How to Use the Weather (Open-Meteo) MCP in OpenAI Agents SDK

Q: How can I check the weather using Weather (Open-Meteo) and OpenAI Agents SDK?

You call weather.current with any natural language city name—like 'São Paulo' or 'Paris, France.' Your agent gets real-time conditions back instantly.

Q: What kind of alerts can Weather (Open-Meteo) provide using OpenAI Agents SDK?

The weather.alerts tool checks the active advisories and warnings for a city based on its forecast data. If things are totally clear, it just returns an empty list.

Q: Can I compare multiple locations with Weather (Open-Meteo) using OpenAI Agents SDK?

Yeah, weather.compare accepts 2 to 5 cities at once. It figures out which place has the best weather overall and gives you a solid comfort score for comparison.

Q: What if I need a multi-day forecast with Weather (Open-Meteo) and OpenAI Agents SDK?

Use weather.forecast. You can get a full 1 to 14-day outlook for any city globally, helping you plan way ahead.

Get real-time weather data and alerts using your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weather (Open-Meteo) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Weather (Open-Meteo) 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 Weather (Open-Meteo) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check current air quality with the MCP Server

When you run `weather.air_quality`, it checks the city's AQI, PM2.5, and ozone levels right now. More importantly, it always spits out a health recommendation, so you know if people need to stay indoors or head out. Don't just get numbers; you get actionable advice on air quality for any location.

Compare conditions across multiple cities

Want to figure out where everyone should go? Use `weather.compare` and feed it 2 to 5 city names. The MCP Server spits back a side-by-side comparison, giving you a comfort score for each one. It tells you which option is the best bet—like, 'Go to Lisbon this weekend.' No guesswork needed.

Plan your day with hourly forecasts

Need to know what's happening over the next 24 hours? `weather.hourly` gives you an hour-by-hour breakdown of conditions for any city worldwide. It's high precision, perfect for planning. It lets your agent build tight schedules knowing exactly when the rain hits and when the sun comes back.

Setup guide

Set up Weather (Open-Meteo) 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 Weather (Open-Meteo) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Weather (Open-Meteo) 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="Weather (Open-Meteo) Agent",
            instructions="You have access to Weather (Open-Meteo) 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 Open-Meteo. 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 Weather (Open-Meteo) 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 Weather (Open-Meteo) MCP in OpenAI Agents SDK

You call `weather.current` with any natural language city name—like 'São Paulo' or 'Paris, France.' Your agent gets real-time conditions back instantly.

The `weather.alerts` tool checks the active advisories and warnings for a city based on its forecast data. If things are totally clear, it just returns an empty list.

Yeah, `weather.compare` accepts 2 to 5 cities at once. It figures out which place has the best weather overall and gives you a solid comfort score for comparison.

This MCP Server touches public, real-time atmospheric data (AQI, temperature, precipitation). The data is read-only weather information; no private user records are touched.

Use `weather.forecast`. You can get a full 1 to 14-day outlook for any city globally, helping you plan way ahead.

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