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

Q: What happens to my Fly.io logs inside the Vercel AI SDK?

Logs from execmachine are transmitted as plain text strings. They are handled in-memory by your AI client and are not stored by the server itself.

Control your edge infrastructure directly from your React or Next.js app using Vercel AI SDK and the Fly.io 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 Fly.io MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time infrastructure control

Feed your AI client live data from your edge machines. You can trigger `create_machine` or `start_machine` directly through your UI components. Your users see the status updates immediately. The `get_machine` tool returns the exact state of your microVMs, keeping your frontend in sync with your global deployment.

Stream command results to the browser

Execute diagnostic commands like `exec_machine` without leaving your IDE or browser. The output streams straight into your application state. This makes debugging production issues fast. You get raw logs from `exec_machine` and can pipe them into your UI dashboards without extra middleware.

Manage volume state dynamically

Check your persistent storage health using `list_volumes` as your AI agent interacts with your database layers. It handles stateful data across your Fly.io fleet. You'll see exactly which NVMe volumes are attached, preventing configuration errors during high-traffic scaling events.

Setup guide

Set up Fly.io 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 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 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 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 MCP in Vercel AI SDK

Install the MCP client packages and point them to your server URL. You then inject the tool definitions into your `generateText` calls. It connects your edge compute to your AI client in minutes.

Yes, you can script error handling logic within your AI client. If `get_machine` reports a crash, your agent can trigger a `start_machine` command to recover.

It does. Since the MCP server provides a standard interface, your edge functions communicate with your infrastructure machines over a stable, authenticated connection.

Your infrastructure credentials and machine IDs never leave your local environment or authorized runtime. The connection uses your private endpoint token to secure all requests.

Logs from `exec_machine` are transmitted as plain text strings. They are handled in-memory by your AI client and are not stored by the server itself.

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