Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Your homelab, legible to AI agents — a read-only MCP server that rides along with your monitor

说明与用途

通过只读 MCP 服务器,AI 代理可以访问 homelab 监控数据,实时查询 GPU 使用、能耗和磁盘使用情况,无需手动复制数据。

问题

AI agents could not access detailed homelab monitoring data, forcing manual data transfer and inaccurate inference.

结果

Agents can now retrieve accurate, real‑time homelab metrics without manual intervention, while remaining read‑only for security.

工作流

  • 1. Run monitoring container that collects data into SQLite.
  • 2. Enable MCP server (enable_mcp=0 turns it off).
  • 3. Start MCP server on port 9810 inside the container.
  • 4. Register MCP endpoint with an agent using claude mcp add --transport http homelab http://YOUR-HUB:9810/mcp.
  • 5. Agent queries tools such as hosts, containers, services, per‑card GPU state, energy cost, etc. to obtain read‑only insights.

证据

i keep a monitoring container on my homelab — it reads nvidia-smi, the docker api, systemd and /proc, and turns it into one page.

来源

the agent couldn't see my homelab. it could run commands, but it couldn't see — which model is holding the 3090, why the temperature is climbing, what the month cost in energy.

来源

so i added a read-only MCP server to the same container. it comes up on port 9810, and the whole setup is one line:

来源

nineteen named tools, all read-only: hosts, containers, services, per-card gpu state and which process is on which card, per-process ram, the model servers, installed models, energy cost, benchmark runs, disk treemaps, history, alerts.

来源

no writes. both directions are question and answer. the agent can look around the lab, it can't restart anything.

来源

  • 记录日期: 2026-10-18T09:41:09.160Z