convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
Knuckles-Team

Portainer Agent MCP

Knuckles-Team/portainer-agent

Gerencie Portainer via Claude com MCP e agent integrado

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP Server que integra Claude com Portainer, permitindo gerenciar containers Docker, stacks, clusters Kubernetes, registries e dispositivos edge via agente IA. Oferece ferramentas otimizadas com roteamento de ações, segurança em nível empresarial e telemetria nativa com OpenTelemetry.

Instalação

$npx convez-ai Knuckles-Team/portainer-agent

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 5 dias
Versão
v2.4.0
Issues abertas
0
Contribuidores
2

Casos de uso

  • Automação de deploy e gerenciamento de containers via IA
  • Operações DevOps conversacionais com Claude
  • Gerenciamento centralizado de infraestrutura containerizada

Veredito

MCP Server maduro e bem arquitetado para quem já usa Portainer e quer orquestração de containers via Claude. Requer familiaridade com Portainer e configuração de credenciais, mas oferece integração profissional com segurança e observabilidade robustas.

README

A tradução para o português deste README ainda está na fila.

Portainer Agent

CLI or API | MCP | Agent

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: 0.29.0

Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, and guidance for provisioning the Portainer platform are maintained in the official documentation.


Overview

Portainer Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Portainer container management — Docker environments, stacks, Kubernetes clusters, registries, users, and edge devices..


Key Features

  • Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
  • Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
  • Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
  • Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the Portainer container management — Docker environments, stacks, Kubernetes clusters, registries, users, and edge devices. API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.


MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool ModuleToggle Env VarEnabled by DefaultDescription & Nested Methods
AuthAUTH_TOOLTrueManage auth operations. Action-routed methods: authenticate, logout, validate_oauth.
EnvironmentENVIRONMENT_TOOLTrueManage environment operations. Action-routed methods: create_endpoint, create_endpoint_group, delete_endpoint, delete_endpoint_group, get_endpoint, get_endpoint_groups, get_endpoints, snapshot_all_endpoints, snapshot_endpoint, update_endpoint.
DockerDOCKER_TOOLTrueManage docker operations. Action-routed methods: docker_create_container, docker_create_exec, docker_create_network, docker_create_volume, docker_get_container_logs, docker_get_container_stats, docker_get_info, docker_get_service_logs, docker_get_stack_logs, docker_get_system_df, docker_get_version, docker_inspect_container, docker_inspect_exec, docker_inspect_image, docker_inspect_network, docker_inspect_service, docker_inspect_volume, docker_list_containers, docker_list_images, docker_list_networks, docker_list_services, docker_list_volumes, docker_remove_container, docker_restart_container, docker_start_container, docker_start_exec, docker_stop_container, get_container_gpus, get_docker_dashboard.
StackSTACK_TOOLTrueManage stack operations. Action-routed methods: create_standalone_stack, create_standalone_stack_from_repo, delete_stack, get_stack, get_stack_file, get_stacks, redeploy_stack_git, start_stack, stop_stack, update_stack.
KubernetesKUBERNETES_TOOLTrueManage kubernetes operations. Action-routed methods: delete_helm_release, get_helm_releases, get_k8s_applications, get_k8s_configmaps, get_k8s_dashboard, get_k8s_events, get_k8s_ingresses, get_k8s_metrics_nodes, get_k8s_namespaces, get_k8s_nodes_limits, get_k8s_secrets, get_k8s_services, get_k8s_volumes, install_helm_chart.
EdgeEDGE_TOOLTrueManage edge operations. Action-routed methods: create_edge_group, create_edge_job, create_edge_stack, delete_edge_group, delete_edge_job, delete_edge_stack, get_edge_groups, get_edge_job, get_edge_jobs, get_edge_stack, get_edge_stacks.
TemplateTEMPLATE_TOOLTrueManage template operations. Action-routed methods: create_custom_template, delete_custom_template, get_custom_template, get_custom_template_file, get_custom_templates, get_helm_templates, get_templates.
UserUSER_TOOLTrueManage user operations. Action-routed methods: create_team, create_user, delete_team, delete_user, get_current_user, get_roles, get_teams, get_user, get_user_tokens, get_users.
RegistryREGISTRY_TOOLTrueManage registry operations. Action-routed methods: create_registry, delete_registry, get_registries, get_registry.
SystemSYSTEM_TOOLTrueManage system operations.
    Actions:
      - 'get_status': Get Portainer instance status.
      - 'get_system_info': Get system information.
      - 'get_system_version': Get Portainer version information.
      - 'get_settings': Get Portainer settings.
      - 'update_settings': Update Portainer settings.
      - 'get_tags': List all tags.
      - 'create_tag': Create a tag.
      - 'delete_tag': Delete a tag.
      - 'get_motd': Get the message of the day.
      - 'backup_portainer': Call backup_portainer Action-routed methods: `backup_portainer`, `create_tag`, `delete_tag`, `get_motd`, `get_settings`, `get_status`, `get_system_info`, `get_system_version`, `get_tags`, `update_settings`. |

    Actions:
      - 'get_status': Get Portainer instance status.
      - 'get_system_info': Get system information.
      - 'get_system_version': Get Portainer version information.
      - 'get_settings': Get Portainer settings.
      - 'update_settings': Update Portainer settings.
      - 'get_tags': List all tags.
      - 'create_tag': Create a tag.
      - 'delete_tag': Delete a tag.
      - 'get_motd': Get the message of the day.
      - 'backup_portainer': Call backup_portainer Action-routed methods: `backup_portainer`, `create_tag`, `delete_tag`, `get_motd`, `get_settings`, `get_status`, `get_system_info`, `get_system_version`, `get_tags`, `update_settings`. |

    Actions:
      - 'get_status': Get Portainer instance status.
      - 'get_system_info': Get system information.
      - 'get_system_version': Get Portainer version information.
      - 'get_settings': Get Portainer settings.
      - 'update_settings': Update Portainer settings.
      - 'get_tags': List all tags.
      - 'create_tag': Create a tag.
      - 'delete_tag': Delete a tag.
      - 'get_motd': Get the message of the day.
      - 'backup_portainer': Call backup_portainer Action-routed methods: `backup_portainer`, `create_tag`, `delete_tag`, `get_motd`, `get_settings`, `get_status`, `get_system_info`, `get_system_version`, `get_tags`, `update_settings`. |

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

  • CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
  • Environment Variables: Define standard environment variables:
    • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
    • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
  • HTTP SSE Request Headers: Pass custom headers during transport initialization:
    • x-mcp-enabled-tools / x-mcp-disabled-tools
    • x-mcp-enabled-tags / x-mcp-disabled-tags
  • HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
    • ?tools=tool1,tool2
    • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.


MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "portainer-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "portainer-agent",
        "portainer-mcp"
      ],
      "env": {
        "PORTAINER_ENDPOINT": "your_portainer_endpoint_here",
        "PORTAINER_USERNAME": "your_portainer_username_here",
        "PORTAINER_PASSWORD": "your_portainer_password_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "portainer-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "portainer-agent",
        "portainer-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "PORTAINER_ENDPOINT": "your_portainer_endpoint_here",
        "PORTAINER_USERNAME": "your_portainer_username_here",
        "PORTAINER_PASSWORD": "your_portainer_password_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "portainer-agent": {
      "url": "http://localhost:8000/portainer-agent/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name portainer-agent-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e PORTAINER_ENDPOINT="your_value" \
  -e PORTAINER_USERNAME="your_value" \
  -e PORTAINER_PASSWORD="your_value" \
  knucklessg1/portainer-agent:latest

Additional Deployment Options

portainer-agent can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

  • Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
  • Remote URL — connect to a server deployed behind Caddy at http://portainer-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export PORTAINER_ENDPOINT="your_value"
export PORTAINER_USERNAME="your_value"
export PORTAINER_PASSWORD="your_value"

# Run the agent server
portainer-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  portainer-agent-mcp:
    image: knucklessg1/portainer-agent:latest
    container_name: portainer-agent-mcp
    hostname: portainer-agent-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  portainer-agent-agent:
    image: knucklessg1/portainer-agent:latest
    container_name: portainer-agent-agent
    hostname: portainer-agent-agent
    restart: always
    depends_on:
      - portainer-agent-mcp
    env_file:
      - ../.env
    command: [ "portainer-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9004
      - MCP_URL=http://portainer-agent-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9004:9004"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9004/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.


Environment Variables

The agent can be configured via the following environment variables:

Core Portainer API Settings

  • PORTAINER_URL: The base HTTP/HTTPS URL of your Portainer instance (e.g., http://localhost:9000). Default: http://localhost:9000.
  • PORTAINER_ENDPOINT: Alternative Portainer socket or connection endpoint path.
  • PORTAINER_USERNAME: The Portainer username to authenticate with. Default: admin.
  • PORTAINER_PASSWORD: The Portainer user password.
  • PORTAINER_TOKEN: Portainer API token (alternative to username/password authentication).
  • PORTAINER_SSL_VERIFY: Whether to verify SSL/TLS certificates when calling the Portainer API (True, False, yes, or no). Default: True.

Transport & Server Settings

  • TRANSPORT: The MCP communication transport protocol. Options: stdio, streamable-http, sse. Default: stdio.
  • HOST: Server interface to bind to (e.g., 0.0.0.0). Default: 0.0.0.0.
  • PORT: Server port to listen on. Default: 8000.

Tool Toggle Switches

Each major tool category can be dynamically enabled or disabled using the following boolean environment variables (options: True, False; default: True):

  • AUTHTOOL: Enable/Disable the Auth tool category.
  • ENVIRONMENTTOOL: Enable/Disable the Environment tool category.
  • DOCKERTOOL: Enable/Disable the Docker tool category.
  • STACKTOOL: Enable/Disable the Stack tool category.
  • KUBERNETESTOOL: Enable/Disable the Kubernetes tool category.
  • EDGETOOL: Enable/Disable the Edge tool category.
  • TEMPLATETOOL: Enable/Disable the Template tool category.
  • USERTOOL: Enable/Disable the User tool category.
  • REGISTRYTOOL: Enable/Disable the Registry tool category.
  • SYSTEMTOOL: Enable/Disable the System tool category.

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

  • Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
  • OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
  • Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

FeatureFunctionalityEnablement
Tool GuardSensitivity inspection with human-in-the-loop validationEnabled by default
Prompt Injection DefenseInput scanning, repetition monitoring, and recursive loop blocksEnabled by default
Context Safety GuardStuck-loop detectors and contextual overflow preemptive alertsEnabled by default

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install portainer-agent[all]

# Using standard pip
python -m pip install portainer-agent[all]

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

PageContents
Installationpip, source, extras, prebuilt Docker image
Deploymentrun the MCP server and A2A agent, Compose, Caddy + Technitium, env config
Usagethe MCP tools, the PortainerApi client, the CLI
Backing Platformdeploy Portainer with Docker
Overviewmodes, environment variables, graph routing
Conceptsconcept registry (CONCEPT:PORT-*)

AGENTS.md is the canonical contributor/agent guidance.


Repository Owners

GitHub followers GitHub User's stars


Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

  • Format code using ruff format .
  • Lint code using ruff check .
  • Validate type-safety with mypy .
  • Execute test suites using pytest
Ver o original no GitHub

Bom para

Relacionados