How to Use the IBAMA Dados Abertos MCP in Vercel AI SDK

Q: How do I handle large datasets from IBAMA Dados Abertos in my Vercel AI SDK app?

Use datastoresearch to request paginated chunks instead of downloading entire CSVs. This keeps your edge functions light and prevents your frontend from hanging.

Q: Can I stream real-time infraction updates using IBAMA Dados Abertos with Vercel AI SDK?

Yes, you pipe the tool output from searchresources directly into your UI stream. The client processes the raw CSV chunks as they arrive from the Brazilian portal.

Q: How does the agent know which dataset to query?

The agent uses listdatasets to get a high-level index of what is available. From there, it targets specific resources using showdataset.

Stream Brazilian environmental data directly to your frontend with Vercel AI SDK and this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBAMA Dados Abertos MCP to Vercel AI SDK

Create your Vinkius account to connect IBAMA Dados Abertos 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 IBAMA Dados Abertos with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live environmental data to your UI

`datastore_search` fetches raw tabular data from the Brazilian environmental registry and feeds it directly into your frontend stream. Your Vercel AI SDK application renders raw rows of infraction data as they arrive from the server, skipping the typical loading states. You don't make your users wait for a massive payload to download and parse. Instead, your AI client uses `search_resources` to isolate specific CSV files, processing and displaying the metrics piece by piece in real-time.

Map IBAMA organizations dynamically inside React

`show_organization` extracts structural data and active datasets from specific Brazilian environmental departments directly. Your Vercel AI SDK components map these organizational hierarchies on the fly without heavy backend middleware. Your agent calls `list_organizations` to build dynamic navigation elements. This lets your users explore different departments and their respective data catalogs through a clean, responsive interface.

Query datasets using an edge-compatible MCP Server

`search_datasets` runs directly within your Edge Functions to find specific environmental metrics without cold-start delays. This MCP Server setup allows your Vercel AI SDK app to run lightweight queries close to your users. By using `list_datasets` alongside edge-compatible transports, you bypass heavy database drivers entirely. Your agent discovers new environmental registries and presents them instantly.

Setup guide

Set up IBAMA Dados Abertos 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 IBAMA Dados Abertos 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 IBAMA Dados Abertos 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 IBAMA 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 IBAMA Dados Abertos 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 IBAMA Dados Abertos MCP in Vercel AI SDK

Use `datastore_search` to request paginated chunks instead of downloading entire CSVs. This keeps your edge functions light and prevents your frontend from hanging.

Yes, you pipe the tool output from `search_resources` directly into your UI stream. The client processes the raw CSV chunks as they arrive from the Brazilian portal.

Yes, the server connects via standard HTTP or SSE transports. This lets your Vercel AI SDK code run inside lightweight Vercel Edge Functions without issues.

The agent uses `list_datasets` to get a high-level index of what is available. From there, it targets specific resources using `show_dataset`.

All queries go through an ephemeral, zero-trust V8 sandbox on Vinkius. Your API keys and connection tokens never persist, and the raw infraction data streams directly to your client without middle-man caching.

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