Dokku Mcp Server

What is Dokku MCP Server?

Dokku MCP Server is a Model Context Protocol (MCP) server written in Go that exposes Dokku’s management capabilities to Large Language Models (LLMs). It allows AI assistants to interact with and manage a Dokku instance programmatically.

How to use Dokku MCP Server?

Download the prebuilt binary or build from source, configure SSH access to your Dokku host via a YAML file or environment variables, then add the server’s command to your MCP client configuration (e.g., .cursor/mcp.json or claude_desktop_config.json). Run dokku-mcp to start the server, or use make inspect for a quick MCP Inspector playground.

Key features of Dokku MCP Server

• MCP-compatible interface for Dokku management
• Implemented commands for apps, config, deployments, plugins, proxies, SSH keys, and more
• Supports async deployments with IDs and background status
• Plugin-based architecture following Domain-Driven Design
• Transport modes: stdio (default) and SSE (HTTP-based)
• Security via blacklist environment variable DOKKU_MCP_SECURITY_BLACKLIST
• Configuration via YAML file or environment variables (prefix DOKKU_MCP_)

Use cases of Dokku MCP Server

• Let an AI assistant create, deploy, and scale Dokku apps
• Automate environment variable configuration and troubleshooting
• Manage plugins (list, install, uninstall, enable, disable, update)
• Retrieve server info, app lists, and deployment logs
• Integrate Dokku into MCP-supporting IDEs like Cursor, Claude Code, or Goose

FAQ from Dokku MCP Server

What prerequisites are needed to use Dokku MCP Server?

You need a running Dokku instance and SSH access to it (e.g., SSH host, port, user, and key). For building from source, Go 1.25 or later is required.

Can I run a local Dokku instance for development?

Yes, the project provides a Docker-based setup: run make setup-dokku and make dokku-start to spin up a local Dokku container for testing.

What Dokku commands are currently implemented?

The server supports a wide range: apps:create, apps:destroy, apps:info, apps:list, config:show, config:set, ps:scale, logs, plugin:*, ssh-keys:list, registry:logout, and many more. Some commands like ssh-keys:add and registry:login are marked as missing/partial.

Is this project ready for production use?

No, it is in early development (v0.3.0). Breaking changes are expected, and it is not recommended for production use.

What transport modes does the server support?

It supports stdio (default, for direct process communication) and sse (Server-Sent Events, for HTTP-based web clients). CORS configuration options are available for SSE mode.