How to Use the NOAA Observations — US Current Conditions MCP in Vercel AI SDK

Q: Can the Vercel AI SDK get historical weather data from the NOAA Observations — US Current Conditions server?

Yes. The getobservationhistory tool is designed for this. You can call it from your agent to fetch recent observations and stream them to your UI to build trend charts or timelines.

Q: What's the difference between getstations and getradarstations?

getstations finds ground-level observation posts based on latitude and longitude. getradarstations lists the big Doppler radar installations. You'll use the former for current conditions and the latter for network mapping.

Stream live US weather from NOAA directly into your UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NOAA Observations — US Current Conditions MCP to Vercel AI SDK

Create your Vinkius account to connect NOAA Observations — US Current Conditions to Vercel AI 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 Observations — US Current Conditions with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Live Conditions in Your UI

The `get_latest_observation` tool streams temperature, wind, and pressure right into your React components. Your users see the data appear character-by-character, not after a frustrating delay. First, use `get_stations` to find the closest weather station to a user's location. Then, you pipe that station ID into `get_latest_observation` for hyper-local, real-time conditions. It's all handled on the edge, so it's fast.

Build Live Weather Trend Charts

Pull recent records for any US station with `get_observation_history`. This lets you build charts in Svelte or Vue that show temperature changes or wind shifts over the last few hours, streaming the updates live. This isn't just a single data point. The tool gives your agent a time-series to work with. That's perfect for building simple predictive displays or just showing users how the day's weather has unfolded.

Map the Official Weather Network

This MCP Server gives your agent tools to find official NWS sites. The `get_radar_stations` tool returns a list of all WSR-88D locations in the US, so you know where the real radar data comes from. Combine this with `get_station_metadata` to map out both observation points and radar coverage. Your UI can show a complete picture of the official weather monitoring network your app is using.

Setup guide

Set up NOAA Observations — US Current Conditions MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all NOAA Observations — US Current Conditions tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent NOAA Observations — US Current Conditions transactions",
});

console.log(text);
await mcpClient.close();

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 Observations — US Current Conditions 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 Observations — US Current Conditions MCP in Vercel AI SDK

Install the SDK, create an MCP client pointing to your Vinkius endpoint, and pass the tools to `streamText`. The weather data will stream directly into your frontend components as it's generated.

You get raw observation data from official NWS stations. This includes temperature, wind speed and direction, barometric pressure, visibility, and current weather phenomena for any station in the US.

Yes. The `get_observation_history` tool is designed for this. You can call it from your agent to fetch recent observations and stream them to your UI to build trend charts or timelines.

`get_stations` finds ground-level observation posts based on latitude and longitude. `get_radar_stations` lists the big Doppler radar installations. You'll use the former for current conditions and the latter for network mapping.

Yes. When your code sends latitude and longitude to find a station, the request passes through our ephemeral MCP server. We don't log or store the location data; it's used once to query the NOAA API and then discarded.

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