How to Use the NOAA Alerts — US Severe Weather Warnings MCP in Vercel AI SDK

Q: How do I connect NOAA Alerts — US Severe Weather Warnings to Vercel AI SDK?

Install @ai-sdk/mcp and define your transport layer using createMCPClient. You pass the HTTP URL to the transport configuration. Call mcpClient.tools() and feed the output straight into your streamText function.

Q: How do I filter alerts by severity?

Pass the severity parameter to the getactivealerts tool. Valid options include Extreme, Severe, Moderate, and Minor. The NWS assigns these tags at the source.

Q: How is location data handled when querying weather alerts?

Querying getalertsbypoint requires sending raw latitude and longitude coordinates to the server. The Vinkius V8 Isolate Sandbox processes these coordinates in an ephemeral execution context. We drop the memory state the millisecond the request completes, leaving zero trace of user locations.

Stream real-time National Weather Service warnings directly into your Next.js frontend using Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NOAA Alerts — US Severe Weather Warnings MCP to Vercel AI SDK

Create your Vinkius account to connect NOAA Alerts — US Severe Weather Warnings 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 Alerts — US Severe Weather Warnings with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Active Warnings to Vercel AI SDK

`get_active_alerts` pulls live National Weather Service warnings filtered by state, severity, or urgency directly into your Vercel AI SDK stream. You pass a two-letter state code like FL or TX. The server returns exactly what the NWS published seconds ago. Your users watch tornado warnings or flood advisories render on their screens instantly, long before a traditional loading spinner finishes. We built this to handle extreme weather events where latency costs lives. Your Next.js app hits the endpoint, grabs the raw text, and pushes it to the client. The data arrives raw and unfiltered, giving your frontend complete control over how to display immediate threats.

Map Exact Coordinates to Danger

`get_alerts_by_point` takes a specific latitude and longitude and returns every active weather alert overlapping that exact physical location. Your application grabs the user's current GPS coordinates and hands them to the MCP Server. If a severe thunderstorm warning covers that specific street corner, the agent knows immediately. Broad state-level alerts cause panic fatigue. Pinpoint accuracy solves that problem by ignoring storms 50 miles away. You only show warnings that actually matter to the person holding the phone.

Classify 120+ Weather Threats

`get_alert_types` dumps the complete list of valid National Weather Service event categories so your agent knows exactly what to look for. You need this to build accurate filters for your UI. The tool returns everything from "Hurricane Warning" to "Ashfall Advisory" without guessing the exact string format. Hardcoding these values always fails when the NWS adds a new category. Pulling the list dynamically ensures your application never misses a rare alert type. Your system adapts to the official terminology automatically.

Setup guide

Set up NOAA Alerts — US Severe Weather Warnings 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 Alerts — US Severe Weather Warnings 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 Alerts — US Severe Weather Warnings 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 Alerts — US Severe Weather Warnings 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 Alerts — US Severe Weather Warnings MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and define your transport layer using `createMCPClient`. You pass the HTTP URL to the transport configuration. Call `mcpClient.tools()` and feed the output straight into your `streamText` function.

Yes. The MCP Server returns JSON payloads that the SDK streams directly to your React or Vue frontend. Users see the active alerts appear character by character.

The HTTP transport method works perfectly in Edge environments. You just need to ensure your deployment platform allows outgoing requests to the endpoint. Keep your `mcpClient.close()` call inside a finally block to prevent memory leaks.

Pass the severity parameter to the `get_active_alerts` tool. Valid options include Extreme, Severe, Moderate, and Minor. The NWS assigns these tags at the source.

Querying `get_alerts_by_point` requires sending raw latitude and longitude coordinates to the server. The Vinkius V8 Isolate Sandbox processes these coordinates in an ephemeral execution context. We drop the memory state the millisecond the request completes, leaving zero trace of user locations.

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