How to Use the Mato Grosso do Sul Open Data MCP in Vercel AI SDK

Q: How do I handle large SQL payloads from Mato Grosso do Sul Open Data in Vercel AI SDK?

Keep your queries tight by having your agent use datastoresearchsql with explicit SELECT and LIMIT clauses. The SDK streams the parsed JSON chunks directly to the client, preventing serverless function timeouts on heavy government datasets.

Q: How does Vercel AI SDK handle schema changes in Mato Grosso do Sul Open Data tables?

The agent should call getresource first to inspect the current field definitions before querying. This lets the Vercel AI SDK dynamically adjust its SQL generation based on the actual table structure instead of assuming a static schema.

Q: How do I clean up connections after querying the state portal?

Always call mcpClient.close() inside your API route's finally block. This prevents dangling connections to the MCP Server when your serverless execution finishes.

Stream real-time public records from Mato Grosso do Sul directly into Next.js UIs 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 Mato Grosso do Sul Open Data MCP to Vercel AI SDK

Create your Vinkius account to connect Mato Grosso do Sul 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 Mato Grosso do Sul Open Data with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Brazilian public datasets to your UI with this MCP Server

The `list_packages` tool fetches dataset catalogs, and then your agent can query specific resources instantly. Instead of making users wait for a massive backend payload to load, this MCP Server lets your app stream raw state data directly into React components. You feed `datastore_search` parameters directly into the Vercel AI SDK's `streamText` function. The data renders chunk by chunk as it comes back from the state's CKAN portal.

Run direct SQL on government databases in real-time

When basic keyword searches fall short, the `datastore_search_sql` tool lets your Vercel AI SDK agent execute actual SQL queries against the Mato Grosso do Sul datastore. Your frontend can ask for complex aggregates, and the agent writes the query and gets the results. You don't have to write custom API endpoints for every state department. The agent uses `list_organizations` to map the source and then runs SQL to pull the numbers.

Map state departments without page loads

Use `list_groups` and `list_organizations` to let your agent build dynamic navigation menus. The Vercel AI SDK handles these tools as executable functions, feeding the state's structural metadata right into your active session. Once the agent finds the right department, it calls `get_package` to inspect the available tables. Your users get a live, browseable directory of Mato Grosso do Sul public records without you hardcoding a single route.

Setup guide

Set up Mato Grosso do Sul 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 Mato Grosso do Sul 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 Mato Grosso do Sul 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 Mato Grosso do Sul Dados Abertos. 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 Mato Grosso do Sul 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 Mato Grosso do Sul Open Data MCP in Vercel AI SDK

Keep your queries tight by having your agent use `datastore_search_sql` with explicit SELECT and LIMIT clauses. The SDK streams the parsed JSON chunks directly to the client, preventing serverless function timeouts on heavy government datasets.

Yes, this server runs over lightweight HTTP transports, making it fully compatible with Vercel's edge runtime. You just initialize the client inside your route handler and pass the tools to `streamText`.

The agent should call `get_resource` first to inspect the current field definitions before querying. This lets the Vercel AI SDK dynamically adjust its SQL generation based on the actual table structure instead of assuming a static schema.

Always call `mcpClient.close()` inside your API route's finally block. This prevents dangling connections to the MCP Server when your serverless execution finishes.

No, this server only accesses public government records, such as state budget allocations and department performance metrics. All data is fetched from the state's official public CKAN instance, meaning zero private or classified citizen information is ever touched.

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