How to Use the GDACS MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK with GDACS to monitor earthquakes?

Your agent calls getlatestearthquakes, then streams the results directly into your UI. Use streamText and pass the tools from the GDACS MCP Server. You can render each earthquake on a map as it's received.

Q: Can I filter GDACS alerts by type in my Vercel AI SDK app?

Yes. The getalerts tool supports filtering by event type. Your agent can specifically request TC for cyclones or EQ for earthquakes, so your UI only shows the data your user asked for.

Q: How can I get GeoJSON data from GDACS using the Vercel AI SDK?

Just have your agent call geteventgeojson with an event ID. The Vercel AI SDK will stream the GeoJSON payload, which you can then feed directly into a mapping library like Mapbox or Leaflet in your React or Next.js app.

Q: What kind of disaster details can I get?

A lot. Use geteventdetail for specifics like magnitude, depth, and affected countries. For cyclones, getlatestcyclones gives you wind speeds and forecast tracks. For volcanoes, getlatestvolcanoes returns ash plume information.

Stream real-time disaster data from GDACS directly into your Vercel AI SDK app's UI. 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 GDACS MCP to Vercel AI SDK

Create your Vinkius account to connect GDACS 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 GDACS with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Disaster Maps in React

Use the Vercel AI SDK to stream geographic data straight from GDACS. The `get_event_geojson` tool sends disaster boundary polygons directly to your frontend, letting you render affected areas on a map as the data arrives. Your users see the disaster's footprint unfold in real time. Combine this with `get_latest_earthquakes` or `get_latest_cyclones` to plot event locations instantly. Because the AI SDK streams tool results, you can build UIs that feel alive, updating maps and data tables without waiting for the full response. It's a much better user experience than a static page.

Stream Alert Feeds with the AI SDK

Your agent can call `get_alerts` to fetch a stream of color-coded disaster warnings. With the Vercel AI SDK, you don't just get a list—you can render each alert (red, orange, green) in your UI the moment your agent gets it from the MCP server. Let users click an alert to trigger a call to `get_alert_detail` or `get_impacts`. The results stream back, populating your UI with population estimates and economic loss figures without a full page reload. This makes your application feel fast and responsive.

Show Event Impact as It's Calculated

When a user asks about a specific flood or wildfire, your agent can query `get_event_detail` for the basics. Then, it can follow up with `get_impacts` to get the estimated human and economic costs. The AI SDK's streaming capability means you can design a component that shows "Fetching impact data..." and then fills in the numbers as they arrive from GDACS. It makes your app feel directly connected to the source of the data.

Setup guide

Set up GDACS 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 GDACS 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 GDACS 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 GDACS. 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 GDACS 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 GDACS MCP in Vercel AI SDK

Your agent calls `get_latest_earthquakes`, then streams the results directly into your UI. Use `streamText` and pass the tools from the GDACS MCP Server. You can render each earthquake on a map as it's received.

Yes. The `get_alerts` tool supports filtering by event type. Your agent can specifically request `TC` for cyclones or `EQ` for earthquakes, so your UI only shows the data your user asked for.

Just have your agent call `get_event_geojson` with an event ID. The Vercel AI SDK will stream the GeoJSON payload, which you can then feed directly into a mapping library like Mapbox or Leaflet in your React or Next.js app.

A lot. Use `get_event_detail` for specifics like magnitude, depth, and affected countries. For cyclones, `get_latest_cyclones` gives you wind speeds and forecast tracks. For volcanoes, `get_latest_volcanoes` returns ash plume information.

Vinkius handles the connection to the GDACS server, which only sees the query itself—like a request for `get_latest_floods`. Your Vercel AI SDK client auth token is managed by our ephemeral, zero-trust platform. We don't log or store the disaster data that comes back to you.

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