Docker MCP server
✓ VerifiedAllows AI agents to manage Docker containers, monitor health, orchestrate Compose stacks, and stream logs through a local socket connection.
Also known as friendlygeorge/docker-mcp-server, docker-mcp-server, @supernova123/docker-mcp-server
- Stars
- 4
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.3.5
- Last commit
- Jun 24, 2026
- License
- MIT
What is Docker MCP?
Docker allows AI agents to manage Docker containers, monitor health, orchestrate Compose stacks, and stream logs through a local socket connection.
Summary generated from the project's README
About Docker MCP server
Managing containerized environments and maintaining service uptime from within an AI agent is what this server enables. It provides a direct connection to your local Docker socket, meaning it requires no API keys, no cloud accounts, and no paid subscriptions to function. Developers can use it to orchestrate entire Compose stacks, monitor container health, and manage service lifecycles through a single interface.
Unlike basic CRUD implementations, this server includes specialized tools for fleet monitoring and self-healing infrastructure. It allows agents to perform HTTP, TCP, or exec probes to verify readiness, set restart policies to handle crashes, and stream logs using timestamp filters. By using commands like fleet_status, watch_events, and search_logs, an agent can move beyond simple deployment to active operational management of a local container environment.
What you can do with it
- 1Automated deployment and rollbackAn agent can deploy a new container version, verify its health via a specific path, and automatically revert to a previous image if the readiness check fails.
- 2Self-healing infrastructure managementYou can instruct an agent to monitor container health and automatically restart services that have crashed to prevent downtime.
- 3Orchestrating complex Compose stacksAn agent can manage the entire lifecycle of a multi-service application including bringing up services, monitoring their states, and cleaning up resources.
- 4Remote container debuggingAn agent can perform diagnostics by executing commands inside a container and streaming filtered logs without needing SSH access.
Written from the project's README. Every use case is checked against a quote from it.
How to install Docker MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Docker MCP in Claude Code
$ claude mcp add docker-mcp-server -- npx -y @supernova123/docker-mcp-serverInstall Docker MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"docker-mcp-server": {
"command": "npx",
"args": [
"-y",
"@supernova123/docker-mcp-server"
]
}
}
}Install Docker MCP in VS Code
.vscode/mcp.json
{
"servers": {
"docker-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@supernova123/docker-mcp-server"
]
}
}
}Install Docker MCP in VS Code CLI
$ code --add-mcp '{"name":"docker-mcp-server","type":"stdio","command":"npx","args":["-y","@supernova123/docker-mcp-server"]}'Install Docker MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"docker-mcp-server": {
"command": "npx",
"args": [
"-y",
"@supernova123/docker-mcp-server"
]
}
}
}Install Docker MCP in Codex
$ codex mcp add docker-mcp-server -- npx -y @supernova123/docker-mcp-serverInstall Docker MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.docker-mcp-server] command = "npx" args = ["-y", "@supernova123/docker-mcp-server"]
Install Docker MCP in Gemini CLI
$ gemini mcp add -s user docker-mcp-server npx -- -y @supernova123/docker-mcp-serverInstall Docker MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"docker-mcp-server": {
"command": "npx",
"args": [
"-y",
"@supernova123/docker-mcp-server"
]
}
}
}Configuration
DOCKER_HOSTDocker socket path (default: /var/run/docker.sock)
| Name | Description | |
|---|---|---|
| DOCKER_HOST | Docker socket path (default: /var/run/docker.sock) |
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablefriendlygeorge/docker-mcp-server is public and reachablegithub.com/friendlygeorge/docker-mcp-server ↗Pass
- Package names this repository as its source@supernova123/docker-mcp-server names friendlygeorge/docker-mcp-server as sourcenpmjs.com/package/@supernova123/docker-mcp-server ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-06-24github.com/friendlygeorge/docker-mcp-server ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @supernova123/docker-mcp-serverPass
- No critical advisory in the package or its dependencies160 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub@supernova123/docker-mcp-server
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, uptime
5. Watch: watch_events(window=60) → detect crashes, restarts, health changes
6. 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
Docker MCP questions
How do I add Docker MCP to Claude Code?
Run claude mcp add docker-mcp-server -- npx -y @supernova123/docker-mcp-server in your terminal. Add --scope user to make it available in every project.
How do I add Docker MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does this server require an API key or a paid plan?
No, it runs locally and connects directly to your Docker socket without needing API keys, cloud services, or monthly fees.