How to Use the DigitalOcean MCP in Vercel AI SDK

Q: How do I clean up the connection after listing active droplets?

Always call mcpClient.close() once your Vercel AI SDK stream finishes processing listdroplets. This prevents hanging HTTP connections in your serverless environments.

Let your Vercel AI SDK app stream real-time DigitalOcean infrastructure updates directly to your frontend without lag.

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 Vercel AI SDK

Create your Vinkius account to connect DigitalOcean to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Droplet Tracking with Vercel AI SDK

`list_droplets` serves as the entry point for your Vercel AI SDK interface to pull active virtual machine data. When a user asks your Vercel AI SDK chatbot what DigitalOcean servers are running, the SDK streams active IP addresses directly to your Next.js components. `get_droplet_details` handles deep queries when your Vercel AI SDK users select a specific node from the streamed list. The agent fetches CPU and region metrics, passing them directly into React components as JSON to build a live DigitalOcean dashboard on the fly.

Real-Time Database Status Streaming

`list_databases` lets your Next.js application display live DigitalOcean cluster configurations and engine specs on demand. Your Vercel AI SDK agent grabs the database connection endpoints and feeds them to the frontend using the SDK's real-time streaming capabilities. `list_volumes` pairs with database checks to show attached DigitalOcean block storage directly inside your Vercel AI SDK panel. Users see active disk sizes and attachment states update live as the model reads the API payload.

Direct Domain Configuration Inspections

`list_domains` gives your Vercel AI SDK setup the power to audit public DigitalOcean DNS configurations instantly. The agent reads live DNS zones to verify where your web traffic points, outputting the records directly into a clean Next.js chat interface. `list_actions` tracks the history of these DigitalOcean infrastructure shifts right inside the Vercel AI SDK streaming interface. Your users get a running log of recent account changes via this MCP server without digging through the cloud console.

Setup guide

Set up DigitalOcean MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all DigitalOcean tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent DigitalOcean transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

This MCP Server handles the raw API responses, but you should use Vercel's edge caching to prevent your AI client from repeatedly calling `list_droplets` during traffic spikes. If the model spams calls, DigitalOcean will throttle your token.

Yes, because the MCP server runs in a secure sandbox and only passes the final output of `list_databases` to your Vercel AI SDK stream. You control which fields the model exposes to the client-side UI.

Absolutely, you can initialize the MCP client inside an Edge Route and call `get_account_info` to check your limits. The SDK streams the JSON payload back to the browser with zero cold-start delay.

Always call `mcpClient.close()` once your Vercel AI SDK stream finishes processing `list_droplets`. This prevents hanging HTTP connections in your serverless environments.

Your API tokens remain strictly inside the Vinkius vault and never touch Vercel's servers or the model's training data. The tool only processes raw droplet metadata in memory during active tool calls, discarding it immediately after.

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