How to Use the Dokku MCP in Pydantic AI

Q: How do I configure the Dokku MCP Server in Pydantic AI?

Install the client library and initialize MCPToolset using your Vinkius HTTP endpoint. Pass the toolset instance directly into the Agent constructor to expose the container management tools.

Q: How does Pydantic AI validate Dokku container logs?

The agent calls getlogs and parses the raw output stream against a Pydantic model. This ensures log entries conform to your defined schema, allowing reliable automated error detection.

Q: Can I run safe database migrations on Dokku using Pydantic AI?

Yes, you can use runcommand to execute migrations inside an isolated container. The agent validates the exit codes and command outputs to ensure the migration completed successfully.

Deploy and monitor self-hosted Dokku applications using this MCP Server inside Pydantic AI workflows.

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 Pydantic AI

Create your Vinkius account to connect Dokku to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe App Provisioning with Pydantic AI

`create_app` sets up the structural network allocations and Nginx reverse-proxy hooks on your host machine before code transfer. The MCP Server ensures your Pydantic AI agent validates the host configuration parameters at runtime, preventing malformed deployment requests from reaching your VPS. When stripping down old setups, `destroy_app` removes the application container and dismantles local DNS routing records. Every step of this teardown is validated against strict Pydantic schemas, ensuring your python code handles the deletion sequence without silent failures.

Manage Configuration Variables with this MCP Server

`list_config` extracts the internal environment dictionary bound to your application, exposing runtime inputs like SQL credentials. The agent parses this dictionary into structured Python models, ensuring your application settings match expected data types. To update variables, `set_config` injects new keys and triggers a rolling deployment of the process cluster. If your agent tries to inject invalid configuration formats, the schema validation fails loudly before the command can disrupt your live app.

Monitor Logs and Scale Containers Safely

`get_logs` streams standard output and error streams directly from your Docker containers to diagnose runtime issues. Pydantic AI parses these log lines into structured error events, allowing your agent to react to specific stack traces programmatically. To handle traffic spikes, `ps_scale` modifies the active replica count for your web and background worker processes. The agent monitors container status using `list_apps`, verifying that the running container count matches your target state.

Setup guide

Set up Dokku MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "dokku-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Dokku tools.",
)

result = await agent.run("List recent Dokku transactions")
print(result.output)

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 Pydantic AI

Install the client library and initialize `MCPToolset` using your Vinkius HTTP endpoint. Pass the toolset instance directly into the `Agent` constructor to expose the container management tools.

The agent calls `get_logs` and parses the raw output stream against a Pydantic model. This ensures log entries conform to your defined schema, allowing reliable automated error detection.

Yes, you can use `run_command` to execute migrations inside an isolated container. The agent validates the exit codes and command outputs to ensure the migration completed successfully.

The framework raises a validation error immediately, halting execution. This prevents your agent from acting on corrupt or malformed container states, protecting your infrastructure.

The server processes your app configurations, environment variables, and container logs within an ephemeral, zero-trust runtime. Your sensitive production secrets are never stored or exposed outside the secure execution context.

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