How to integrate AccuWeather MCP with Vercel AI SDK v6

This guide walks you through connecting AccuWeather to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working AccuWeather agent that can fetch current conditions, get hourly forecasts, retrieve your weather alerts, and report minute-by-minute precipitation through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a AccuWeather account through Composio's AccuWeather MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
AccuWeather logoAccuWeather
Api Key

AccuWeather is a global weather service providing current conditions, forecasts, MinuteCast precipitation, alerts, and lightning data. Use it for fast, localized forecasts and real-time weather alerts.

41 Tools

Introduction

This guide walks you through connecting AccuWeather to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working AccuWeather agent that can fetch current conditions, get hourly forecasts, retrieve your weather alerts, and report minute-by-minute precipitation through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a AccuWeather account through Composio's AccuWeather MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate AccuWeather with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with AccuWeather integration
  • Using Composio's Tool Router to dynamically load and access AccuWeather tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the AccuWeather MCP server, and what's possible with it?

The AccuWeather MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your AccuWeather account. It provides structured and secure access to global weather conditions, forecasts, alerts, precipitation updates, and storm data, so your agent can check current weather, plan around forecasts, monitor alerts, assess precipitation, and track tropical storms on your behalf.

  • Current conditions and forecasts: Have your agent check current conditions and retrieve hourly or daily forecasts for cities and other locations worldwide.
  • Weather alerts and alarms: Let the agent monitor active government weather alerts and threshold-based alarms for locations you care about.
  • Minute-by-minute rain and lightning: Direct your agent to assess near-term precipitation, forecast lightning probability, or review recent lightning strikes around chosen coordinates.
  • Tropical storm tracking: Instruct your agent to find active tropical storms and review their latest positions, observed paths, forecast tracks, intensity, and status.
  • Local weather context: Have your agent find locations, explore nearby cities, review lifestyle indices, or retrieve recent radar and satellite imagery for trip and activity planning.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["accu_weather"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to AccuWeather tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all AccuWeather-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available AccuWeather tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to accu_weather, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use AccuWeather tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with AccuWeather and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["accu_weather"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to accu_weather, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a AccuWeather agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every AccuWeather action and event your agent gets out of the box.

Autocomplete Locations

Return location-name suggestions for all locations, cities, or points of interest, optionally restricted to a country.

Get Administrative Area

Return one administrative area by country and administrative-area codes.

Get Country

Return one country by AccuWeather region and country codes.

Get Current Conditions

Return current weather observations for an AccuWeather location key, optionally including extended details and weather photos.

Get Daily Forecast

Return a 1, 5, 7, 10, or 15-day forecast for a location key.

Get Daily Indices

Return 1, 5, 10, or 15-day lifestyle-index forecasts for all indices, one group, or one index at an AccuWeather location.

Get Historical Current Conditions

Return the past 6 or 24 hours of current-condition observations for an AccuWeather location key.

Get Hourly Forecast

Return a 1, 12, 24, 72, or 120-hour forecast for an AccuWeather location key.

Get Index

Return metadata for one AccuWeather lifestyle index.

Get Index Group

Return the lifestyle indices belonging to one AccuWeather index group.

Get Lightning Forecast

Return forecast lightning probabilities for latitude/longitude coordinates.

Get Location

Return full location metadata for an AccuWeather location key.

Get MinuteCast Forecast

Return minute-by-minute precipitation conditions for latitude/longitude coordinates.

Get Radar and Satellite Imagery

Return recent radar and satellite image metadata and URLs for an AccuWeather location at a selected resolution.

Get Region

Return one AccuWeather region by region code.

Get Translation Group

Return translated strings for one AccuWeather translation group.

Get Tropical Storm Current Position

Return the latest observed position of a government-issued tropical storm.

List Active Tropical Storms

Return active government-issued tropical storms globally, by basin, or by basin and government storm ID.

List Administrative Areas

Return administrative areas globally or within a country, one provider page at a time.

List Countries

Return countries globally or within a specific AccuWeather region, one provider page at a time.

List Index Groups

Return lifestyle-index groups and their identifiers.

List Indices

Return all supported lifestyle indices and their identifiers.

List MinuteCast Color Codes

Return full or simplified color-code metadata used in MinuteCast precipitation output.

List Neighboring Cities

Return cities near an AccuWeather location key.

List Recent Lightning Strikes

Return recent lightning strikes within 1 to 60 miles of latitude/longitude coordinates as a GeoJSON FeatureCollection.

List Regions

Return AccuWeather geographic regions and their codes.

List Supported Languages

Return AccuWeather-supported languages with numeric IDs and language codes.

List Top Cities

Return top-ranked AccuWeather cities globally or within one region.

List Top City Conditions

Return current weather conditions for a requested number of globally ranked cities.

List Translation Groups

Return available AccuWeather translation groups and their identifiers.

List Tropical Storm Forecasts

Return forecast positions and intensity for a government-issued tropical storm.

List Tropical Storm Positions

Return the observed position history of a government-issued tropical storm.

List Tropical Storms by Year

Return government-issued tropical storms for a year, optionally filtered by basin and government storm ID.

List Tropical Storm Statuses

Return government-issued tropical storm status categories and wind-speed definitions globally or for one basin.

List Weather Alarms

Return threshold-based weather alarms for the next 1, 5, 10, or 15 days at an AccuWeather location.

List Weather Alerts

Return active government-issued weather alerts for a location key.

Resolve Language Identifier

Convert an AccuWeather language code to its numeric ID or a numeric language ID to its code.

Search Administrative Areas

Search administrative areas by required non-empty name text and optional country and administrative-area code filters, one 25-result provider page at a time.

Search City by IP Address

Resolve an IPv4 or IPv6 address to an AccuWeather city location.

Search Locations

Search cities, general locations, postal codes, or points of interest by text and optional geographic filters.

Search Locations by Coordinates

Find the nearest general location, city, or point of interest to latitude/longitude coordinates.

FRAMEWORKS

How to build AccuWeather MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use AccuWeather MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use AccuWeather MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use AccuWeather MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use AccuWeather MCP with Claude Cowork

Codex logo

Codex

Use AccuWeather MCP with Codex

OpenClaw logo

OpenClaw

Use AccuWeather MCP with OpenClaw

Hermes logo

Hermes

Use AccuWeather MCP with Hermes

CLI logo

CLI

Use AccuWeather MCP with CLI

Google ADK logo

Google ADK

Use AccuWeather MCP with Google ADK

LangChain logo

LangChain

Use AccuWeather MCP with LangChain

Mastra AI logo

Mastra AI

Use AccuWeather MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use AccuWeather MCP with LlamaIndex

CrewAI logo

CrewAI

Use AccuWeather MCP with CrewAI

FAQ

Frequently asked questions

With a standalone AccuWeather MCP server, the agents and LLMs can only access a fixed set of AccuWeather tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from AccuWeather and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right AccuWeather tools.

Yes, absolutely. You can configure which AccuWeather scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your AccuWeather data and credentials are handled as safely as possible.

Start with AccuWeather.It takes 30 seconds.

Managed auth, hosted MCP servers, and every AccuWeather tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies