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

Q: How do I stream Campinas Open Data search results into my app with the Vercel AI SDK?

You pass the tools from this MCP server to the streamText or generateText function. When your agent calls searchpackages, the SDK automatically handles streaming the response, which you can then render piece-by-piece in your UI.

Q: Can I build a real-time dashboard for Campinas Open Data using the Vercel AI SDK?

Yes. You can have your agent periodically call tools like listpackages or searchresources and stream any new or updated data directly to your dashboard components. The UI will update live as the data comes in.

Q: What's the best way to get dataset metadata from Campinas Open Data in my Next.js app?

Use the getpackage tool. When a user interacts with a dataset in your app, trigger an AI client call to that tool with the dataset's ID. The metadata streams back as a JSON object you can immediately use to update your React components.

Stream public data from Campinas, Brazil, directly into your web app's UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Campinas Open Data MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Campinas Data Live

Let your agent search Campinas's public data portal right from your app's interface. When your code calls `search_packages` or `search_resources`, the Vercel AI SDK streams the results directly into your React or Svelte components. Users see data appear in real-time as it's found. This isn't just about getting data. It's about building a front-end that feels alive. You can create an interactive search that shows results instantly, giving your users a much better experience than a static page that has to reload.

Build Interactive Data Explorers

Hook up your UI to the `get_package` and `get_resource` tools. A user can click on a dataset name in your app, and you can instantly fetch and display its full metadata, source, and update frequency. It all happens without a full page refresh. This turns a simple data list into a fluid exploration tool. You're not just showing users a table of data; you're giving them a way to dig in and see the details for themselves, right in the browser.

Your MCP Server, Your Frontend

This MCP server gives you the tools to build dynamic filters and navigation. Use `list_groups`, `list_tags`, and `list_organizations` to create dropdowns or sidebars that let users slice the data however they want. They can filter by topic, department, or keyword. You get all the building blocks needed to construct a custom front-end for the Campinas public data portal. It’s a fast way to give your users structured access to a city's open information.

Setup guide

Set up Campinas 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 Campinas 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 Campinas 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 Campinas Open Data Portal. 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 Campinas 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 Campinas Open Data MCP in Vercel AI SDK

You pass the tools from this MCP server to the `streamText` or `generateText` function. When your agent calls `search_packages`, the SDK automatically handles streaming the response, which you can then render piece-by-piece in your UI.

Yes. You can have your agent periodically call tools like `list_packages` or `search_resources` and stream any new or updated data directly to your dashboard components. The UI will update live as the data comes in.

Use the `get_package` tool. When a user interacts with a dataset in your app, trigger an AI client call to that tool with the dataset's ID. The metadata streams back as a JSON object you can immediately use to update your React components.

Yes, the whole setup is compatible with Edge Functions. Your AI client can run close to the user, call the Campinas data tools, and stream the results back with very low latency.

Yes, it's safe. This server only interacts with public dataset metadata from the city of Campinas, like dataset names and descriptions. Vinkius runs every request in an ephemeral, zero-trust sandbox, and your connection is authenticated with your private endpoint token.

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