Skip to main content

Portainer container management — Docker environments, stacks, Kubernetes clusters, registries, users, and edge devices.

Project description

Portainer Agent - A2A | AG-UI | MCP

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub

GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues

GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 0.8.0

Overview

Portainer Agent MCP Server + A2A Agent

Agent package for Portainer container management — Docker environments, stacks, Kubernetes clusters, registries, users, and edge devices.

This repository is actively maintained - Contributions are welcome!

MCP

Using as an MCP Server

The MCP Server can be run in two modes: stdio (for local testing) or http (for networked access).

Environment Variables

  • PORTAINER_URL: The URL of the target Portainer service.
  • PORTAINER_TOKEN: The API token or access token.
  • PORTAINER_SSL_VERIFY: Verify SSL certificate (default: True).

Run in stdio mode (default):

export PORTAINER_URL="http://localhost:9000"
export PORTAINER_TOKEN="your_token"
portainer-mcp --transport "stdio"

Run in HTTP mode:

export PORTAINER_URL="http://localhost:9000"
export PORTAINER_TOKEN="your_token"
portainer-mcp --transport "http" --host "0.0.0.0" --port "8000"

A2A Agent

Run A2A Server

export PORTAINER_URL="http://localhost:9000"
export PORTAINER_TOKEN="your_token"
portainer-agent --provider openai --model-id gpt-4o --api-key sk-...

Docker

Build

docker build -t portainer-agent .

Run MCP Server

docker run -d \
  --name portainer-agent \
  -p 8000:8000 \
  -e TRANSPORT=http \
  -e PORTAINER_URL="http://your-service:9000" \
  -e PORTAINER_TOKEN="your_token" \
  knucklessg1/portainer-agent:latest

Deploy with Docker Compose

services:
  portainer-agent:
    image: knucklessg1/portainer-agent:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=http
      - PORTAINER_URL=http://your-service:9000
      - PORTAINER_TOKEN=your_token
    ports:
      - 8000:8000

Configure mcp.json for AI Integration (e.g. Claude Desktop)

{
  "mcpServers": {
    "portainer": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "portainer-agent",
        "portainer-mcp"
      ],
      "env": {
        "PORTAINER_URL": "http://your-service:9000",
        "PORTAINER_TOKEN": "your_token"
      }
    }
  }
}

Install Python Package

python -m pip install portainer-agent
uv pip install portainer-agent

Repository Owners

GitHub followers GitHub User's stars

Graph Architecture

This agent uses pydantic-graph orchestration for intelligent routing and optimal context management.

---
title: Portainer Agent Graph Agent
---
stateDiagram-v2
  [*] --> RouterNode: User Query
  RouterNode --> DomainNode: Classified Domain
  RouterNode --> [*]: Low confidence / Error
  DomainNode --> [*]: Domain Result
  • RouterNode: A fast, lightweight LLM (e.g., nvidia/nemotron-3-super) that classifies the user's query into one of the specialized domains.
  • DomainNode: The executor node. For the selected domain, it dynamically sets environment variables to temporarily enable ONLY the tools relevant to that domain, creating a highly focused sub-agent (e.g., gpt-4o) to complete the request. This preserves LLM context and prevents tool hallucination.

MCP Configuration Examples

1. Standard IO (stdio) Deployment

{
  "mcpServers": {
    "portainer-agent": {
      "command": "uv",
      "args": [
        "run",
        "portainer-mcp"
      ],
      "env": {
        "AGENT_DESCRIPTION": "<YOUR_AGENT_DESCRIPTION>",
        "AGENT_SYSTEM_PROMPT": "<YOUR_AGENT_SYSTEM_PROMPT>",
        "AUTHTOOL": "True",
        "DEFAULT_AGENT_NAME": "<YOUR_DEFAULT_AGENT_NAME>",
        "DOCKERTOOL": "True",
        "EDGETOOL": "True",
        "ENVIRONMENTTOOL": "True",
        "KUBERNETESTOOL": "True",
        "PORTAINER_TOKEN": "<YOUR_PORTAINER_TOKEN>",
        "PORTAINER_URL": "<YOUR_PORTAINER_URL>",
        "PORTAINER_VERIFY": "<YOUR_PORTAINER_VERIFY>",
        "REGISTRYTOOL": "True",
        "STACKTOOL": "True",
        "SYSTEMTOOL": "True",
        "TEMPLATETOOL": "True",
        "USERTOOL": "True"
      }
    }
  }
}

2. Streamable HTTP (SSE) Deployment

{
  "mcpServers": {
    "portainer-agent": {
      "command": "uv",
      "args": [
        "run",
        "portainer-mcp",
        "--transport",
        "http",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ],
      "env": {
        "AGENT_DESCRIPTION": "<YOUR_AGENT_DESCRIPTION>",
        "AGENT_SYSTEM_PROMPT": "<YOUR_AGENT_SYSTEM_PROMPT>",
        "AUTHTOOL": "True",
        "DEFAULT_AGENT_NAME": "<YOUR_DEFAULT_AGENT_NAME>",
        "DOCKERTOOL": "True",
        "EDGETOOL": "True",
        "ENVIRONMENTTOOL": "True",
        "KUBERNETESTOOL": "True",
        "PORTAINER_TOKEN": "<YOUR_PORTAINER_TOKEN>",
        "PORTAINER_URL": "<YOUR_PORTAINER_URL>",
        "PORTAINER_VERIFY": "<YOUR_PORTAINER_VERIFY>",
        "REGISTRYTOOL": "True",
        "STACKTOOL": "True",
        "SYSTEMTOOL": "True",
        "TEMPLATETOOL": "True",
        "USERTOOL": "True"
      }
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

portainer_agent-0.8.0.tar.gz (270.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

portainer_agent-0.8.0-py3-none-any.whl (722.1 kB view details)

Uploaded Python 3

File details

Details for the file portainer_agent-0.8.0.tar.gz.

File metadata

  • Download URL: portainer_agent-0.8.0.tar.gz
  • Upload date:
  • Size: 270.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for portainer_agent-0.8.0.tar.gz
Algorithm Hash digest
SHA256 ffedb658ace3c4059c065276cdac8c7c4094c4d2abd9f1ac313f5cf4d136485c
MD5 7842e26793a12afe8e8e5b4282ec1561
BLAKE2b-256 508bcca424dc7abeb505ff8996da5f7bcb5e16e415e9403fab95c2cc0fbd71b3

See more details on using hashes here.

File details

Details for the file portainer_agent-0.8.0-py3-none-any.whl.

File metadata

File hashes

Hashes for portainer_agent-0.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c376655ffb4a3837f82310b0225a9465cf28dc86466f7b0fd9473fbb81abdd56
MD5 00bdf4589328c711bd98099312310445
BLAKE2b-256 99e2c412e252bd5368c99d6dbd3305fcbb7430eb71fc040c645940d7df4dcd11

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page