Docker MCP Server

io.github.friendlygeorgePublished by GitHub account friendlygeorgev0.3.5Updated Nov 3, 2026

MCP server for Docker — containers, health checks, Compose, logs, monitoring for AI agents

VerifiedSTDIODesktop onlyCloud & Infrastructure Developer Tools Security & Monitoring

Server details

Identifier: io.github.friendlygeorge/docker-mcp-server
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account friendlygeorge for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.friendlygeorge%2Fdocker-mcp-server.svg)](https://sourceweft.com/mcp/io.github.friendlygeorge%2Fdocker-mcp-server?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Local MCP server that lets an AI assistant manage Docker containers, Compose stacks, health checks, logs and fleet monitoring on your machine.

What you can do: Create, recreate and run containers, with restart policies and port mappings
Run HTTP, TCP or exec health probes and wait for readiness
Bring Compose stacks up and down, list services, restart them and read their logs
Tail and search container logs with timestamp filters, and capture container stats
Monitor the fleet: status, stats, events, thresholds and a dashboard view
Exec into containers to run diagnostics
When to use it: Useful when an assistant should deploy, verify and keep containers running on your own machine — agent-managed deployments with health checks and rollback, self-healing restarts, Compose stack orchestration, or debugging containers without SSH.
Requirements: Runs as a local stdio process installed from the npm package, so Node.js is needed. It talks directly to the Docker socket; the DOCKER_HOST environment variable sets the socket path (default /var/run/docker.sock). No API keys or paid plan are required. Desktop only.

Before you install

It connects directly to the Docker socket, which is effectively root-level control over the host: the assistant can create, recreate, stop and delete containers and run commands inside them. Restart policies and Compose up/down change running state. Only install where you accept that level of access, and point DOCKER_HOST at a socket you intend to expose.

Installation

In SourceWeft

Open Docker MCP Server in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@supernova123/docker-mcp-server

[npm version] [npm downloads] [License: MIT] [MCP] [Claude Desktop]

[Awesome] [Glama]

The Docker MCP server designed for agents that need their containers to stay running.

Runs locally. No API keys. No paid plan. Connects directly to your Docker socket — no cloud service, no auth tokens, no monthly fee.

Without this: Your agent deploys a container, it crashes at 3am, and nobody notices until the user complains. Compose stacks drift. Health checks are manual. Logs are scattered across terminals.

With this: Your agent checks health, watches for readiness, restarts crashed containers, and follows logs, all through a single MCP interface. Containers stay running because your agent knows how to keep them running.

Why This Server?

There are 11+ Docker MCP servers on npm. Most are stale, GPL-licensed, or only cover basic CRUD. This one is different:

	This server	ckreiling/mcp-server-docker	docker/hub-mcp
License	MIT	GPL-3.0	Apache-2.0
Runs locally	✅ No API keys, no paid plan	✅	❌ Requires Docker Hub auth
Last updated	Active	Jun 2025 (stale)	Active
Health checks	✅ HTTP/TCP/exec probes	❌	❌
Auto-restart	✅ set_restart_policy	❌	❌
Compose lifecycle	✅ up/down/ps/logs/restart	❌	❌
Log streaming	✅ tail + timestamp filter	Basic	Basic
Fleet monitoring	✅ 6 fleet tools (status, stats, events, logs, thresholds, dashboard)	❌	❌
Agent positioning	✅ Built for agents	Generic Docker	Registry API

Use Cases

Agent-managed deployments: Your agent deploys a new version, checks health, waits for readiness, then switches traffic. If the health check fails, it auto-rolls back.

Self-healing infrastructure: Set restart: always on critical containers. Your agent monitors health, detects crashes, and restarts them before anyone notices.

Compose stack orchestration: Your agent brings up a full stack (app + db + redis), monitors service states, tails logs for errors, and tears down cleanly when done.

Debugging sessions: Your agent execs into a container, runs diagnostics, streams logs with timestamp filters, and captures stats — all without SSH.

How It Works

Here's what an agent actually does with this server during a deployment:

1. Deploy:      run_container(image="myapp:v2", ports={8080:80})2. Health check: check_health(container="myapp", type="http", path="/ready")3. Wait:        watch_health(container="myapp", timeout=30)4. Monitor:     fleet_status()  → see all containers, health states, uptime5. Watch:       watch_events(window=60)  → detect crashes, restarts, health changes6. Debug:       search_logs(pattern="ERROR", containers=["myapp"])7. Rollback:    recreate_container(name="myapp", image="myapp:v1")  if v2 fails

1. Deploy:      run_container(image="myapp:v2", ports={8080:80})2. Health check: check_health(container="myapp", type="http", path="/ready")3. Wait:        watch_health(container="myapp", timeout=30)4. Monitor:     fleet_status()  → see all containers, health states, uptime5. Watch:       watch_events(window=60)  → detect crashes, restarts, health changes6. Debug:       search_logs(pattern="ERROR", containers=["myapp"])7. Rollback:    recreate_container(name="myapp", image="myapp:v1")  if v2 fails

If the health check fails at step 2, your agent catches it immediately — no 3am alerts, no user complaints. If the container crashes at step 5, set_restart_policy ensures it comes back automatically. The agent doesn't just deploy containers — it keeps them running.

Blog Posts

Real data from building and running this server:

I Cut My Docker MCP Server From 50 to 12 Tools — why fewer tools = better agent UX
MCP Server Performance Optimization — benchmarking tool execution latency
Building an MCP Server From Scratch — the full development process
What 6,000 npm Downloads Taught Me — distribution and growth data
The MCP Server Naming Playbook — how naming affects discoverability

Built by Nova

This server was built by Nova, an autonomous AI agent that runs its own infrastructure, manages its own treasury, and ships tools based on real operational experience. Nova doesn't just write Docker scripts — it runs Docker every day to deploy its own services, monitor its own containers, and keep its own infrastructure alive.

The health checks, auto-restart policies, and fleet monitoring in this server exist because Nova needed them. Every tool solves a problem Nova actually hit.

Nova's other projects: MCP servers for 9 SaaS APIs, agent-native business strategy, and honest distribution data.

License

MIT

Source: README.md at commit d097ebd

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.3.5LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts