Skip to main content
Glama

Docker MCP 🐳

Gerencie containers Docker diretamente através do Claude usando o Model Context Protocol (MCP)

🚀 Instalação (Containerizado)

Método Recomendado - Docker:

# 1. Navegue até o diretório
cd /root/.claude/docker-mcp-py

# 2. Construa a imagem (se ainda não existe)
docker build -t docker-mcp-py:latest .

# 3. Adicione ao Claude
claude mcp add docker-mcp-py -s user -- /root/.claude/docker-mcp-py/start-docker.sh

# 4. Verifique
claude mcp list

Método Alternativo - Python Local (Legado):

# Use apenas se preferir não usar Docker
claude mcp add docker-mcp-py -s user -- \
  /root/.claude/docker-mcp-py/venv/bin/python3 \
  /root/.claude/docker-mcp-py/docker_mcp_server.py

⚠️ IMPORTANTE:

  • RECOMENDADO: Use o método containerizado com start-docker.sh

  • Container tem acesso total ao Docker do host via socket

  • Não precisa mais do venv se usar o método Docker

Related MCP server: Docker MCP Server

🚀 Ferramentas Disponíveis (14 total)

  • create-container

  • list-containers

  • stop-container

  • start-container

  • remove-container

  • get-logs

  • get-container-stats

  • list-images

  • pull-image

  • remove-image

  • list-volumes

  • remove-volume

  • deploy-compose

  • compose-down

🔧 Solução de Problemas

Se aparecer "docker-mcp-py: failed":

Veja o arquivo SOLUCAO_DEFINITIVA_DOCKER_MCP.md

Para reinstalar:

claude mcp remove docker-mcp-py -s user
claude mcp add docker-mcp-py -s user -- /root/.claude/docker-mcp-py/venv/bin/python3 /root/.claude/docker-mcp-py/docker_mcp_server.py

📁 Arquivos Importantes

Arquivos Docker (Novo):

  • Dockerfile - Define a imagem Docker do MCP

  • requirements.txt - Dependências Python

  • start-docker.sh - Script para iniciar via Docker

  • .dockerignore - Arquivos ignorados no build

  • CONTAINERIZATION.md - Documentação da containerização

Arquivos Originais:

  • docker_mcp_server.py - Script principal do servidor

  • src/ - Código fonte do servidor MCP

  • setup.sh - Instalador de dependências (legado)

🔄 Migração para Docker

  1. Teste o container: ./start-docker.sh

  2. Se funcionar bem: rm -rf venv/

  3. Atualize o Claude:

    claude mcp remove docker-mcp-py -s user
    claude mcp add docker-mcp-py -s user -- /root/.claude/docker-mcp-py/start-docker.sh

Versão: 0.4.0 | Status: ✅ Containerizado

F
license - not found
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    F
    maintenance
    Allows Claude and other AI assistants to interact with Docker through the MCP protocol, enabling container and image management including listing, running, stopping, and pulling Docker resources.
    6
    91
    4
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    Enables AI assistants like Claude to manage Docker containers, images, and Docker Compose deployments through the Model Context Protocol. Provides secure container lifecycle management, image operations, and multi-host Docker server connections.
    356
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    Enables AI assistants to manage Docker containers, images, networks, volumes, and Compose services through the Model Context Protocol. It supports system operations, command execution within containers, and integration with Docker Hub and GitHub Container Registry.
    135
    2
    MIT

View all related MCP servers

Related MCP Connectors

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

  • Free public MCP for AI agents — 193 tools, 44 workflows. No API key.

  • Build, validate, and deploy multi-agent AI solutions from any AI environment.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/diegofornalha/docker-mcp-py'

If you have feedback or need assistance with the MCP directory API, please join our Discord server