OpenAI · Supported

Codex ships more branches.
Each one needs somewhere to run.

When an agent authors ten times more branches, ten times more infrastructure surrounds them: an environment per pull request, a database per environment, secrets, DNS, teardown. Install eight Qovery skills with one command and Codex can create and destroy all of it on your own cloud account, inside a boundary it does not get to negotiate.

Start free trial Talk with us

What it can do

Eight skills, one install.

The Qovery skills follow the Agent Skills open standard, so OpenAI Codex picks the right one from what you ask. Each also has a slash command if you would rather be explicit.

qovery

/qovery

Entry point. Routes to the right skill and handles quick operations: list, status, stop, restart, logs, clone, scale, custom domains, deployment history.

qovery-onboard

/qovery-onboard

Guided setup. Recommends cloud provider, cluster type, environment structure, RBAC and cost defaults. Handles bring-your-own-Kubernetes and migrations from Heroku, Vercel, Netlify, Render and Railway.

qovery-deploy

/qovery-deploy

Deploys any application to Kubernetes. Analyses the codebase, writes a Dockerfile if one is missing, provisions databases, sets environment variables, then deploys via CLI and API or Terraform.

qovery-troubleshoot

/qovery-troubleshoot

Eight-layer diagnosis across deployment status, build and runtime logs, health checks, env vars, networking, resources and cluster. Matches 20+ error patterns and writes a runbook to .qovery/runbooks/.

qovery-optimize

/qovery-optimize

Analyses historical CPU and memory against allocation across seven optimisation dimensions, estimates external cloud costs, and produces a markdown report plus CSV export.

qovery-speedup

/qovery-speedup

Measures the deployment pipeline stage by stage, classifies each bottleneck as yours or Qovery infrastructure, and proposes Dockerfile and health-check fixes with before and after timings.

qovery-preview

/qovery-preview

Creates a preview environment from a pull request. Detects or builds a blueprint environment, clones it, switches branches, and configures auto-shutdown so it does not run all weekend.

qovery-terraform

/qovery-terraform

Reads an existing Qovery setup from the API and generates HCL for the qovery/qovery provider, imports resources into state, and validates against a test clone before you commit.

Connect it

Two interfaces. Pick both.

The skills deploy. The MCP Server operates what is already running. They are complementary, and most teams end up using both.

Agent Skills

OpenAI Codex is listed as Supported in the Qovery skills compatibility table. The installer places all eight skills where compatible tools discover them, alongside their slash commands.

Then just ask: "Deploy my application with Qovery".

# Install all eight skills, globally
$ curl -fsSL https://skill.qovery.com/install.sh | bash

# Or scope them to the current project only
$ curl -fsSL https://skill.qovery.com/install.sh | bash -s -- --project

MCP Server

The skills deploy. The MCP Server operates what is already running. It is a standard remote MCP endpoint, so configure it the way you configure any MCP server in Codex.

Also published in the MCP registry as com.qovery. Write mode additionally requires write access enabled in the Qovery Console.

# Server URL, read-only by default
https://mcp.qovery.com/mcp

# Read/write, when you explicitly want it
https://mcp.qovery.com/mcp?read_write=true

# Or authenticate with a Qovery API token
https://mcp.qovery.com/mcp?token=YOUR_QOVERY_TOKEN

Read the full setup guide

What it cannot do

The boundary is not in the prompt.
It is in the API underneath.

Instructions in a file are a request. OpenAI Codex can read them, and it can also decide not to follow them. These four properties hold regardless of what the model decides, because none of them are things the model is asked to respect.

Every one of them is checkable in the docs before you trust a word of this page.

Read-only by default

The Qovery MCP Server connects in read-only mode unless you say otherwise. Your agent can list environments, read service state, and tail logs. It cannot change anything.

Write access is two deliberate switches

Writes require read_write=true on the connection URL and a separate write-access setting enabled in the Qovery Console. Neither one is something a model can talk its way into.

Scoped by the RBAC you already run

An agent authenticates with its own API token and inherits the permissions of the role that token was issued under. Agents do not get a parallel access model, and they do not consume user seats.

Every action lands in the audit log

MCP tool calls and API operations are recorded in the Qovery Console audit trail against the token that made them, which is what turns "an agent did something" into an answerable question.

Keep reading

Use case

AI DevOps and CI/CD

OpenAI Codex and Qovery.

Does Qovery work with OpenAI Codex?

Yes. OpenAI Codex is listed as Supported in the Qovery agent skills compatibility table. The skills follow the Agent Skills open standard, so one install command covers Codex along with Claude Code, Cursor, Gemini CLI, OpenCode, VS Code Copilot and 30+ other tools.

How do I connect OpenAI Codex to Qovery?

Run curl -fsSL https://skill.qovery.com/install.sh | bash to install the eight Qovery agent skills, then ask Codex to deploy your application. To manage running infrastructure as well, add https://mcp.qovery.com/mcp as an MCP server in your Codex configuration.

Can Codex create and tear down preview environments?

Yes, through the qovery-preview skill. It detects or creates a blueprint environment, clones it for the pull request, switches the relevant services to the PR branch, and configures an auto-shutdown strategy so preview environments do not idle over the weekend. Teardown is a first-class operation rather than something you remember to do.

How many agents can I run against Qovery?

There is no limit. Agents authenticate with their own API tokens and do not consume user seats. They inherit scoped RBAC permissions and every action is audited exactly like a human user. What they consume is deployment minutes and environments.

Get started

One command, and OpenAI Codex
deploys to your own cloud.

Install the skills, point them at your AWS, GCP, Azure or Scaleway account, and let the agent work inside a boundary you set once. Read-only until you decide otherwise.