About Portainer MCP Server
Portainer MCP Server lets AI assistants manage Docker resources through the Portainer API. It covers container, image, network, and service operations, including logs and container resource limits.
Key features
- 01Create, start, and remove containers
- 02Fetch container and service logs
- 03List and clean up images
- 04Inspect Docker networks
- 05Manage container resource limits
Use cases
- 01Check container status and logs
- 02Start or remove a container
- 03Clear unused images or build cache
- 04Inspect networks and services
MCP support
The MCP server exposes tools for Docker container, image, network, and service management through Portainer. MCP clients can also retrieve logs and update container resource limits.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPortainer MCP Server
A Model Context Protocol (MCP) server implementation for Portainer, enabling AI assistants to interact with Docker containers and services through Portainer's API.
Features
- Docker container management (create, start, delete, fetch logs)
- Docker image management (fetch, delete unused, clear build cache)
- Docker network operations (inspect, fetch)
- Docker service management (fetch, logs)
- Resource limit management for containers
Project Structure
portainer-ce-mcp/
├── src/
│ ├── api/
│ │ └── portainer.ts # Portainer API integration
│ ├── constants/
│ │ └── index.ts # Tool names and other constants
│ ├── types/
│ │ └── index.ts # TypeScript type definitions
│ └── main.ts # Main server implementation
├── package.json # Project dependencies
├── package-lock.json # Dependency lock file
├── deno.json # Deno configuration
└── README.md # Project documentation
Prerequisites
- Deno
- Portainer instance with API access
- Docker installed and running
Installation
- Clone the repository:
git https://github.com/BirajMainali/poratiner-ce-mcp-server.git
cd portainer-ce-mcp
Configuration
The server requires the following environment variables:
PORTAINER_URL: The URL of your Portainer instancePORTAINER_API_KEY: Your Portainer API keyPORTAINER_ENV_ID: Your Poratiner Environment Id
API Tools
The server provides the following tools for AI assistants:
Container Management
FETCH_DOCKER_CONTAINERS: List all containersCREATE_DOCKER_CONTAINER: Create a new containerSTART_DOCKER_CONTAINER: Start a containerDELETE_DOCKER_CONTAINER: Remove a containerFETCH_CONTAINER_LOGS: Get container logsUPDATE_CONTAINER_RESOURCE_LIMITS: Update container resourcesDELETE_STOPPED_CONTAINERS: Clean up stopped containers
Image Management
FETCH_IMAGES: List all imagesDELETE_IMAGE_BUILD_CACHE: Clear build cacheDELETE_UNUSED_IMAGES: Remove unused images
Network Operations
FETCH_NETWORKS: List all networksINSPECT_NETWORK: Get network details
Service Management
FETCH_SERVICES: List all servicesFETCH_SERVICE_LOG: Get service logs
Development
Building
deno compile --allow-env --allow-read --allow-net --env-file=.env src/main.ts
Inspect MCP Server
npx @modelcontextprotocol/inspector deno run --allow-env --allow-read --allow-net --env-file=.env src/main.ts
MCP Config
{
"mcpServers": {
"poratiner": {
"command": "C:\\MCP\\portainer-ce-mcp\\src.exe", // use executable path
"args": [
"y"
]
}
}
}
License
MIT
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
