How do I securely obtain my Qovery API Token?

Sign in to your Qovery Console. Navigate to your **Organization Settings**, then to the **API Tokens** section. Click **Generate Token** (or Add). Give it a brief name, select the desired roles, and click Create. Copy the static string immediately as it won't be shown again, and paste it to authenticate.

Can it restart specific microservices?

Yes. Once you identify the `app_id` using the list components tools, you can instruct your agent to `restart_application`. This triggers a rolling restart exactly as if you clicked 'Restart' on the console. Traffic is routed seamlessly while pods re-initialize.

What does deploy specific Git commit do?

Normally, Qovery auto-deploys a branch. With `deploy_application` you can force Qovery to pull a specific commit ID (SHA) and deploy it immediately to an environment. This is perfect for hotfixes, effectively circumventing prolonged CI loops while ensuring zero downtime.

Is this tool safe to run on production?

Yes, but with caveats. Standard queries (like listing environments and getting stats) are entirely read-only. However, tools like `restart` and `deploy` are mutating operations. Always make sure you instruct your agent precisely and maintain manual approval checkpoints before executing deployment functions.

Qovery MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Qovery
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Qovery through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Qovery "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Qovery?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Qovery MCP Server

Connect your Qovery infrastructure to any AI agent and bring DevOps execution directly into your coding environment.

Pydantic AI validates every Qovery tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Map your Infrastructure — Traverse effortlessly through your Qovery Organizations, Projects, and Environments to build a complete mental map of your deployments
Monitor Applications — Inspect individual microservices, check active replica counts, verify auto-deploy settings, and get real-time status updates without switching contexts to the Qovery dashboard
Take Action via Chat — Trigger zero-downtime rolling restarts to cycle Kubernetes pods and refresh environment variables directly inside Claude or Cursor
Targeted Deployments — Issue a fast-track deploy of a specific Git commit SHA for hotfixes or localized feature testing, all handled friction-free by the LLM

The Qovery MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Qovery to Pydantic AI via MCP

Follow these steps to integrate the Qovery MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Qovery with type-safe schemas

Why Use Pydantic AI with the Qovery MCP Server

Pydantic AI provides unique advantages when paired with Qovery through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Qovery integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Qovery connection logic from agent behavior for testable, maintainable code

Qovery + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Qovery MCP Server delivers measurable value.

Type-safe data pipelines: query Qovery with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Qovery tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Qovery and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Qovery responses and write comprehensive agent tests

Qovery MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Qovery to Pydantic AI via MCP:

deploy_application

Triggers an immediate deployment of a specific Git commit SHA

get_application

Retrieves details for a specific Qovery application

get_environment

Retrieves details for a specific Qovery environment

get_organization

Retrieves details for a specific Qovery organization

get_project

Retrieves details for a specific Qovery project

list_applications

Lists all applications running in a specific environment

list_environments

Lists all environments (Production, Staging, etc.) in a project

list_organizations

Lists all Qovery organizations associated with the token

list_projects

Lists all projects within a Qovery organization

restart_application

Performs a zero-downtime rolling restart of a Qovery application

Example Prompts for Qovery in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Qovery immediately.

"List all Qovery projects and tell me how many there are."

"Check the health and limits of the application in my staging environment."

"Deploy commit 7a8f9b2 to the backend application immediately."

Troubleshooting Qovery MCP Server with Pydantic AI

Common issues when connecting Qovery to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Qovery + Pydantic AI FAQ

Common questions about integrating Qovery MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Qovery MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.