How to Use the Dokku MCP in VS Code Copilot

Q: How do we share Dokku access across our team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root containing the server settings. When team members open the workspace in VS Code, Copilot automatically loads the tools for managing your self-hosted apps.

Q: Can VS Code Copilot restart a failing Dokku process?

Yes. Copilot can run psrestart to bounce your application containers, and then run getlogs to check if the process restarted successfully.

Q: Can we scale our web processes from VS Code Copilot?

Yes, Copilot can call psscale to adjust your container count, allowing you to manage your application's capacity directly from the editor.

Manage your team's self-hosted Dokku deployments and environments directly inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dokku MCP to VS Code Copilot

Create your Vinkius account to connect Dokku to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Dokku with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-wide Dokku management with this MCP Server

`list_apps` displays all active Git-push applications running on your shared Dokku host, giving your entire team visibility into current deployments. By committing the configuration to your repository, every developer gets instant access to these tools. When testing new microservices, `create_app` provisions the host boundary and configures Nginx or Traefik proxies. If an environment is no longer needed, `destroy_app` tears down the containers and detaches volumes to free up VM resources.

Safe environment updates from VS Code Copilot

`set_config` injects updated environment variables into your production containers, triggering a rolling deployment to avoid service interruptions. Copilot can generate secure tokens and apply them to your server without you leaving your workspace. This MCP Server allows Copilot to generate secure tokens and apply them to your server without you leaving your workspace. Developers can use `list_config` to verify active configurations, or `unset_config` to remove obsolete variables.

Process control and ephemeral container execution

`ps_scale` adjusts container counts for web and worker processes, allowing Copilot to scale your infrastructure up to ten replicas. If a service becomes unresponsive, `ps_restart` executes a zero-downtime container bounce to restore performance. `run_command` launches a one-off ephemeral container to run database migrations or seed scripts safely away from active web traffic. Copilot monitors the execution and streams the output directly into your VS Code chat window.

Setup guide

Set up Dokku MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Dokku MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Dokku tools listed. Try asking: "List my recent Dokku transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "dokku-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dokku. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Dokku now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Dokku MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root containing the server settings. When team members open the workspace in VS Code, Copilot automatically loads the tools for managing your self-hosted apps.

Yes. Copilot can run `ps_restart` to bounce your application containers, and then run `get_logs` to check if the process restarted successfully.

Ask Copilot to run your migration command, and it will execute `run_command` to spin up an ephemeral container with your production image layers.

Yes, Copilot can call `ps_scale` to adjust your container count, allowing you to manage your application's capacity directly from the editor.

The server runs locally on your developer machines or within a secure enterprise sandbox, communicating directly with your VM over SSH. Your production logs and environment variables are never transmitted to or cached by any external server.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript