How to Use the Fly.io Extended MCP in Vercel AI SDK

Q: How do I configure the Fly.io Extended MCP Server with the Vercel AI SDK?

Install @ai-sdk/mcp and set up an HTTP transport pointing to your Vinkius endpoint. Retrieve the tool definitions by calling mcpClient.tools() and pass them directly into streamText or generateText. Remember to call mcpClient.close() once your stream completes to prevent memory leaks.

Q: How do I manage Let's Encrypt certificates using Fly.io Extended and Vercel AI SDK?

Your agent calls createacmecertificate to request a certificate, and then uses checkcertificate to verify DNS validation. The Vercel AI SDK updates the user on the verification progress in real-time, displaying each DNS check as it occurs.

Watch your Fly.io Extended infrastructure spin up in real-time as your Vercel AI SDK client streams live server updates to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fly.io Extended MCP to Vercel AI SDK

Create your Vinkius account to connect Fly.io Extended 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 Fly.io Extended with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision Fly.io Apps Live with Vercel AI SDK

`create_app` initializes fresh application instances on Fly.io directly from your user interface. Your AI client calls this tool, and instead of waiting for a slow backend response, the Vercel AI SDK streams the raw JSON metadata directly to the frontend. When you need compute, `create_machine` spins up a new Firecracker microVM with your designated container image. Users watch the boot logs render line-by-line as the LLM executes the command.

Scale Storage Volumes on the Fly

`create_volume` provisions persistent disk storage in your targeted Fly.io regions instantly. This MCP Server exposes storage actions directly to your Vercel AI SDK stream, letting users watch disk creation happen in real-time. If a database runs out of space, `extend_volume` increases the partition size without requiring a manual terminal session. Your AI agent handles the expansion and pushes the new volume details straight to the UI.

Reboot and Monitor MicroVMs via Streams

`stop_machine` halts active microVM instances when traffic drops or maintenance is required. By routing this tool through the Vercel AI SDK, you can build interactive admin dashboards where the AI shuts down idle resources and updates the UI state immediately. If a machine hangs, `start_machine` brings it back online while `wait_machine` blocks the stream until the VM reaches a healthy running state. This gives your users instant feedback on their hardware status without refreshing their browser.

Setup guide

Set up Fly.io Extended 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 Fly.io Extended 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 Fly.io Extended 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 Fly.io. 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 Fly.io Extended 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 Fly.io Extended MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up an HTTP transport pointing to your Vinkius endpoint. Retrieve the tool definitions by calling `mcpClient.tools()` and pass them directly into `streamText` or `generateText`. Remember to call `mcpClient.close()` once your stream completes to prevent memory leaks.

Yes, because the SDK supports streaming, your agent can call `wait_machine` and yield status updates back to the UI while waiting for the Fly.io API to return. This keeps the user interface responsive even during multi-second machine state transitions.

Absolutely, you pass the region parameter through your agent to `create_volume` to allocate storage exactly where your users need it. The SDK streams the resulting volume metadata directly into your React components for immediate rendering.

Your agent calls `create_acme_certificate` to request a certificate, and then uses `check_certificate` to verify DNS validation. The Vercel AI SDK updates the user on the verification progress in real-time, displaying each DNS check as it occurs.

Vinkius manages your Fly.io API tokens within an isolated, zero-trust V8 sandbox, meaning your Vercel AI SDK code never directly exposes these sensitive credentials to the client-side browser. Only structured, non-sensitive JSON metadata about your machines and volumes gets returned to your frontend application.

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