How to Use the Gipuzkoa Irekia MCP in Vercel AI SDK

Q: How do I handle large JSON payloads from Gipuzkoa Irekia in my ai-sdk application?

Use showpackage to fetch metadata, then stream the parsed JSON keys directly to your UI components. The sdk-typescript MCP client processes the incoming chunks sequentially, preventing browser memory spikes even when handling massive Basque regional datasets.

Q: Can I filter Gipuzkoa Irekia resources by file type using ai-sdk?

Yes, your agent can call searchresources with specific format parameters like CSV or PDF. The ai-sdk client then receives these filtered endpoints and can present them as direct download links in the chat UI.

Q: How do I fetch the latest public transit data from this endpoint?

Direct your agent to run searchpackages with the query "garraioa" or "transporte". Once it locates the dataset, it calls showresource to get the latest live CSV link.

Pipe real-time Basque country public datasets directly into your React frontend 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 Gipuzkoa Irekia MCP to Vercel AI SDK

Create your Vinkius account to connect Gipuzkoa Irekia 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 Gipuzkoa Irekia with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream public datasets to your UI

`search_packages` queries the Basque regional data catalog to find matching datasets for your user's prompt. Your application feeds these package IDs directly into Vercel AI SDK's streaming text generation, letting users watch the search results populate their screen in real-time. By routing the output of `show_package` straight to your frontend components, you bypass the typical blank loading screens. The AI client handles the API payload parsing on the fly, rendering structured tables of Basque public records while the connection remains open.

Map regional metadata with Vercel AI SDK

`list_groups` retrieves the thematic taxonomy used by the Gipuzkoa government to organize their public records. The Vercel AI SDK translates these raw categories into interactive UI filters on your client side without requiring intermediate server endpoints. Your frontend uses `show_group` to fetch specific metadata schemas for chosen sectors like transportation or environment. The SDK handles the asynchronous data stream, updating your React state as the regional data structures resolve.

Direct resource inspection via MCP Server

`show_resource` fetches the specific file URLs and formats for actual CSV or JSON files hosted on the Basque portal. Your Vercel AI SDK client processes these download links directly, allowing the user to trigger immediate local downloads or preview the raw data structures in their browser. Using `search_resources` lets your interface filter for specific file extensions or update dates instantly. This MCP Server integration ensures your frontend always points to live government assets instead of hardcoded, stale endpoints.

Setup guide

Set up Gipuzkoa Irekia 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 Gipuzkoa Irekia 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 Gipuzkoa Irekia 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 Gipuzkoa Irekia. 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 Gipuzkoa Irekia 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 Gipuzkoa Irekia MCP in Vercel AI SDK

Use `show_package` to fetch metadata, then stream the parsed JSON keys directly to your UI components. The sdk-typescript MCP client processes the incoming chunks sequentially, preventing browser memory spikes even when handling massive Basque regional datasets.

Yes, your agent can call `search_resources` with specific format parameters like CSV or PDF. The ai-sdk client then receives these filtered endpoints and can present them as direct download links in the chat UI.

The server runs in an isolated sandbox that handles connection pooling. Your ai-sdk client communicates with a single managed endpoint, which buffers calls to `list_organizations` and prevents your frontend from hitting Basque government rate limits.

Direct your agent to run `search_packages` with the query "garraioa" or "transporte". Once it locates the dataset, it calls `show_resource` to get the latest live CSV link.

No. The server only acts as a thin proxy between your client and the official Basque government API. No Basque public datasets and metadata or search queries are stored, keeping your operations compliant with EU data regulations.

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