Portainer MCP
[](https://goreportcard.com/report/github.com/portainer/portainer-mcp)
Ever wished you could just ask Portainer what's going on?
Now you can! Portainer MCP connects your AI assistant directly to your Portainer environments. Manage Portainer resources such as users and environments, or dive deeper by executing any Docker or Kubernetes command directly through the AI.
Overview
Portainer MCP is a work in progress implementation of the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) for Portainer environments. This project aims to provide a standardized way to connect Portainer's container management capabilities with AI models and other services.
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs (Large Language Models). Similar to how USB-C provides a standardized way to connect devices to peripherals, MCP provides a standardized way to connect AI models to different data sources and tools.
This implementation focuses on exposing Portainer environment data through the MCP protocol, allowing AI assistants and other tools to interact with your containerized infrastructure in a secure and standardized way.
See the [Portainer Version Support](#portainer-version-support) and [Supported Capabilities](#supported-capabilities) sections for more details on compatibility and available features.
*Note: This project is currently under development.*
It is currently designed to work with a Portainer administrator API token.
Installation
You can download pre-built binaries for Linux (amd64) and macOS (arm64) from the [**Latest Release Page**](https://github.com/portainer/portainer-mcp/releases/latest). Find the appropriate archive for your operating system and architecture under the "Assets" section.
**Download the archive:**
You can usually download this directly from the release page. Alternatively, you can use `curl`. Here's an example for macOS (ARM64) version `v0.2.0`:
(Linux AMD64 binaries are also available on the release page.)
**(Optional but recommended) Verify the checksum:**
First, download the corresponding `.md5` checksum file from the release page.
Example for macOS (ARM64) `v0.2.0`:
(For Linux, you can use `md5sum -c <checksum_file_name>.md5`)
If the verification command outputs "OK", the file is intact.
**Extract the archive:**
This will extract the `portainer-mcp` executable.
**Move the executable:**
Move the executable to a location in your `$PATH` (e.g., `/usr/local/bin`) or note its location for the configuration step below.
Usage
With Claude Desktop, configure it like so:
Replace `[IP]`, `[PORT]` and `[TOKEN]` with the IP, port and API access token associated with your Portainer instance.
[!NOTE] By default, the tool looks for "tools.yaml" in the same directory as the binary. If the file does not exist, it will be created there with the default tool definitions. You may need to modify this path as described above, particularly when using AI assistants like Claude that have restricted write permissions to the working directory.
Tool Customization
By default, the tool definitions are embedded in the binary. The application will create a tools file at the default location if one doesn't already exist.
You can customize the tool definitions by specifying a custom tools file path using the `-tools` flag:
The default tools file is available for reference at `internal/tooldef/tools.yaml` in the source code. You can modify the descriptions of the tools and their parameters to alter how AI models interpret and decide to use them. You can even decide to remove some tools if you don't wish to use them.
[!WARNING] Do not change the tool names or parameter definitions (other than descriptions), as this will prevent the tools from being properly registered and functioning correctly.
Read-Only Mode
For security-conscious users, the application can be run in read-only mode. This mode ensures that only read operations are available, completely preventing any modifications to your Portainer resources.
To enable read-only mode, add the `-read-only` flag to your command arguments:
When using read-only mode:
- Only read tools (list, get) will be available to the AI model
- All write tools (create, update, delete) are not loaded
- The Docker proxy requests tool is not loaded
- The Kubernetes proxy requests tool is not loaded
Portainer Version Support
This tool is pinned to support a specific version of Portainer. The application will validate the Portainer server version at startup and fail if it doesn't match the required version.
[object Object] | [object Object] |
[object Object] | [object Object] |
[object Object] | [object Object] |
[object Object] | [object Object] |
Supported Capabilities
The following table lists the currently (latest version) supported operations through MCP tools:
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
[object Object] | [object Object] | [object Object] | [object Object] |
Development
Code Statistics
The repository includes a helper script `cloc.sh` to calculate lines of code and other metrics for the Go source files using the `cloc` tool. You might need to install `cloc` first (e.g., `sudo apt install cloc` or `brew install cloc`).
Run the script from the repository root to see the default summary output:
Refer to the comment header within the `cloc.sh` script for details on available flags to retrieve specific metrics.