How to Use the Mariana Tek MCP in Vercel AI SDK

Q: How do I connect my Mariana Tek studio data to the Vercel AI SDK?

Install the @ai-sdk/mcp package and initialize the client using createMCPClient with your Vinkius endpoint. Pass the tools from mcpClient.tools() directly into your streamText function to let your agent query class data.

Q: Can I stream Mariana Tek class schedules to Next.js components using the Vercel AI SDK?

Yes, you can. The SDK allows you to stream tool calls like listclasses directly into your UI, updating the React state as the data arrives from the MCP Server.

Q: How does the Vercel AI SDK handle authentication for Mariana Tek endpoints?

You configure the authProvider during the createMCPClient setup to pass your secure tokens. This ensures all requests to retrieve member data via getcustomer remain locked down.

Q: Do I need to clean up the connection after fetching studio schedules?

Absolutely. Always call mcpClient.close() once your streaming session finishes to prevent socket leaks and keep your serverless functions running efficiently.

Feed Mariana Tek class schedules and member bookings directly into your React frontend in real-time using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mariana Tek MCP to Vercel AI SDK

Create your Vinkius account to connect Mariana Tek 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 Mariana Tek with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live streaming studio schedules with Vercel AI SDK

This Mariana Tek MCP Server lets your application fetch class lists instantly. Skip the loading spinners when your users want to see what's happening at the studio. Your agent calls `list_classes` and streams the active schedule straight to the client's screen. By calling `list_locations` and `list_instructors` in the background, you can render full studio timetables on the fly. The Vercel AI SDK handles the UI updates dynamically, so your members see open spots the second they search.

Real-time member profile checks on the edge

This Mariana Tek MCP Server gives you edge compatibility so there is zero lag when pulling up member accounts. Your application uses `search_customers` to find a matching profile and immediately streams their current booking status. If a member wants to verify their plan, the agent triggers `list_memberships` to display their active package. Because this runs on Edge Functions, the response returns in milliseconds without blocking the main thread.

Instant class details without UI lag

This Mariana Tek MCP Server ensures nobody has to wait for a full page reload just to check who is teaching a 6 PM spin class. Your agent calls `get_class_detail` and streams the exact session details directly into the user's chat window. Using `list_class_types` ensures the agent can explain the workout intensity and duration instantly. Combining this MCP Server with React Server Components gives your boutique fitness app a desktop-grade feel.

Setup guide

Set up Mariana Tek 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 Mariana Tek 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 Mariana Tek 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 Mariana Tek. 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 Mariana Tek 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 Mariana Tek MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your Vinkius endpoint. Pass the tools from `mcpClient.tools()` directly into your `streamText` function to let your agent query class data.

Yes, you can. The SDK allows you to stream tool calls like `list_classes` directly into your UI, updating the React state as the data arrives from the MCP Server.

You configure the `authProvider` during the `createMCPClient` setup to pass your secure tokens. This ensures all requests to retrieve member data via `get_customer` remain locked down.

Absolutely. Always call `mcpClient.close()` once your streaming session finishes to prevent socket leaks and keep your serverless functions running efficiently.

Your members' reservation histories and profile records never persist on Vinkius. The MCP Server acts as an ephemeral bridge, transmitting data directly between your secure database and the Next.js runtime.

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