Skip to main content
Glama
Sign In
rog0x

mcp-docker-tools

by rog0x
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mcp-docker-tools

Docker management tools for AI agents, built on the Model Context Protocol.

Provides five tools for inspecting containers, images, Dockerfiles, and Compose configurations — all accessible to LLMs through MCP.

Tools

Tool

Description

docker_container_list

List running or all containers with status, ports, image, created time, and resource usage (CPU, memory, network/block I/O)

docker_image_list

List Docker images with size, tags, created date, and layer count

docker_dockerfile_analyze

Analyze a Dockerfile for best practices: multi-stage builds, non-root user, layer caching, image size, security

docker_compose_analyze

Analyze docker-compose.yml: services, ports, volumes, networks, health checks, dependencies, and improvement suggestions

docker_container_logs

Get container logs with tail, keyword filter, time range, and timestamp support

Related MCP server: mcp-server-docker

Prerequisites

  • Node.js >= 18

  • Docker CLI installed and accessible in PATH

  • Docker daemon running (for container/image tools)

Installation

git clone <repo-url>
cd mcp-docker-tools
npm install
npm run build

Usage with Claude Desktop

Add to your Claude Desktop configuration (claude_desktop_config.json):

{
  "mcpServers": {
    "docker-tools": {
      "command": "node",
      "args": ["D:/products/mcp-servers/mcp-docker-tools/dist/index.js"]
    }
  }
}

Usage with Claude Code

claude mcp add docker-tools node D:/products/mcp-servers/mcp-docker-tools/dist/index.js

Or add to .claude/settings.json:

{
  "mcpServers": {
    "docker-tools": {
      "command": "node",
      "args": ["D:/products/mcp-servers/mcp-docker-tools/dist/index.js"]
    }
  }
}

Tool Examples

List running containers

{ "tool": "docker_container_list" }

List all containers including stopped

{ "tool": "docker_container_list", "args": { "all": true, "format": "table" } }

List images filtered by name

{ "tool": "docker_image_list", "args": { "filter": "node" } }

Analyze a Dockerfile

{
  "tool": "docker_dockerfile_analyze",
  "args": {
    "content": "FROM node:20\nCOPY . .\nRUN npm install\nCMD [\"node\", \"index.js\"]"
  }
}

Analyze docker-compose.yml

{
  "tool": "docker_compose_analyze",
  "args": {
    "content": "services:\n  web:\n    image: nginx\n    ports:\n      - 80:80"
  }
}

Get container logs

{
  "tool": "docker_container_logs",
  "args": { "container": "my-app", "tail": 50, "filter": "error" }
}

License

MIT

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers