An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Portainer to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run and orchestrate your Docker infrastructure through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Portainer.

  1. 01

    List docker containers

    This capability pulls a list of all Docker containers within a specific environment.

  2. 02

    Start docker container

    Use this to trigger the start command for an existing Docker container.

  3. 03

    Add endpoint

    This capability adds a new local or remote Docker or Kubernetes environment to your Portainer setup.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Portainer.

  1. 04

    Authenticate

    This capability handles authentication to your Portainer instance to retrieve a secure JWT token.

  2. 05

    Create docker container

    This capability allows your agent to build and deploy a new Docker container from an image.

  3. 06

    Init admin

    Use this to set up the initial admin password on a fresh Portainer installation.

Real work

What teams actually run

01

Rapid Testing

A developer asks the agent to spin up a specific image to test a new feature locally.

02

Incident Response

A DevOps engineer asks the agent to list containers to identify which service has stopped running.

03

Environment Scaling

An admin uses the agent to add a new remote endpoint to the Portainer setup.

04

Configuration Management

A user deploys a container with specific port mappings using a JSON configuration via the agent.

Automate a task

Put Portainer to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Portainer works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Portainer to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

981ms average. Fast in production.

Portainer is checked daily against the live service.

Daily averagePeak 1228ms
Oct 3Today
Fastest day
717ms
Slowest day
1228ms
14-day trend
Slowing+10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Portainer, so you can see the experience inside your AI.

It does not authenticate your account with Portainer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Portainer Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_vAtyUqdwLcdumic07vZOqC4647ETb6UK429Uaxij/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Portainer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "portainer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_vAtyUqdwLcdumic07vZOqC4647ETb6UK429Uaxij/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Portainer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Portainer owners hand off.

This MCP is built for technical professionals who manage containerized workloads and want to reduce context switching.

  • 01

    DevOps Engineers

    They use the agent to check container statuses and restart services without leaving their terminal.

  • 02

    Developers

    They deploy new testing environments or images directly from their code editor.

  • 03

    System Administrators

    They manage multiple remote environments through a single AI interface.

FAQ

Questions Portainer owners ask.

  • 01

    How do I connect my Portainer instance?

    You need to provide your Portainer URL and your API Key during the setup process in Vinkius.

  • 02

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I manage Kubernetes with this?

    Yes, this MCP allows you to manage environments that include Kubernetes endpoints through Portainer.

  • 04

    Does this work with remote environments?

    Yes, you can add and manage remote Docker or Kubernetes endpoints using the add_endpoint capability.

  • 05

    Is my connection secure?

    The MCP uses Portainer's authentication mechanisms to receive secure JWT tokens for all operations.

  • 06

    How do I see all containers running in a specific environment?

    Use the list_docker_containers capability by providing the specific endpoint_id. The agent will return a list of all containers managed within that Portainer environment.

  • 07

    Can I add a new remote Docker endpoint through the AI?

    Yes! Use the add_endpoint action. You can specify the name, set the type to 2 (Remote), and provide the URL (e.g., tcp://10.0.0.1:2375) to connect a new environment.

  • 08

    Is it possible to deploy a container with specific port mappings?

    Yes. When using create_docker_container, you can provide a config_json string containing standard Docker API parameters like ExposedPorts or HostConfig to define your network and port requirements.

Explore

More in Ship It

Suggestions

Connect Portainer to Claude, Cursor, ChatGPT & more