Portainer MCP — Install & Live Demo

Name: Portainer MCP MCP Server
Author: portainer

Why use it

Key features

Multi-environment: Docker, Docker Swarm, Kubernetes, KubeEdge
RBAC respected — agent acts with the API token's permissions
Read logs, exec into containers, restart services
Stack and Helm chart deployment
Works with self-hosted Portainer CE (free) and BE

Live Demo

What it looks like in practice

portainer-mcp.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "portainer-mcp": {
      "command": "uvx",
      "args": [
        "portainer-mcp"
      ]
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "portainer-mcp": {
      "command": "uvx",
      "args": [
        "portainer-mcp"
      ]
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "portainer-mcp": {
      "command": "uvx",
      "args": [
        "portainer-mcp"
      ]
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "portainer-mcp": {
      "command": "uvx",
      "args": [
        "portainer-mcp"
      ]
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "portainer-mcp",
      "command": "uvx",
      "args": [
        "portainer-mcp"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "portainer-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "portainer-mcp"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add portainer-mcp -- uvx portainer-mcp

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use Portainer MCP

Triage which containers are unhealthy across the fleet

👤 DevOps / SRE ⏱ ~15 min intermediate

When to use: You manage many envs through Portainer and need a fleet-wide health snapshot.

Prerequisites

Server/skill installed and authenticated — See repo README

Flow

Inventory

List every environment Portainer manages. For each, count running, exited, and unhealthy containers.✓ Copied

→ Per-env health table
Drill in

For the env with the most unhealthy containers, show the last 50 log lines from each and tell me what's failing.✓ Copied

→ Root-cause hypothesis per container

Outcome: Fleet-wide triage in one chat, prioritized by impact.

Pitfalls

Granting an API token full admin to give Claude broad access is risky — Granting an API token full admin to give Claude broad access is risky — scope to read-only first, then escalate per-task.

Combine with: kubernetes-mcp-server · filesystem

Combinations

Pair with other MCPs for X10 leverage

portainer-mcp + kubernetes-mcp-server

Pair with kubernetes-mcp-server for complementary capabilities

Use this server together with kubernetes-mcp-server to complete a multi-step task.✓ Copied

portainer-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
list_environments	(none)	Discover which clusters Portainer manages	1 API call
list_containers	environment_id, filter	Inventory running containers in one env	1 API call
container_logs	environment_id, container_id, lines	Triage a misbehaving container	1 API call
container_restart	environment_id, container_id	Bounce an unhealthy container	1 API call

Cost & Limits

What this costs to run

API quota: See provider docs for rate limits
Tokens per call: Varies by tool
Monetary: See repo README for pricing details
Tip: Cache tool results and avoid repeated identical calls.

Security

Permissions, secrets, blast radius

Credential storage: Use environment variables; never commit secrets

Data egress: Tool calls go to the provider's API as documented

Troubleshooting

Common errors and fixes

401 Unauthorized

Create an API token in Portainer (User settings → Access tokens) and set PORTAINER_API_KEY.

Verify: list_environments returns a list

Endpoint not found

Token must have access to the requested environment. Check team/endpoint permissions in Portainer.

Verify: list_environments returns the target env

Alternatives

Portainer MCP vs others

Alternative	When to use it instead	Tradeoff
Rancher MCP	You're a Rancher shop	Different feature set; Portainer is broader on plain Docker

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills