How to Use the INMET (Apitempo - Meteorologia) MCP in OpenAI Agents SDK

Q: How do agent handoffs work when querying INMET (Apitempo - Meteorologia) with OpenAI Agents SDK?

You assign getmeteorologicaldatabydate to a specialized historical agent. If the primary user agent needs historical data, it hands off the context to the history agent, which runs the tool and returns the clean data.

Q: Does this MCP integration support streaming responses for satellite data?

The getsatelliteimages tool returns structured metadata and direct URLs. Your agent processes these links instantly, allowing you to stream the resulting analysis directly to your frontend application.

Get official Brazilian weather telemetry directly into your OpenAI Agents SDK production pipelines with zero manual configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect INMET (Apitempo - Meteorologia) MCP to OpenAI Agents SDK

Create your Vinkius account to connect INMET (Apitempo - Meteorologia) to OpenAI Agents 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 INMET (Apitempo - Meteorologia) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run validated weather lookups with automated guardrails

The `get_station_data_hourly` tool pulls raw meteorological telemetry straight from Brazilian government sensors into your active run context. Because you are deploying with OpenAI Agents SDK, the framework intercepts these incoming data blocks to validate them against your safety schemas before they hit your model. This means your production pipelines can request daily records using `get_station_data_daily` without risking injection attacks or raw string failures. Every single sensor reading passes through the agent guardrails first, ensuring your system only processes clean, structured numbers.

Coordinate regional forecasts using specialized MCP Server agents

The `get_forecast_by_city` tool allows you to isolate weather queries to specific municipal coordinates. You can set up a dedicated forecaster agent that hands off complex tasks to a regional analyzer running `get_meteorological_data_by_region` when local anomalies pop up. Splitting the work across multiple specialized agents keeps your token usage down and prevents context drift. The main agent handles the high-level routing, while the sub-agents query the MCP Server to pull localized atmospheric readings only when needed.

Track GOES-16 satellite imagery inside OpenAI dashboard

The `get_satellite_images` tool fetches real-time cloud cover data directly from the GOES-16 satellite. When your agent calls this endpoint, the entire payload is logged inside your OpenAI developer dashboard for immediate debugging and telemetry tracing. You don't have to guess why an agent made a specific routing decision based on cloud density. Just open the execution trace, inspect the returned image paths, and check the exact raw data that went into the prompt.

Setup guide

Set up INMET (Apitempo - Meteorologia) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all INMET (Apitempo - Meteorologia) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives INMET (Apitempo - Meteorologia) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate INMET (Apitempo - Meteorologia) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="INMET (Apitempo - Meteorologia) Agent",
            instructions="You have access to INMET (Apitempo - Meteorologia) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 INMET. 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 INMET (Apitempo - Meteorologia) 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 INMET (Apitempo - Meteorologia) MCP in OpenAI Agents SDK

Install the package, define your HTTP parameters, and pass the server instance inside the mcp_servers list. The SDK automatically discovers tools like list_stations and registers them to your agent schema without manual coding.

Yes, set cacheToolsList=True when initializing the server connection. This keeps your agent from re-fetching tool schemas like get_all_forecasts on every turn, which speeds up response latency.

You assign get_meteorological_data_by_date to a specialized historical agent. If the primary user agent needs historical data, it hands off the context to the history agent, which runs the tool and returns the clean data.

The get_satellite_images tool returns structured metadata and direct URLs. Your agent processes these links instantly, allowing you to stream the resulting analysis directly to your frontend application.

All API traffic to INMET goes through Vinkius's isolated sandbox. Your raw telemetry data and station coordinates are never cached or exposed to third parties, maintaining complete data isolation.

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