How to Use the DigitalOcean MCP in Mastra AI

Q: Can I build a Mastra AI workflow to scale DigitalOcean droplets automatically?

Yes, you can set up a workflow that uses listdroplets to monitor load and then triggers scaling actions. Mastra AI manages the execution steps and retries if the DigitalOcean API experiences temporary downtime.

Q: How does Mastra AI handle failures when querying DigitalOcean Kubernetes clusters?

Mastra AI uses its built-in workflow engine to retry listkubernetesclusters calls with exponential backoff. If the DigitalOcean API is unresponsive, the agent won't crash your entire pipeline.

Q: Is human approval required before Mastra AI modifies my DigitalOcean domains?

You can configure Mastra's requireToolApproval setting on tools exposed by this MCP server like listdomains. This forces the agent to pause and wait for your green light before making any live DNS changes.

Build resilient Mastra AI workflows that auto-remediate DigitalOcean server failures and manage clusters.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DigitalOcean MCP to Mastra AI

Create your Vinkius account to connect DigitalOcean 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 DigitalOcean with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Droplet Recovery Workflows

`list_droplets` acts as the trigger mechanism for Mastra AI workflows monitoring your DigitalOcean virtual infrastructure. When a server goes offline, the Mastra workflow engine detects the status change and initiates custom recovery logic. `get_droplet_details` runs immediately after to gather specific diagnostic info on the failing DigitalOcean node. The Mastra agent evaluates the CPU load and memory pressure, then decides whether to notify your team or attempt an automated reboot.

Multi-Step Kubernetes Cluster Health Checks

`list_kubernetes_clusters` integrates directly into your Mastra AI automated maintenance pipelines to check cluster health. The Mastra agent scans your active DigitalOcean clusters to check node health, running these checks on a cron-like schedule. `list_actions` tracks every automated change the Mastra agent executes across your DigitalOcean Kubernetes setups. This audit log ensures your Mastra workflow has a clear record of when clusters were checked or modified.

Dynamic Storage Management via MCP Server

`list_volumes` allows Mastra AI workflows to monitor DigitalOcean block storage limits before they cause database crashes. The Mastra agent checks disk sizes and attachment states, automatically flagging volumes that are running out of space. `list_images` helps the Mastra agent locate valid DigitalOcean snapshots when a volume needs to be restored or cloned. Mastra's retry logic ensures that if a snapshot lookup fails due to network hiccups, it retries with exponential backoff.

Setup guide

Set up DigitalOcean 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 DigitalOcean 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: "digitalocean-alternative-mcp-client",
  servers: {
    "digitalocean-alternative-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent DigitalOcean 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 DigitalOcean. 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 DigitalOcean 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 DigitalOcean MCP in Mastra AI

Yes, you can set up a workflow that uses `list_droplets` to monitor load and then triggers scaling actions. Mastra AI manages the execution steps and retries if the DigitalOcean API experiences temporary downtime.

Mastra AI uses its built-in workflow engine to retry `list_kubernetes_clusters` calls with exponential backoff. If the DigitalOcean API is unresponsive, the agent won't crash your entire pipeline.

You can configure Mastra's `requireToolApproval` setting on tools exposed by this MCP server like `list_domains`. This forces the agent to pause and wait for your green light before making any live DNS changes.

You configure the MCP client with your Vinkius endpoint URL, which securely injects your DigitalOcean token. The Mastra agent never sees your raw credentials during execution.

All database endpoints and cluster configurations retrieved via `list_databases` are processed inside an isolated V8 sandbox. The data is encrypted in transit and never cached or stored on disk after the tool execution completes.

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