Sentinal MCP
Redis health, BullMQ queue monitoring, memory analysis, and slow query diagnostics
README
Sentinal
Infrastructure monitoring tools for AI assistants. One codebase, multiple platforms.
Ask your AI assistant to check Redis health, inspect BullMQ queues, diagnose slow queries — all through natural conversation.
Platforms
| Platform | Distribution | Install |
|---|---|---|
| Claude, Cursor, Copilot, Cline, Warp, Gemini CLI | MCP Server (npm) | npx @md-musaraf/sentinal-mcp |
| OpenClaw | ClawHub | clawhub install sentinal-redis |
| ChatGPT | GPT Store | Coming soon |
| Raycast | Raycast Store | Coming soon |
Modules
| Module | Status | What it monitors |
|---|---|---|
| Redis | ✅ Ready | Server health, memory, slow queries, clients, BullMQ queues |
| Docker | 🔜 Planned | Container health, logs, resource usage |
| Kubernetes | 🔜 Planned | Pod status, restart counts, resource limits |
| GitHub Actions | 🔜 Planned | Workflow runs, failures, re-triggers |
| Vercel | 🔜 Planned | Deployment status, rollbacks |
MCP Server
Works with any AI tool that supports Model Context Protocol — Claude Desktop, Claude Code, Cursor, GitHub Copilot, Cline, Warp, Gemini CLI, Continue, and more.
Install
Add to your MCP client config:
{
"mcpServers": {
"sentinal": {
"command": "npx",
"args": ["@md-musaraf/sentinal-mcp"],
"env": {
"REDIS_URL": "redis://localhost:6379"
}
}
}
}
Tools
| Tool | Description |
|---|---|
redis_ping |
Test connectivity to a Redis instance |
redis_health |
Full health report — server, memory, clients, slow queries, BullMQ queues |
redis_memory |
Deep memory analysis with fragmentation diagnostics |
redis_slowlog |
Inspect slow queries |
bullmq_list |
List all BullMQ queues with job counts per state |
bullmq_failed_jobs |
Inspect failed jobs with payloads and stack traces |
bullmq_job_details |
Full details of a specific job |
bullmq_stale_jobs |
Find jobs stuck in active state |
Example Usage
Just ask your AI assistant:
- "Check my Redis health"
- "Are any BullMQ queues backing up?"
- "Show me failed jobs in the email-queue"
- "Why is Redis slow?"
- "How much memory is Redis using?"
- "Find stale jobs in the payment-queue"
OpenClaw Skills
Install individual skills from ClawHub:
clawhub install sentinal-redis
The skill teaches your OpenClaw assistant to monitor Redis and BullMQ using redis-cli. No code required — just install and ask.
Project Structure
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
Development
Prerequisites
- Node.js 22+
- pnpm 10+
Setup
git clone https://github.com/Musaraf-M/sentinal.git
cd sentinal
pnpm install
Build
pnpm build
Run MCP server locally
node platforms/mcp/dist/index.js
Contributing
Contributions are welcome! Areas where help is needed:
- New monitoring modules (Docker, Kubernetes, GitHub Actions)
- New platform adapters
- Bug fixes and improvements
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。