How to Use the Aragón Open Data MCP in Vercel AI SDK

Q: How do I connect the Aragón Open Data MCP server to Vercel AI SDK?

Install @ai-sdk/mcp. Initialize the client with createMCPClient({ transport: { type: "http", url: "YOURVINKIUSURL" } }) and pass the returned tools to streamText.

Q: Can Vercel AI SDK search the Aragón Open Data catalog?

Yes. The server exposes searchdatasets and listdatasets. Your agent can use these to find specific civic information based on user prompts.

Stream public datasets from the Government of Aragón directly into your React or Next.js frontends 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 Aragón Open Data MCP to Vercel AI SDK

Create your Vinkius account to connect Aragón 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 Aragón Open Data with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Aragón Open Data into Vercel AI SDK

The `search_datasets` tool connects your application to the CKAN catalog managed by the Government of Aragón. Your Vercel AI SDK client connects to this MCP server to call `search_datasets` or `newest_datasets` and stream the metadata straight to your React frontend. Users watch the available data packages appear in the UI instantly instead of staring at a loading spinner. You control exactly what gets rendered. When a user selects a specific package, the agent runs `get_dataset` to pull the full metadata. You can map these JSON responses to custom React components on the fly, building a live data explorer without writing complex backend fetch logic.

Render Live Table Previews

The `preview_data` tool grabs up to 1000 records from a specific view or resource. Your edge function streams these rows directly to a data grid component in your frontend. Since the response streams chunk by chunk, the user sees the first few rows immediately while the rest load. Before rendering the grid, your agent can fire off `show_columns`. This returns the schema for the requested view. Your UI uses that schema to automatically generate table headers and format the incoming data types correctly.

Execute Semantic Queries on the Fly

The `query_sparql` tool executes raw SPARQL queries against ontologies like EI2A, Aragopedia, ELI, and DataCube. You pass the query string, and the server returns the semantic data payload. This means you can build dynamic dashboards that answer complex civic questions. If a user asks your Next.js app about regional budget allocations, the agent constructs the SPARQL query, runs it, and streams the precise numerical results into a chart component.

Setup guide

Set up Aragón 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 Aragón 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 Aragón 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 Aragón Open Data. 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 Aragón 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 Aragón Open Data MCP in Vercel AI SDK

Install `@ai-sdk/mcp`. Initialize the client with `createMCPClient({ transport: { type: "http", url: "YOUR_VINKIUS_URL" } })` and pass the returned tools to `streamText`.

Yes. The server exposes `search_datasets` and `list_datasets`. Your agent can use these to find specific civic information based on user prompts.

The server returns an error payload. Your application can catch this error and prompt the user to rephrase their request, or the agent can attempt to rewrite the query automatically.

It works perfectly. The HTTP transport layer used by Vinkius is fully compatible with Edge runtimes, so you avoid cold starts when querying the regional catalog.

This MCP Server only reads public civic datasets, ontologies, and CKAN catalog metadata. Vinkius runs the connection in a V8 Isolate Sandbox that destroys itself after the session, ensuring your API requests leave no permanent trace.

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