How to Use the NCDC Climate Data Online MCP in OpenAI Agents SDK

Fetch raw weather history directly into your openai-agents-sdk workflow using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NCDC Climate Data Online MCP to OpenAI Agents SDK

Create your Vinkius account to connect NCDC Climate Data Online 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 NCDC Climate Data Online with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run openai-agents-sdk with climate discovery.

This MCP Server exposes tools like `get_climate_data` so your openai-agents-sdk can fetch weather history without writing API wrappers. Your agent calls `list_datasets` to see what is available, then narrows down the search using `list_stations` to find the exact hardware tracking the weather. This setup avoids hardcoded endpoints. Your openai-agents-sdk agent dynamically discovers the data structure, meaning it can pivot from daily precipitation logs to monthly averages on the fly. It uses `get_dataset` to inspect metadata before pulling millions of weather data points, saving you from broken runtime loops.

Validate historical lookups before running agents.

The `get_climate_data` tool lets you pull massive datasets, which is where openai-agents-sdk guardrails come in handy. You don't want an agent running wild and querying fifty years of global temperature data on a loop. The SDK intercepts the tool call, checks the parameters, and ensures the request fits your budget. You set these guardrails in Python, and the openai-agents-sdk agent obeys. When it needs to map out specific weather stations via `list_locations`, the system verifies the location category before hitting the NCDC API. You get clean, validated weather records without worrying about runaway API bills.

Cache weather station lists for faster runs.

Caching the `list_stations` tool output ensures you do not fetch the same weather station list twice in an openai-agents-sdk session. Weather stations don't move. There is zero reason to pull the exact same NOAA coordinates over the network repeatedly. The openai-agents-sdk agent uses `list_data_types` and `get_station` to pull cached schemas instantly. It only hits the live network when executing `get_climate_data` for fresh records. This cuts down on latency and keeps your OpenAI execution times incredibly short.

Setup guide

Set up NCDC Climate Data Online 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 NCDC Climate Data Online tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with pip install openai-agents. Initialize MCPServerStreamableHttp using your Vinkius endpoint, and pass it directly to your Agent constructor inside an async with block.

Yes. Once you pass the server to the agent constructor, tools like list_data_categories and get_climate_data are instantly visible. You do not need to register them one by one.

Set cacheToolsList=True in your server parameters. This keeps the tool schemas for things like list_locations cached in memory, preventing redundant discovery calls to the MCP Server.

Your openai-agents-sdk agent will receive a clean response indicating no records matched. It can then use list_data_classes or get_station to debug if the station was active during those dates.

Vinkius processes your NCDC API calls inside an ephemeral V8 sandbox. Your historical climate records and station queries never persist on our servers, keeping your environmental research data isolated.

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