How to Use the INPE (STAC API - Satélites) MCP in Vercel AI SDK

Q: How do I stream INPE (STAC API - Satélites) metadata using Vercel AI SDK?

Install @ai-sdk/mcp and initialize the client using createMCPClient with your HTTP endpoint. Pass the tools from this MCP Server directly to streamText to feed raw STAC coordinates and catalog details into your UI.

Q: How does Vercel AI SDK handle authentication for INPE (STAC API - Satélites)?

Pass an authorization header or use authProvider in your createMCPClient setup. Vinkius handles the underlying token exchange so your frontend code stays clean.

Feed live Brazilian satellite metadata directly into your React or Next.js frontend with 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 INPE (STAC API - Satélites) MCP to Vercel AI SDK

Create your Vinkius account to connect INPE (STAC API - Satélites) 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 INPE (STAC API - Satélites) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live STAC catalog queries

The `list_collections` tool pulls available satellite datasets from INPE directly into your streaming UI. Your users don't stare at loading spinners because the server pushes raw collection data like CBERS-4A directly into the Vercel AI SDK stream. You initialize the client with `createMCPClient` and pass the tools directly to `streamText`. This setup bypasses intermediate state management, sending Earth observation metadata straight to the browser.

Spatial search inside Next.js Edge Functions

The `search_items` tool executes bounding box and datetime queries across INPE's satellite archives. Running this tool inside Vercel AI SDK Edge Functions lets your agent locate specific cloud-free imagery over the Amazon basin in milliseconds. By calling `mcpClient.tools()`, you give your LLM the exact parameters needed to query coordinates without bloated server-side dependencies. The agent filters the results dynamically and streams the exact asset links to the user.

Map collection metadata with this MCP Server

The `get_collection` tool retrieves specific sensor characteristics and temporal coverage from the Brazilian Space Research Institute. This MCP Server exposes the raw JSON structure of CBERS or Amazonia-1 collections, allowing the Vercel AI SDK to render interactive UI components on the fly. You close the connection using `mcpClient.close()` once the streaming session completes. This prevents memory leaks in your serverless functions while ensuring clean metadata delivery.

Setup guide

Set up INPE (STAC API - Satélites) 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 INPE (STAC API - Satélites) 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 INPE (STAC API - Satélites) 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 INPE (STAC API). 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 INPE (STAC API - Satélites) 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 INPE (STAC API - Satélites) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using `createMCPClient` with your HTTP endpoint. Pass the tools from this MCP Server directly to `streamText` to feed raw STAC coordinates and catalog details into your UI.

Yes, the server runs in a V8 Isolate Sandbox, making it compatible with edge runtimes. Your agent can call `search_items` to fetch satellite metadata without hitting cold start delays.

Pass an authorization header or use `authProvider` in your `createMCPClient` setup. Vinkius handles the underlying token exchange so your frontend code stays clean.

Vercel AI SDK handles the slow response by streaming chunks of data as they arrive. If `list_collection_items` takes time to resolve, the agent keeps the connection open and streams the JSON array incrementally.

Yes, only the raw bounding boxes, datetime ranges, and collection IDs pass through the Vinkius sandbox to the INPE endpoint. No proprietary coordinate data or search histories are stored on our servers.

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