Provides tools for managing Docker containers, images, networks, and volumes via Portainer, including listing, creating, starting, stopping, removing, and inspecting Docker resources.
Enables management of Docker containers, images, networks, and volumes through Portainer's API, including operations like creating, starting, stopping, removing, and inspecting resources.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@VPS MCP Server list all running Docker containers on my VPS"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Servidor MCP (Model Context Protocol) que permite ao modelo de IA gerenciar containers Docker através da API do Portainer.
Este projeto implementa um MCP Server que expõe ferramentas para gerenciar:
Containers: listar, criar, iniciar, parar, remover, inspecionar
Imagens: listar, pull, remover, inspecionar
Networks: listar, criar, remover
Volumes: listar, criar, remover
Configuração: definir/obter credenciais do Portainer
Related MCP server: Portainer MCP Server
# Clonar o repositório
git clone https://github.com/onlitec/VPS-MCP-SERVER.git
cd VPS-MCP-SERVER
# Instalar dependências
npm install
# Configurar variáveis de ambiente
cp .env.example .env
# Editar .env com suas credenciais do Portainer
# Build
npm run build
# Testar conexão
npm run test:connectionAntigravity Setup - Como instalar no Antigravity IDE
Setup Guide - Guia de instalação e configuração
Architecture - Arquitetura do sistema
API Reference - Referência completa das ferramentas MCP
Install Node.js - Como instalar Node.js
Node.js 18+
Acesso a uma instância Portainer
Chave de API do Portainer
MIT
Create a new container
Inputs: image (required), name, env, ports, +3 more.
Create a new Docker network
Inputs: name (required), driver, internal, subnet.
Create a new Docker volume
Inputs: name (required), driver, labels.
Get detailed information about a specific container
Inputs: id (required).
Get detailed information about a specific image
Inputs: id (required).
Get current Portainer configuration (API key is masked for security)
Inputs: no named parameters.
List all Docker containers
Inputs: all.
List available Portainer endpoints to find the correct Endpoint ID. Use this when you get an "Object not found" error during connection test.
Inputs: no named parameters.
List all Docker images
Inputs: all.
List all Docker networks
Inputs: no named parameters.
List all Docker volumes
Inputs: no named parameters.
Pull an image from a registry
Inputs: image (required).
Remove a container
Inputs: id (required), force, volumes.
Remove an image
Inputs: id (required), force.
Remove a Docker network
Inputs: id (required).
Remove a Docker volume
Inputs: name (required), force.
Restart a container
Inputs: id (required), timeout.
Configure Portainer connection settings (URL, API Key, Endpoint ID). The settings are saved to the .env file.
Inputs: url, api_key, endpoint_id.
Start a stopped container
Inputs: id (required).
Stop a running container
Inputs: id (required), timeout.
Test the connection to Portainer API with current configuration
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 21 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools are organized around specific Docker/Portainer resources (containers, images, networks, volumes, Portainer config) and actions (create, get, list, remove, start/stop/restart), making it easy for an agent to select the correct one. For example, 'create_container' vs 'start_container' serve different lifecycle stages.
All tool names follow a consistent verb_noun pattern using snake_case throughout. Verbs like create, get, list, remove, start, stop, restart, pull, test, and set are applied predictably to nouns like container, image, network, volume, and portainer_config. There are no deviations in naming conventions.
With 21 tools, the count is slightly high but reasonable for the server's purpose of managing Docker and Portainer operations. It covers a comprehensive set of actions across multiple resource types, though it might feel heavy compared to a more minimal set. Each tool earns its place by addressing a specific need in container management.
The tool surface provides complete CRUD/lifecycle coverage for Docker resources (containers, images, networks, volumes) and Portainer configuration. It includes creation, retrieval, listing, removal, and operational controls (start/stop/restart), with no obvious gaps. The Portainer tools handle connection testing and configuration, ensuring agents can manage the full workflow.
Give your AI agents trusted access to the full Postman platform.
Manage your own cloud with AI: deploy apps, push and ship custom Docker images, manage resources via your AI agent.
Hosting for AI agents: your AI client deploys Docker apps to live HTTPS URLs over MCP.
Deploy apps from GitHub, read build/runtime logs, and manage your app's users from your AI agent.
