How to Use the EMT Madrid (Open Data) MCP in Vercel AI SDK

Q: How do I handle authentication for EMT Madrid (Open Data) inside Vercel AI SDK?

You run the login tool first to retrieve an accessToken from EMT MobilityLabs. Pass this token into your MCP client configuration so subsequent tool calls remain authorized.

Q: Does using this integration expose my users' location data to third parties?

No, only the coordinates you explicitly send to planbusroute leave your secure Vinkius environment. Your EMT MobilityLabs credentials used in login are stored as encrypted environment variables and never exposed to the client.

Feed real-time Madrid transit data directly into your React components using 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 EMT Madrid (Open Data) MCP to Vercel AI SDK

Create your Vinkius account to connect EMT Madrid (Open Data) 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 EMT Madrid (Open Data) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Madrid Bus Times with Vercel AI SDK

The `get_bus_arrivals` tool pulls live waiting times for any stop across the Madrid municipal network. Your Vercel AI SDK client streams this data straight to Next.js components without a loading spinner. By coupling this tool with edge runtime, your React UI updates live. The raw JSON payload from the Madrid bus network converts to instant UI updates, showing commuters exactly when their bus will pull up.

Track Active BiciMAD Docks in Your App

The `list_bicimad_stations` tool checks the occupancy and bike availability of Madrid's public electric bike stations. It feeds the exact coordinates and dock counts directly into the Vercel AI SDK stream. This setup lets your Next.js interface update bike maps on the fly. Users get immediate, live BiciMAD bike counts during peak rush hours before they walk to an empty rack.

Render Madrid Transit Routes on the Edge

The `plan_bus_route` tool calculates optimal paths across the city using the official EMT network. This MCP Server integration allows your Vercel AI SDK client to suggest paths based on real-time transit status. You feed the computed route steps directly into your chat interface. Commuters receive step-by-step directions as the model generates them, keeping latency under 200ms.

Setup guide

Set up EMT Madrid (Open Data) 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 EMT Madrid (Open Data) 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 EMT Madrid (Open Data) 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 EMT Madrid. 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 EMT Madrid (Open Data) 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 EMT Madrid (Open Data) MCP in Vercel AI SDK

You run the `login` tool first to retrieve an accessToken from EMT MobilityLabs. Pass this token into your MCP client configuration so subsequent tool calls remain authorized.

Yes, the SDK processes tool outputs as they arrive from the server. When the model invokes `get_bus_arrivals`, the resulting JSON payload streams straight to your frontend UI components.

It relies on your Vinkius hosted endpoint to manage the connection. Since the SDK runs on edge functions, you should cache the `list_bicimad_stations` response to avoid hitting EMT rate limits.

The tool returns an error payload which your model reads. The SDK then prompts the model to adjust the coordinates and try the calculation again automatically.

No, only the coordinates you explicitly send to `plan_bus_route` leave your secure Vinkius environment. Your EMT MobilityLabs credentials used in `login` are stored as encrypted environment variables and never exposed to the client.

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