How to Use the Mariana Tek MCP in Mastra AI

Q: How do I register the Mariana Tek tools inside a Mastra AI agent?

Instantiate the client using new MCPClient and point it to your Vinkius server URL. Use mcpClient.listTools() to retrieve the tools, then spread them directly into your agent's tool array.

Q: Can Mastra AI handle conditional branching based on Mariana Tek class availability?

Yes, you can design workflows that check listclasses and branch based on open spots. If a class is full, the workflow can automatically trigger a search for alternative locations.

Q: Does Mastra AI support human-in-the-loop validation for Mariana Tek operations?

Yes, you can use the requireToolApproval setting on sensitive tools like searchcustomers. This forces the workflow to pause until a studio manager confirms the action.

Q: How is member pricing and corporate rate data protected?

All pricing structures retrieved via listpricing are transmitted over encrypted TLS channels. The server acts as a pass-through gateway, ensuring no corporate rate sheets are stored or cached.

Build automated Mariana Tek workflows with Mastra AI agents that handle bookings and class schedules.

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 Mastra AI

Create your Vinkius account to connect Mariana Tek to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated booking checks with Mastra AI

This Mariana Tek MCP Server lets your agent check reservations automatically using `list_reservations` to spot overbooked classes before they become a problem. Studio operations require handling complex, multi-step scenarios when classes fill up. If a session is full, the Mastra AI workflow can trigger a branch to search for alternative times. The agent reads `list_classes` to find open slots and alerts the customer relations team automatically.

Intelligent membership matching and retries

This Mariana Tek MCP Server helps you manage membership packages when a member tries to book with an expired plan. By querying `list_pricing` and `list_memberships`, the agent identifies the correct package options for that specific user. Mastra AI manages this with built-in retry logic, ensuring that temporary connection drops don't break the booking flow. If the initial check fails, the workflow backs off and tries again before alerting staff.

Human-approved customer updates via MCP Server

This Mariana Tek MCP Server integrates with Mastra's approval system, requiring a manager's nod before executing sensitive lookups. You don't want an autonomous agent modifying customer details without oversight. When the agent uses `get_customer` or `search_customers` to verify a high-value account, the workflow pauses. Once the front desk clicks approve, the agent retrieves the profile details.

Setup guide

Set up Mariana Tek MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Mariana Tek tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "mariana-tek-mcp-client",
  servers: {
    "mariana-tek-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Mariana Tek Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Mariana Tek tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Mariana Tek transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the client using `new MCPClient` and point it to your Vinkius server URL. Use `mcpClient.listTools()` to retrieve the tools, then spread them directly into your agent's tool array.

Yes, you can design workflows that check `list_classes` and branch based on open spots. If a class is full, the workflow can automatically trigger a search for alternative locations.

Yes, you can use the `requireToolApproval` setting on sensitive tools like `search_customers`. This forces the workflow to pause until a studio manager confirms the action.

The framework handles this with automatic exponential backoff. If a call to `list_reservations` fails due to a network hiccup, the agent retries the request before throwing an error.

All pricing structures retrieved via `list_pricing` are transmitted over encrypted TLS channels. The server acts as a pass-through gateway, ensuring no corporate rate sheets are stored or cached.

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