Use Qovery with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Bring effortless Kubernetes and cloud deployment management to your IDE. List environments, check application states, restart pods, and deploy exact Git commits
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 10 capabilities
The complete Qovery capability set.
These are the exact actions your AI can choose when you ask it to work with Qovery.
01-04
4 capabilities in this set.
Part of 10 available through Qovery.
- 01
List environments
Lists all environments (Production, Staging, etc.) in a project
- 02
Restart application
Performs a zero-downtime rolling restart of a Qovery application
- 03
Get organization
Retrieves details for a specific Qovery organization
- 04
List organizations
Lists all Qovery organizations associated with the token
05-07
3 capabilities in this set.
Part of 10 available through Qovery.
- 05
List projects
Lists all projects within a Qovery organization
- 06
Get application
Retrieves details for a specific Qovery application
- 07
Deploy application
Triggers an immediate deployment of a specific Git commit SHA
08-10
3 capabilities in this set.
Part of 10 available through Qovery.
- 08
Get environment
Retrieves details for a specific Qovery environment
- 09
Get project
Retrieves details for a specific Qovery project
- 10
List applications
Lists all applications running in a specific environment
Observed, not estimated
859ms average. Fast in production.
Qovery is checked daily against the live service.
- Fastest day
- 744ms
- Slowest day
- 1087ms
- 14-day trend
- Slowing+15%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Qovery, so you can see the experience inside your AI.
It does not authenticate your account with Qovery. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Qovery Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_TO2qfcTL6CfQKOXfGLBnMgWFpOD49hykqaFBjirY/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Qovery capabilities are ready to use.
{
"mcpServers": {
"qovery-mcp": {
"url": "https://edge.vinkius.com/vk_preview_TO2qfcTL6CfQKOXfGLBnMgWFpOD49hykqaFBjirY/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Qovery owners ask.
- 01
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.
- 02
Can it restart specific microservices?
Yes. Once you identify the app_id using the list components capabilities, 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.
- 03
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.
- 04
Is this capability safe to run on production?
Yes, but with caveats. Standard queries (like listing environments and getting stats) are entirely read-only. However, capabilities like restart and deploy are mutating operations. Always make sure you instruct your agent precisely and maintain manual approval checkpoints before executing deployment functions.
Explore
More in Developer Tools
Porter PaaS AI Connector
Orchestrate Kubernetes clusters via Porter — manage apps, projects, container tags, and enforce rollouts direc
ViewHarness AI Connector
Automate CI/CD and DevOps workflows via Harness — manage pipelines, executions, and secrets directly from any
ViewCodefresh AI Connector
Manage CI/CD and GitOps via Codefresh — track pipelines, trigger builds, and monitor delivery clusters directl
ViewModal (Serverless AI Infrastructure) AI Connector
Manage serverless compute via Modal — audit active apps, track GPU deployments, and monitor network volumes.
View
Suggestions
Dagger (Programmable CI) AI Connector
Build, test, and deploy using Dagger's programmable CI engine. Execute GraphQL queries, manage containers, and
ViewDrata AI Connector
Automate compliance and security via Drata — monitor controls, track personnel onboarding, audit policies, and
ViewFlightcontrol (AWS PaaS Deployments) AI Connector
Deploy and manage AWS infrastructure via Flightcontrol — list projects, manage environments, and scale service
ViewGoogle Deps.dev Security Hacker AI Connector
Transform your AI into a Senior DevSecOps Engineer. Instantly audit any open-source package, hunt for hidden s
View
