How to Use the Docker MCP Server for Container Management

Manage Docker containers, images, and volumes through your AI agent using the Docker MCP server. Build, run, and monitor containers with natural language.

DockercontainersDevOpsinfrastructuredeployment

Use the Docker MCP Server for Container Management

The Docker MCP server lets AI agents manage Docker containers, images, volumes, and networks through natural language commands.

Prerequisites

▸Docker Desktop or Docker Engine installed
▸Docker daemon running
▸Node.js 18+

Configuration

json

{
  "mcpServers": {
    "docker": {
      "command": "npx",
      "args": ["-y", "mcp-server-docker"]
    }
  }
}

Available Tools

Container Operations

▸
code
```
list_containers
```
— List running and stopped containers
▸
code
```
create_container
```
— Create new containers from images
▸
code
```
start_container
```
/
code
```
stop_container
```
— Manage container lifecycle
▸
code
```
remove_container
```
— Delete containers
▸
code
```
container_logs
```
— View container output
▸
code
```
container_stats
```
— Get resource usage statistics

Image Operations

▸
code
```
list_images
```
— List available images
▸
code
```
pull_image
```
— Pull images from registries
▸
code
```
build_image
```
— Build images from Dockerfiles
▸
code
```
remove_image
```
— Delete images

Volume & Network

▸
code
```
list_volumes
```
— List Docker volumes
▸
code
```
create_volume
```
— Create new volumes
▸
code
```
list_networks
```
— List Docker networks

Example Workflows

Container Monitoring

code

"Show me all running containers and their resource usage"

Quick Deployment

code

"Pull the latest nginx image and run it on port 8080 with the name 'web-server'"

Cleanup

code

"List all stopped containers and remove them, then remove any unused images"

Development Environment

code

"Create a PostgreSQL container with persistent volume for development, exposed on port 5433"

Security Considerations

▸The Docker MCP server has full Docker access — use with caution
▸Consider running in a restricted Docker context
▸Don't expose on production systems without proper access controls
▸Use Docker's built-in security features (user namespaces, seccomp profiles)