MCP server · Developer tools

Container Host AIops MCP server

Ask your AI to check your containers, find crash loops and wasted disk space, and stop or restart things safely.

Developer tools For it and development For operations Cloud Platforms

This is a helper for people who run apps in containers on a single machine or server. Once it is connected, your AI can look at what is running, spot containers that keep crashing, find wasted disk space, and stop or restart things when you ask. It suits anyone who looks after one Docker or Podman machine themselves and would rather ask a question than click around a dashboard.

What is an MCP server? The 30-second version

On its own, your AI can only chat. It cannot see your computer or your server. An MCP server is a small helper program that gives your AI one new skill, and this one gives it a connection to your container host, which is the place where your Docker or Podman containers actually run. Connect it, and the AI can look things up there and make changes for you, instead of you typing commands yourself.

What this MCP server does

You ask your AI a question in normal words, for example which containers keep restarting. The AI passes that on to this helper, and the helper talks to your container host through the local connection you set up during setup. It reads the facts it needs, such as restart counts, exit codes, log lines and disk usage, and hands them back to the AI. The AI then explains the answer in plain language. If you asked for a change instead, it shows you a preview and carries out the stop, restart or cleanup once you agree.

What you can do with it

See a one-page summary of the health of your container host
List your containers and see which ones are running
Read the recent logs of a container that is misbehaving
Find containers stuck in a restart loop and get a likely cause and fix
Spot containers running close to or over their memory and CPU limits
Total up unused images, volumes and build cache you could clear
Stop, start or restart a container, with a preview before it happens

Try asking your AI

“Which containers on this host are stuck restarting, and why?”
“Show me the last logs from the web container.”
“How much disk space could I get back by cleaning up unused images and volumes?”
“Stop the old reporting container for me, but show me what that will do first.”

What it gives back to you

You get answers in the chat, not raw machine output: a short list, a table of numbers, or a written explanation. The analyses come with their figures attached, so you can see why a container was flagged rather than just taking a verdict on trust. When you ask for a change, you get a preview first and then a confirmation of what was actually done. Every request is also written to a log file on your own machine, so there is a record of what happened.

Before you start

What you need

A machine with Docker or Podman already installed and running, or a Portainer account you can log into
The uv tool or pipx to install the helper program
For Portainer: its web address and an access token, which is a kind of password the Portainer site gives you
A master password you choose, used to keep that token scrambled on your disk

Good to know

It can stop, restart and delete containers, images and volumes, and some deletions cannot be undone, so always read the preview before you say yes.

Install it with your AI

Add Container Host AIops MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Container Host AIops MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.

Who it's for

People who run Docker or Podman on one machine and look after it themselves, such as a small IT team, a developer with their own server, or someone hosting a few apps at home.