MCP server
Coolify MCP server
Coolify's official MCP server lets AI see self-hosted infrastructure, find unhealthy resources, review deployments and deploy with the right token.
- Official server
- Cloud and infrastructure
At a glance
- Maintained by
- Coolify (coollabs)
- Tools exposed
- 8 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Coolify is an open-source, self-hosted alternative to platforms like Heroku and Vercel. Teams use it to run apps, databases and services on their own servers. Coolify now ships its own MCP server, which lets an assistant see an overview of the infrastructure, search resources, list unhealthy ones, review deployments and, with the right token, deploy, cancel deployments and start or stop resources.
We use Coolify for self-hosted projects, so this is a practical tool for checking what is running and why something failed.
By default it reads. Deploy, cancel and start or stop actions need a token with the deploy scope, which is a sensible split. We give assistants read tokens for monitoring and keep deploy tokens for reviewed tasks. A community Coolify server also exists as an alternative.
Use cases
Best business use cases
Infrastructure overview
Unhealthy resources
Deployment review
Deploys
Start and stop
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read by default; deploy, cancel and start/stop actions need a token with the deploy scope.
-
get_infrastructure_overviewGet resource counts and health hints for the team.
-
search_resourcesFind a resource by name, UUID or domain.
-
list_unhealthy_resourcesFind resources that look unhealthy or down.
-
list_deploymentsList queued, running or past deployments.
-
get_deploymentInspect one deployment.
-
deployQueue an application deployment (deploy scope).
-
cancel_deploymentCancel a queued or running deployment (deploy scope).
-
controlStart, stop or restart an app, database or service (deploy scope).
Workflows
Example workflows
Morning health check
-
1
Ask for unhealthy resources.
-
2
The assistant lists them.
-
3
It reads recent deployments for each.
-
4
It explains likely causes.
-
5
An engineer acts.
Redeploy after a fix
-
1
Merge the fix.
-
2
Ask the assistant to deploy the app.
-
3
It uses the deploy-scoped token.
-
4
It watches the deployment.
-
5
It reports success or failure.
Prompts
Example prompts
“Which resources are unhealthy right now?”
“Why did the last deployment of the website fail?”
“Deploy the api service after I confirm.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Code: terminal
claude mcp add --transport http coolify https://app.coolify.io/mcp --header "Authorization: Bearer <COOLIFY_API_TOKEN>"- Hosted server: https://app.coolify.io/mcp for Coolify Cloud, or https://<your-coolify-domain>/mcp self-hosted (Streamable HTTP).
- Needs: Enable MCP in Settings > Configuration > Advanced and in team settings. Coolify API token as Bearer; scopes read, read:sensitive, deploy..
- Claude Desktop: Docs give only URL, transport and Authorization header; no Desktop JSON block published.
Security
Security considerations
-
Read-only first
Start with read access and add actions only for reviewed tasks.
-
Scoped credentials
Use a dedicated role or token with the least access, never an owner or admin key.
-
Separate environments
Keep production changes out of assistant sessions, or require approval for them.
-
Audit
Keep deploy-scoped tokens separate from read tokens.
Related servers
Servers that pair well with it
Docker
A community MCP server that lets AI list, run, stop and remove Docker containers and manage images, networks and volumes.
DigitalOcean
DigitalOcean's MCP server lets AI list and inspect resources and create, update and delete apps and infrastructure.
GitHub
GitHub's official MCP server lets AI read repositories, search code, manage issues and pull requests and, when allowed, change files.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- Product scaling Keep a growing product fast and stable as users, data and features increase.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
- SaaS migration Move a desktop, on-premise or single-customer system to a hosted product that serves many customers.
- API integration Make two systems share data reliably, with retries, logging and alerts when something goes wrong.
- AI-Powered Web Development Business websites, customer portals, dashboards and web applications that load fast, rank well and are easy to change.
Solutions
View all solutionsIndustries
View all industriesGuides and articles
View all guides and articles- How we review AI-generated code The checks we apply to every AI-assisted change, from tests and security to readability and business rules.
- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- MCP security best practices How to choose, configure and monitor MCP servers so AI assistants get the access they need and nothing more.
- How to automate reporting with AI and MCP Build reports that assemble themselves from your systems through MCP, with a written summary people can trust.
- Multi-tenant SaaS architecture explained How SaaS products serve many customers from one system, the main design options and how to choose.
- How to set up automated reporting Replace manual weekly and monthly reports with dashboards and summaries that update themselves.
Glossary terms
View all glossary terms- API integration An API integration connects two or more systems through their APIs so data and actions flow between them automatically.
- SaaS SaaS, or software as a service, is software delivered over the internet on a subscription, rather than installed and owned by each customer.
- Cloud hosting Cloud hosting runs websites and applications on servers rented from a provider, which can grow or shrink with demand.
- Reverse proxy A reverse proxy is a server that sits in front of your applications, receiving visitors' requests and passing them to the right app, often adding security and caching.
- VPS A VPS, or virtual private server, is a rented virtual machine with its own resources, on which you can install and run your own software.
- API An API, or application programming interface, is a defined way for one piece of software to request data or actions from another.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. Coolify ships its own MCP server. A community server also exists.
Yes, with a token that has the deploy scope.
An open-source, self-hosted platform for running apps, databases and services on your own servers.