Qovery MCP. Manage deployments and environments from your chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Qovery connects your Kubernetes and cloud infrastructure to any AI agent. You can list environments, check application status, restart pods, and deploy specific Git commits right from your chat window.
It gives DevOps control without needing to open the Qovery dashboard.
What your AI agents can do
Deploy application
Triggers an immediate deployment of a specific Git commit SHA to an application.
Get application
Retrieves detailed information for a specified Qovery application instance.
Get environment
Gets specific details and status for a designated Qovery environment (e.g., Staging).
List all organizations, projects, and environments to build a full map of your deployed services.
Get real-time details on individual microservices, including active replica counts and resource limits.
Initiate an immediate deployment using a specific Git commit SHA for hotfixes or testing.
Cycle Kubernetes pods to perform a zero-downtime rolling restart of any connected application.
Retrieve specific configuration details for environments, like Staging or Production.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Qovery MCP Server: 10 Tools for Cloud Operations
These ten tools let you query, list, manage, and deploy resources across all your Qovery environments using simple chat commands.
019d75fbdeploy application
Triggers an immediate deployment of a specific Git commit SHA to an application.
019d75fbget application
Retrieves detailed information for a specified Qovery application instance.
019d75fbget environment
Gets specific details and status for a designated Qovery environment (e.g., Staging).
019d75fbget organization
Retrieves high-level details about the configured Qovery organization.
019d75fbget project
Gets specific details for a defined Qovery project within an organization.
019d75fblist applications
Lists all applications currently running within a single, specified environment.
019d75fblist environments
Returns a list of available deployment environments (Prod, Staging) for a given project.
019d75fblist organizations
Provides a list of all Qovery organizations associated with the API token.
019d75fblist projects
Returns a complete list of projects within your connected Qovery organization.
019d75fbrestart application
Performs a zero-downtime rolling restart on a targeted Qovery application.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Qovery, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're gonna connect your Kubernetes setup and cloud infrastructure directly to your AI agent using this server. You get full DevOps control without ever having to open the Qovery dashboard, which is a massive time-saver.
Mapping Your Infrastructure
Want a complete map of everything you've deployed? You start by calling list_organizations to see every Qovery organization associated with your API token. From there, you use list_projects to get a rundown of all the projects within that connected organization. If you need more detail on one project, run get_project.
To map out environments and services, you can call list_environments, which returns a list like Prod or Staging for any given project. For full visibility into what's running in a specific environment—say, your QA setup—you use list_applications to see every app deployed there.
Checking Status & Details
Checking if things are running right is simple. You can get high-level details on the entire organization using get_organization, or you can drill down into specific configuration details for an environment with get_environment. If you need to know exactly what's happening with one service, you use get_application to pull detailed information about a specific Qovery application instance.
This lets you check things like the active replica count and resource limits right from your chat window; it shows you the current health status of any microservice.
Taking Action & Fixing Stuff
When something breaks, you don't need to log in or mess with a dashboard GUI. You just tell your agent what needs doing. Need an immediate hotfix? Use deploy_application to trigger an instant deployment using a specific Git commit SHA—perfect for testing or patching critical bugs fast. If the service is acting weird, you can run restart_application.
This performs a zero-downtime rolling restart on any connected application, cycling those Kubernetes pods and getting things back online without interrupting users.
This server handles all that complexity within your chat flow. Your AI client calls these specific tools—like calling get_project to check details or running list_applications to see the current services—and you get the results instantly, no context switching required.
How Qovery MCP Works
- 1 Supply your Qovery Organization API Token to the server.
- 2 Tell your agent the full scope of what you want to check (e.g., 'Show me all projects in the production environment').
- 3 The agent runs the necessary tools (
list_projects,get_environment) and gives you the result directly.
The bottom line is: you manage your clusters and trigger deploys across environments without ever leaving your coding or chat interface.
Who Is Qovery MCP For?
Platform Engineers, Full-stack Developers, and Engineering Leads. This server is for anyone who gets tired of clicking through multiple dashboards—especially when they need to hotfix a critical bug at 2 AM. You're the person who needs immediate visibility into cluster health without losing flow state.
Copies a commit SHA and tells their agent, 'Deploy this fix to dev,' rather than manually running deployment scripts.
Uses list_environments and get_project to audit cluster configs while writing infrastructure-as-code or debugging complex setups.
Checks if mission-critical apps are properly scaled across multiple zones by querying replica counts via the agent.
What Changes When You Connect
- Check app health without context switching. You can use
list_applicationsto see replica counts, resource limits, and status updates for every microservice in an environment. - Hotfix deployment is instant. Just provide a Git commit SHA and call
deploy_application. The agent handles the full rollout process so you don't have to run CLI commands manually. - Keep services fresh with minimal risk. Use
restart_applicationto trigger zero-downtime rolling restarts, cycling pods and refreshing environment variables without taking the service offline. - See your entire infrastructure at a glance. Tools like
list_organizationsandlist_projectslet you map out every deployment layer before you write a line of code. - Targeted troubleshooting is fast. When something breaks in Staging, use
get_environmentto pull specific details on the issue without navigating through 10 different tabs.
Real-World Use Cases
Urgent Bug Fix in Production
A developer finds a critical bug. Instead of creating an emergency ticket and manually running deployment commands, they copy the commit SHA and ask their agent to use deploy_application on the production environment immediately. The agent executes the tool and confirms the new status.
Auditing Environment Drift
An engineer suspects Staging isn't matching Production configs. They run list_environments to confirm both exist, then use get_environment for each one to pull resource limits and replica counts side-by-side in the chat.
Pre-Release Health Check
Before a major launch, an engineer needs to ensure all services are healthy. They use list_applications across multiple environments, checking for any app that is marked as 'unhealthy' or doesn't report expected replica counts.
Routine Maintenance Restart
The team detects a potential memory leak in the Payment Gateway service. Instead of logging into the dashboard and initiating a restart, they simply ask their agent to run restart_application, confirming the zero-downtime rolling cycle.
The Tradeoffs
Checking status manually
Logging into Qovery, clicking Projects, finding the right environment tab, then scrolling to find the app details and replica count. It takes 5-7 clicks.
→
Just ask your agent: 'What is the current replica count for the frontend app in Staging?' The agent runs list_applications and gives you the number instantly.
Deploying without context
Running a deployment command on the wrong environment (e.g., pushing a test build to production). This is high risk.
→
Always check first. Use list_environments to confirm the target environment name, then use that confirmed name in conjunction with get_project before running deploy_application.
Forgetting dependency order
Trying to restart an application (restart_application) when its required dependencies haven't been updated first. This breaks the build.
→
Use get_project and list_applications to map out all dependent services, then sequence your actions: deploy dependency A first, then restart service B.
When It Fits, When It Doesn't
Use this server if you need to perform infrastructure management—reading state or triggering action (deploy/restart)—without opening a separate dashboard. The tools are excellent for discovery (list_organizations, list_projects) and immediate execution (deploy_application). Don't use it if your primary task is writing complex, multi-step workflow logic that involves external data validation (like checking database schemas or running unit tests); those require dedicated orchestration pipelines outside the MCP Server. If you just need a simple read of configuration details, get_environment works well. But if you need to see all possible environments in one go for a project, use list_environments; don't rely on manually guessing names.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Qovery. 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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
You shouldn't have to click through four different dashboards just to check deployment status.
Right now, checking if your app is scaled correctly means navigating to the Qovery dashboard. You select the project, then the environment (Staging or Prod), then you find the microservice list. Only after that do you locate the specific app's status card and check the replica count—it’s tedious clicking and context switching.
With this MCP server, you just tell your agent what you need: 'Check the replicas for the Payment Gateway in Staging.' The agent uses `list_applications` or `get_application`, pulls the live metrics, and gives you a clean answer right where you are working. No dashboard hopping.
Qovery MCP Server: Deploying with certainty.
Manually running hotfixes requires copying an SHA from Git, finding the correct environment setting in Qovery, and then triggering the deployment via a CLI command. It's error-prone, especially when under pressure.
Now, you just paste the commit SHA into your chat and tell your agent to run `deploy_application`. The agent handles all the targeting and execution steps, confirming the status immediately. It’s done in one flow.
Common Questions About Qovery MCP
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.
When should I use `list_projects` versus `get_organization` with Qovery? +
You first need to run get_organization to see all available projects. This tool gives you the top-level list of development containers within your account.
Once you have a Project ID, using list_environments lets you map out which specific staging or production environments exist inside that project.
What metrics does `get_application` provide about my running microservices? +
It gives you detailed resource usage information for a single application. You'll get the allocated CPU and RAM limits, plus the current replica count.
This is essential for checking if your service is correctly scaled or if its resource quotas are being met.
If I run `restart_application` and the restart fails, how do I troubleshoot? +
The agent will report a failure status immediately, telling you which component failed to cycle. You'll need to check the detailed logs in your Qovery dashboard.
Using this tool helps trigger the action; checking the actual error code is up to the underlying platform.
Can I use `list_environments` to see all deployment stages for a project? +
Yes, running list_environments pulls every active environment from that specific Qovery Project ID. This includes Dev, Staging, and Production.
It's the fastest way to get an inventory of all available deployment targets without navigating the web UI.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
LangSmith (LLM Observability & Hub)
Monitor LLM apps via LangSmith — track traces, audit prompt templates, and manage evaluation datasets.
Change Case Engine
Transform text between 12 naming conventions (camelCase, snake_case, PascalCase, kebab-case, CONSTANT_CASE, and more) with zero errors.
Maileroo
Deliver transactional emails reliably at scale with an SMTP relay and API that prioritizes inbox placement and speed.
You might also like
Nubank MX
Manage your Nubank Mexico banking from any AI agent — check balances, review transactions, send SPEI transfers, pay bills, and track spending analytics.
Toggl Plan
Manage your team's visual timelines, track project phases, and balance workloads securely via your AI agent.
OpenAlex Alternative
Automate scholarly research via OpenAlex — search millions of works, authors, and institutions directly from any AI agent.