Connects to Redis and BullMQ to surface infrastructure health through natural language. Exposes eight tools including redis_health for full diagnostics, redis_memory for fragmentation analysis, redis_slowlog for query inspection, and bullmq_failed_jobs to pull error traces. You can ask your assistant to find stale jobs stuck in active state or check if queues are backing up. Useful when you're debugging production issues conversationally instead of SSH-ing into boxes to run redis-cli commands. Currently Redis-only but the repo structure shows Docker and Kubernetes modules planned.
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.
| 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 |
| 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 |
Works with any AI tool that supports Model Context Protocol — Claude Desktop, Claude Code, Cursor, GitHub Copilot, Cline, Warp, Gemini CLI, Continue, and more.
Add to your MCP client config:
{
"mcpServers": {
"sentinal": {
"command": "npx",
"args": ["@md-musaraf/sentinal-mcp"],
"env": {
"REDIS_URL": "redis://localhost:6379"
}
}
}
}
| 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 |
Just ask your AI assistant:
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.
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
git clone https://github.com/Musaraf-M/sentinal.git
cd sentinal
pnpm install
pnpm build
node platforms/mcp/dist/index.js
Contributions are welcome! Areas where help is needed:
MIT
REDIS_URLsecretRedis connection URL
hovecapital/read-only-local-postgres-mcp-server
cocaxcode/database-mcp
io.github.infoinlet-marketplace/mcp-mysql
io.github.cybeleri/database-admin
io.github.yash-0620/postgres-mcp-secured