 Redis 健康状况”
“有 BullMQ 队列积压吗?”
“显示 email-queue 中失败的任务”
“为什么 Redis 很慢?”
“Redis 使用了多少内存?”
“查找 payment-queue 中过期的任务”
OpenClaw 技能
从 ClawHub 安装独立技能:
clawhub install sentinal-redis该技能教会你的 OpenClaw 助手使用 redis-cli 监控 Redis 和 BullMQ。无需编写代码 —— 只需安装并提问即可。
项目结构
sentinal/
├── core/ # Shared knowledge and scripts
│ ├── redis/
│ ├── docker/
│ └── kubernetes/
├── platforms/
│ ├── mcp/ # MCP Server → npm
│ ├── openclaw/ # OpenClaw Skills → ClawHub
│ ├── chatgpt/ # Custom GPT → GPT Store
│ └── raycast/ # Extension → Raycast Store
└── scripts/ # Build and publish automation开发
前置要求
Node.js 22+
pnpm 10+
设置
git clone https://github.com/Musaraf-M/sentinal.git
cd sentinal
pnpm install构建
pnpm build在本地运行 MCP 服务器
node platforms/mcp/dist/index.js贡献
欢迎贡献!需要帮助的领域:
新的监控模块(Docker, Kubernetes, GitHub Actions)
新的平台适配器
错误修复和改进
许可证
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Application monitoring: exceptions, slow requests, jobs, queries, logs and uptime monitors.
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Investigate errors, track deployments, analyze performance, and manage application monitoring
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to manage BullMQ Redis-based job queues through natural language, supporting operations like job monitoring, queue control, and multi-instance Redis connections. Users can add, retry, promote, and clean jobs while accessing detailed job logs and queue statistics directly within the assistant.20585 npm7MIT
- AlicenseBqualityBmaintenanceBetterDB gives Claude Code, Cursor, Windsurf, and other MCP clients deep observability into Valkey and Redis instances. It implements 22 MCP tools including get_health, get_slowlog, get_commandlog, get_hot_keys, get_anomalies, get_cluster_nodes, get_cluster_slowlog, and get_slot_stats.64110 npm1,308MIT
- AlicenseAqualityCmaintenanceFastMCP server with read-only tools to monitor Redis — queue depths, Celery queue status, connected clients, server/memory info, and per-database key counts53MIT
- AlicenseAqualityDmaintenanceA lightweight npm MCP server for deep Redis diagnostics, offering tools for memory, slowlog, clients, keyspace, latency, and config analysis with AI-powered recommendations.892 npmMIT