How to Use the Tomorrow.io MCP in Vercel AI SDK

Q: How do I check for historical weather data using Tomorrow.io and Vercel AI SDK?

You call gethistoricalweather to retrieve actual recorded observations. This doesn't predict anything; it just pulls the raw, verified data from a past date range.

Q: What kind of weather data does Tomorrow.io provide for Vercel AI SDK users?

The server provides a huge range: hourly predictions using gethourlyforecast, 15-day summaries with getdailyforecast, and specialized risk scores like those from getroadweatherrisk.

Q: Can I check pollen forecasts when building with Tomorrow.io and Vercel AI SDK?

Yep. You use the getpollenforecast tool to pull daily count indices for a specific area. It's a simple, discrete data point that works great in streaming UIs.

Streamline your front end: Show live climate risk assessments 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 Tomorrow.io MCP to Vercel AI SDK

Create your Vinkius account to connect Tomorrow.io 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 Tomorrow.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Weather Status Checks

Use `get_realtime_weather` to pull current conditions for any location. You just send a latitude/longitude, city name, or zip code, and the agent gets back immediate data. This makes it easy to show users exactly what's happening right now. The results stream directly into your UI with Vercel AI SDK; no loading spinners needed.

Hyperlocal Climate Risk Assessment

Need to check hazards? Call `get_road_weather_risk` for driving conditions, or use `get_wildfire_risk` to pull the index. The agent sends these specialized reports back. These tools let you build high-stakes applications where showing immediate risk data is critical. You'll see the hazard scores stream live as your AI client processes them.

Forecasting Minute by Minute

When minutes count, use `get_minutely_precipitation` for a precipitation nowcast. It gives you minute-by-minute rain predictions right when you need them. If your product needs high fidelity time data—like predicting heavy rain or tracking pollen counts with `get_pollen_forecast`—this server provides it, streaming the results live to the user via Vercel AI SDK.

Setup guide

Set up Tomorrow.io 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 Tomorrow.io 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 Tomorrow.io 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 Tomorrow.io. 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 Tomorrow.io 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 Tomorrow.io MCP in Vercel AI SDK

You call `get_historical_weather` to retrieve actual recorded observations. This doesn't predict anything; it just pulls the raw, verified data from a past date range.

The server provides a huge range: hourly predictions using `get_hourly_forecast`, 15-day summaries with `get_daily_forecast`, and specialized risk scores like those from `get_road_weather_risk`.

Yep. You use the `get_pollen_forecast` tool to pull daily count indices for a specific area. It's a simple, discrete data point that works great in streaming UIs.

The server handles weather predictions, air quality, and climate risk assessments globally. You can pinpoint locations by coordinates, zip code, or city name for maximum flexibility.

This server touches location-based weather and air quality data, specifically including latitude/longitude coordinates and general city names when making a request.

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