How to Use the Equinix Metal MCP in Vercel AI SDK

Q: How do I stream Equinix Metal project keys in a Vercel AI SDK app?

Use the streamText function with the createprojectapikey tool. The key's details will stream as they're generated by the MCP server, allowing you to update your UI in real time. This avoids loading spinners and gives immediate feedback.

Q: What's the best way to handle auth between the Vercel AI SDK and this Equinix Metal server?

Pass your Vinkius endpoint token into the createMCPClient transport options. The Vercel AI SDK also supports an authProvider for more complex scenarios, but for server-to-server calls, the token is all you need.

Q: Is it possible to selectively expose Equinix Metal tools to my Vercel AI SDK client?

Yes. When you get the tools from mcpClient.tools(), you can filter the array in your own code before passing it to generateText. This lets you control exactly which Equinix Metal operations your frontend AI is allowed to perform.

Stream Equinix Metal API keys and invitations directly into your Vercel AI SDK app, showing users real-time infrastructure changes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equinix Metal MCP to Vercel AI SDK

Create your Vinkius account to connect Equinix Metal 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 Equinix Metal with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage API Keys in Real-Time

This toolset lets your UI create and delete Equinix Metal credentials. Use `create_project_api_key` to generate a new key for a service, and the result streams directly into your React components. No more polling or waiting for a refresh. When a key needs to be revoked, call `delete_api_key` or `delete_user_api_key`. The Vercel AI SDK's streaming support means your dashboard can instantly reflect that the key is gone. It's perfect for building interactive admin panels where users see the immediate impact of their actions.

Build Interactive Onboarding UI

These tools handle project invitations within your application's front end. Call `get_invitation` to fetch an invite's details and display them to a user. They can see who invited them and to what project. If the user decides not to join, your interface can call `decline_invitation`. The change is immediate. You can build a complete, self-contained onboarding flow right inside your Next.js or Svelte app without redirecting to the Equinix Metal console.

Live Email Management with your MCP Server

This MCP Server exposes tools for managing user email addresses on Equinix Metal. Your UI can call `create_email` to add a new contact address for a user account, streaming the confirmation back to the browser. Need to change the primary contact? Just use `update_email` to set a different address as the default. The `delete_email` tool removes addresses that are no longer needed. All of this happens live, giving your users a responsive experience.

Setup guide

Set up Equinix Metal 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 Equinix Metal 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 Equinix Metal 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 Equinix Metal. 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 Equinix Metal 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 Equinix Metal MCP in Vercel AI SDK

Use the `streamText` function with the `create_project_api_key` tool. The key's details will stream as they're generated by the MCP server, allowing you to update your UI in real time. This avoids loading spinners and gives immediate feedback.

Yes. The combination is ideal for it. You can build components that call tools like `get_invitation` or `delete_api_key` and show the results instantly, creating an interactive management experience for your users.

Pass your Vinkius endpoint token into the `createMCPClient` transport options. The Vercel AI SDK also supports an `authProvider` for more complex scenarios, but for server-to-server calls, the token is all you need.

Yes. When you get the tools from `mcpClient.tools()`, you can filter the array in your own code before passing it to `generateText`. This lets you control exactly which Equinix Metal operations your frontend AI is allowed to perform.

This server processes Equinix Metal API keys and user email addresses. Vinkius runs each MCP server in an ephemeral, zero-trust sandbox. Your connection is secured, and the server instance is destroyed after execution, leaving no stored data behind.

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