How to Use the Coolify MCP in Mastra AI

Q: Can I set up automatic retries for failed Coolify deployments in Mastra AI?

Yes, you can wrap triggerdeployment in a Mastra workflow with a custom retry policy. If the Nixpacks build fails due to network issues, the agent waits and retries the build automatically.

Q: How does Mastra AI handle database linking on Coolify?

The agent uses getdatabase to get configuration arrays and links them to new web apps. You can build a workflow that provisions a PostgreSQL database and immediately feeds the connection string to your application.

Q: Can I manage multiple Docker swarm nodes using this MCP Server?

Yes, listservers lets the agent query every connected physical endpoint. This allows you to deploy and monitor applications across your entire self-hosted cluster.

Run automated, resilient Coolify deployment workflows and database failovers with Mastra AI agents using our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coolify MCP to Mastra AI

Create your Vinkius account to connect Coolify to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Coolify with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional Deployment Workflows

This MCP Server provides `trigger_deployment` to let your workflows rebuild Nixpacks images automatically when a GitHub webhook fires. If the build fails, Mastra's workflow engine catches the exception and retries with exponential backoff. You can chain `get_application` to check if the Traefik reverse proxy path resolves properly after the build finishes. If the FQDN path is unreachable, the agent automatically triggers a rollback to the previous stable container state.

Automated Incident Response with Mastra AI

The `stop_application` tool integrates directly into your security playbooks via the MCP Server to pause billing or restrict web perimeter ingress during a detected cyber incident. The agent evaluates traffic metrics and shuts down compromised containers without waiting for human intervention. Before pulling the plug, the workflow uses `list_databases` to check that active connection strings and backup cadences are preserved. This ensures you do not lose critical application state when stopping the container.

Dynamic Server Resource Allocation

Use `list_servers` to identify which self-hosted Docker swarm nodes have available capacity for new deployments. The agent reads the IP properties and SSH connection validation statuses before assigning a new project. Once a target node is selected, the workflow calls `get_server` to check executing ports and ensure there are no collisions. This keeps your self-hosted infrastructure balanced and running smoothly.

Setup guide

Set up Coolify MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Coolify tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "coolify-mcp-client",
  servers: {
    "coolify-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Coolify Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Coolify tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Coolify transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coolify. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Coolify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Coolify MCP in Mastra AI

Yes, you can wrap `trigger_deployment` in a Mastra workflow with a custom retry policy. If the Nixpacks build fails due to network issues, the agent waits and retries the build automatically.

The agent uses `get_database` to get configuration arrays and links them to new web apps. You can build a workflow that provisions a PostgreSQL database and immediately feeds the connection string to your application.

You can configure this using Mastra's human-in-the-loop system. When the agent wants to call `stop_application`, the workflow pauses and waits for your manual confirmation.

Yes, `list_servers` lets the agent query every connected physical endpoint. This allows you to deploy and monitor applications across your entire self-hosted cluster.

Your API tokens, Docker executing ports, and server IP properties are never stored by Vinkius. They are injected at runtime into the ephemeral sandbox, ensuring your infrastructure access keys remain private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript