How to Use the NOAA Forecast — US Weather Predictions MCP in OpenAI Agents SDK

Q: How do I start using these tools with my OpenAI Agent?

Just pip install openai-agents and pass the Vinkius server URL to MCPServerStreamableHttp. The agent auto-discovers all five NOAA tools. Set cacheToolsList=True in production.

Q: Can I get a forecast for a specific time of day?

Yes. Use the gethourlyforecast tool. It returns a 156-hour forecast with detailed data for each hour, including temperature, precipitation probability, and wind speed.

Build production weather agents with OpenAI's built-in guardrails and full tracing. No more guessing what your agent did.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NOAA Forecast — US Weather Predictions MCP to OpenAI Agents SDK

Create your Vinkius account to connect NOAA Forecast — US Weather Predictions 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 NOAA Forecast — US Weather Predictions with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Pinpoint Forecasts, Safely

Your agent can find the exact NWS grid for a location using `get_point_metadata`, then pull a 156-hour forecast with `get_hourly_forecast`. This gives you a precise, hour-by-hour look at temperature, wind, and precipitation. It's direct access to raw NWS data. The OpenAI Agents SDK watches every step. If the agent tries to call a tool with bad parameters, the framework's guardrails stop it before it executes. You get full visibility into the agent's plan and actions through the OpenAI dashboard, so you can prove your weather logic is sound.

Combine Numbers and Narratives

Raw data is only half the story. Use one agent to pull quantitative data streams from `get_grid_data` and another, specialized agent to parse the meteorologist's notes from `get_forecast_discussion`. This separates the concerns of number-crunching and text analysis. With agent handoffs, the first agent passes its findings to the second. Your system can then make a final call based on both the raw numbers and the human expert's written context. It's how you catch nuances the raw data might miss.

Trace Every Call with this MCP Server

When your agent uses this NOAA MCP Server, every tool call is logged. You can see the exact latitude and longitude passed to `get_forecast` and the full 7-day forecast JSON that came back. No black boxes. This is critical for debugging and for production systems where you need an audit trail. The OpenAI dashboard gives you a step-by-step trace, showing how your agent decided to fetch weather data and what it got in return.

Setup guide

Set up NOAA Forecast — US Weather Predictions 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 NOAA Forecast — US Weather Predictions tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NOAA Forecast — US Weather Predictions 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="NOAA Forecast — US Weather Predictions Agent",
            instructions="You have access to NOAA Forecast — US Weather Predictions 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 NOAA. 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 NOAA Forecast — US Weather Predictions 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 NOAA Forecast — US Weather Predictions MCP in OpenAI Agents SDK

Just `pip install openai-agents` and pass the Vinkius server URL to `MCPServerStreamableHttp`. The agent auto-discovers all five NOAA tools. Set `cacheToolsList=True` in production.

Yes. Use the `get_hourly_forecast` tool. It returns a 156-hour forecast with detailed data for each hour, including temperature, precipitation probability, and wind speed.

The SDK validates the agent's plan before it calls any NOAA tool. If the agent tries to use `get_forecast` with invalid coordinates, the guardrail catches it, preventing a failed API call and giving you a clear error trace.

Yes. Vinkius hosts the server on a low-latency network. Your agent gets fast responses from tools like `get_point_metadata`, which is critical for chaining calls together without hitting timeouts.

Vinkius processes your latitude and longitude coordinates in an ephemeral, zero-trust sandbox. The request is proxied to NOAA and the container is destroyed. OpenAI's tracing provides an audit log, but the execution environment itself is stateless.

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