How to Use the MeteoSource MCP in OpenAI Agents SDK

Q: Can I use this MCP Server with multi-agent handoffs?

Absolutely. You can have one agent run searchweatherplaces and hand the resulting place ID to a second agent that runs getpointforecast.

Get live weather forecasts inside your OpenAI Agents SDK setup with built-in guardrails and automatic tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MeteoSource MCP to OpenAI Agents SDK

Create your Vinkius account to connect MeteoSource 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 MeteoSource with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate weather forecasts before execution

The `get_point_forecast` tool lets your OpenAI Agents SDK verify real-time weather trends before triggering automated logistics decisions. Because the SDK runs guardrails on every action, your agent checks the raw forecast data against your safety limits before executing subsequent steps. You don't have to write custom validation logic to handle extreme weather events. The agent uses the SDK's built-in tracing to monitor how the weather forecast affects downstream decisions in real-time.

Find coordinates using the OpenAI Agents SDK

The `search_weather_places` tool resolves city names into precise location IDs that your OpenAI Agents SDK uses for targeted weather monitoring. Your specialized routing agent finds the location, then hands off the ID to a forecasting agent using native SDK handoffs. This multi-agent handoff keeps your token usage low. Instead of one massive prompt trying to resolve and forecast at once, the SDK splits the tasks cleanly across specialized agents.

Monitor live server status in your MCP Server

The `check_api_status` tool tells your OpenAI Agents SDK if the weather service is live before you run heavy batch queries. The SDK streams this status check directly through an HTTP connection, stopping failed calls before they consume your API budget. If the status check fails, the SDK handles the exception using its native tracing dashboard. You get clear visibility into whether the connection issue sits with the MCP Server or the external weather provider.

Setup guide

Set up MeteoSource 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 MeteoSource tools at runtime.
3

Create your Agent

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

Run the agent

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

The SDK discovers them automatically when you pass the server parameters to the Agent constructor. You don't need to manually write schemas or define functions for `get_point_forecast` or other tools.

Yes, you can set the cache option to true in your server parameters. This prevents the SDK from refetching the tool list on every run, which speeds up your weather agent's startup time.

You use the SDK's native guardrails to catch errors from tools like `get_nearest_weather_place`. If the tool fails, the agent can automatically route the task to a fallback plan without crashing your application.

Absolutely. You can have one agent run `search_weather_places` and hand the resulting place ID to a second agent that runs `get_point_forecast`.

Vinkius processes your coordinate queries inside an isolated, zero-trust sandbox. Your latitude and longitude values are sent directly to the weather API via encrypted tunnels and are wiped from the sandbox memory the moment the request finishes.

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