How to Use the Civo (Cloud-native Kubernetes Cloud Provider API) MCP in Mastra AI

Q: How can Mastra AI create a Civo instance and set up DNS automatically?

Create a Mastra AI workflow that calls createinstance first, then createdomainrecord using the IP address from the first step's output. Mastra handles passing the data between steps, making the process straightforward.

Q: How do I use the Civo (Cloud-native Kubernetes Cloud Provider API) server with Mastra AI to prevent exceeding my budget?

In your Mastra AI workflow, call the getcharges tool before any tool that creates resources, like createcluster. Then, use a conditional step to check if the current charges exceed your threshold and halt the workflow if they do.

Create resilient Civo automation with Mastra AI. Build workflows that provision clusters, handle errors, and manage resources reliably.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Civo (Cloud-native Kubernetes Cloud Provider API) MCP to Mastra AI

Create your Vinkius account to connect Civo (Cloud-native Kubernetes Cloud Provider API) 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 Civo (Cloud-native Kubernetes Cloud Provider API) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fault-Tolerant Cluster Provisioning

Build a Mastra AI workflow that doesn't just try to `create_cluster`—it succeeds. If the first attempt fails due to capacity in one region, the workflow can automatically query `list_regions` and try again somewhere else. This is how you build production-grade infrastructure automation. Once the cluster is up, the workflow continues. It can then `create_firewall` with your standard rules and `upload_ssh_key` for access. Mastra AI's engine handles the state, ensuring each step completes before the next one begins.

Automated Infrastructure Workflows

Chain Civo operations together into a single, reliable workflow. A common pattern is to `create_instance`, wait for it to be ready, then `attach_volume` for persistent storage, and finally `create_domain_record` to point a DNS entry at it. Your agent just runs one workflow. Mastra AI's built-in retry logic is key here. If attaching the volume fails, it won't just crash. It can retry a few times with exponential backoff before either logging an error and stopping, or triggering a cleanup step to delete the instance.

Conditional Resource Management with Mastra AI

Stop guessing about your account limits. Build a Mastra AI workflow that first calls `get_quota` to check your current usage. With conditional logic, you can tell your agent: IF instance count is below 90% of quota, THEN `create_instance`. This same logic works perfectly for cost control. Before spinning up a large new Kubernetes cluster, your workflow can call `get_charges` to check the month-to-date spend. If it's over budget, the workflow can halt and send a notification instead of proceeding. This MCP Server gives your agent the data it needs to make smart decisions.

Setup guide

Set up Civo (Cloud-native Kubernetes Cloud Provider API) 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 Civo (Cloud-native Kubernetes Cloud Provider API) 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: "civo-cloud-native-kubernetes-cloud-provider-api-mcp-client",
  servers: {
    "civo-cloud-native-kubernetes-cloud-provider-api-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Civo (Cloud-native Kubernetes Cloud Provider API) 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 Civo. 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 Civo (Cloud-native Kubernetes Cloud Provider API) 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 Civo (Cloud-native Kubernetes Cloud Provider API) MCP in Mastra AI

Create a Mastra AI workflow that calls `create_instance` first, then `create_domain_record` using the IP address from the first step's output. Mastra handles passing the data between steps, making the process straightforward.

Yes. You can create a workflow that periodically checks cluster health with `list_clusters`. If it detects a problem, it can use Mastra's conditional logic to trigger a `recycle_cluster_node` action, all without human intervention.

In your Mastra AI workflow, call the `get_charges` tool before any tool that creates resources, like `create_cluster`. Then, use a conditional step to check if the current charges exceed your threshold and halt the workflow if they do.

Use Mastra AI's built-in error handling and retry mechanisms. For example, if `create_cluster` fails, you can catch the error, have the workflow call `list_regions` to find an alternative, and then retry the creation in the new region.

Your Civo API key is the only sensitive data required. Vinkius encrypts this key and isolates it for your Mastra AI agent's use. All operations and the data they return, like cluster details or quota info, are processed in-memory within a sandboxed environment and are never persisted by us.

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