SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Ambee MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Ambee MCP. Show today's air quality for paris, get wildfire risk forecast for california, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Ambee logoAmbee
Api Key

Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.

27 Tools

Introduction

This guide walks you through connecting Ambee to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ambee agent that can check air quality and pollen levels, fetch weather forecasts, track wildfires and natural disasters, and geocode places through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Ambee with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Ambee integration
  • Using Composio's Tool Router to dynamically load and access Ambee 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 Ambee MCP server, and what's possible with it?

The Ambee MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ambee account. It provides structured and secure access to environmental data, so your agent can check air quality history, monitor current weather, review pollen conditions, assess fire risk, and track natural disasters on your behalf.

  • Air quality history: Have your agent retrieve historical air quality data for any location using its latitude and longitude.
  • Weather conditions and forecasts: Let the agent check current temperature, pressure, humidity, and wind conditions, or retrieve forecasts for up to 72 hours by coordinates.
  • Pollen monitoring: Direct your agent to find current pollen conditions by place or coordinates and retrieve 48-hour pollen forecasts by place name.
  • Natural disaster tracking: Instruct your agent to retrieve recent or historical earthquake, flood, drought, and volcanic eruption data by country or coordinates.
  • Fire risk and location details: Have your agent assess forecast fire risk and Fire Weather Index conditions, or turn coordinates into a readable address, place name, and postal code.

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: ["ambee"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Ambee 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 Ambee-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 Ambee 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 ambee, 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 Ambee 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 Ambee 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: ["ambee"],
  });

  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 ambee, 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 Ambee 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 Ambee action and event your agent gets out of the box.

Geocode by Place

Tool to transform a place name or address into geographic coordinates.

Get Air Quality by City

Tool to retrieve real-time air quality data for a specific city.

Get Air Quality by Country Code

Retrieve real-time air quality readings from monitoring stations in a country using a 3-letter ISO country code.

Get Air Quality by Latitude and Longitude

Tool to retrieve real-time air quality data for a specific latitude and longitude.

Get Air Quality by Postal Code

Retrieve real-time air quality data for a specific postal code and country.

Get Air Quality Forecast by Latitude and Longitude

Tool to retrieve air quality forecast for a specific latitude and longitude.

Get Air Quality History by Latitude and Longitude

Tool to retrieve historical air quality data for a specific latitude and longitude.

Retrieve latest natural disasters by continent

Tool to retrieve latest natural disaster data for a specific continent.

Get historical natural disasters by date range

Retrieve global historical natural disaster events from a specified starting date, optionally filtering by event type and paginating results.

Get historical natural disasters by country code

Tool to retrieve historical natural disaster data for a country by ISO country code.

Get historical natural disasters by coordinates

Tool to retrieve historical natural disaster data for a specific location by coordinates with date range.

Get latest disasters by country code

Tool to retrieve latest natural disaster data for a specific country using ISO country code.

Get latest natural disasters by coordinates

Tool to retrieve latest natural disaster data (earthquakes, floods, droughts, volcanic eruptions) for a specific location using geographic coordinates.

Get Elevation by Latitude and Longitude

Tool to retrieve elevation statistics (min, max, mean) for a specific latitude and longitude.

Get Elevation by Place

Retrieve elevation statistics (minimum, maximum, and mean) for a location by place name.

Get Fire Risk by Latitude and Longitude

Retrieve weekly fire risk forecasts and Fire Weather Index data for geographic coordinates in North America, covering the next four weeks.

Get ILI Forecast by Latitude and Longitude

Retrieve an influenza-like illness (ILI) risk forecast for latitude and longitude, optionally including pollen and weather details.

Get Pollen Forecast by Place

Tool to retrieve 48-hour pollen forecast for a specific location by place name.

Get Pollen History by Place

Tool to retrieve historical pollen data for a specific place name.

Get Latest Pollen Data by Latitude and Longitude

Tool to retrieve latest pollen data for a specific geographic location using latitude and longitude coordinates.

Get Latest Pollen by Place

Tool to retrieve latest pollen data for a specific place by name.

Get Weather Forecast by Latitude and Longitude

Tool to retrieve weather forecast for a specific latitude and longitude (up to 72 hours).

Get Current Weather by Latitude and Longitude

Tool to retrieve current weather data for a specific latitude and longitude, including temperature, pressure, humidity, and wind conditions.

Get Wildfire Data by Latitude and Longitude

Retrieves real-time wildfire data for a specific geographic location using latitude and longitude coordinates.

Get Wildfire Data by Place

Retrieve recent wildfire data by place name, optionally filtering for satellite-detected or officially reported fires.

Get Wildfire Risk Forecast by Place

Retrieve weekly wildfire risk forecasts for a place in North America over the next four weeks.

Reverse Geocode by Latitude and Longitude

Tool to convert geographic coordinates into human-readable location data (address, place name, postal code).

FRAMEWORKS

How to build Ambee MCP Agent with another framework

Claude Code logo

Claude Code

Use Ambee MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ambee MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ambee MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ambee MCP with Claude Agent SDK

Codex logo

Codex

Use Ambee MCP with Codex

OpenClaw logo

OpenClaw

Use Ambee MCP with OpenClaw

Hermes logo

Hermes

Use Ambee MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Ambee MCP with Atomic Agent

Google ADK logo

Google ADK

Use Ambee MCP with Google ADK

LangChain logo

LangChain

Use Ambee MCP with LangChain

Mastra AI logo

Mastra AI

Use Ambee MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ambee MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ambee MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Ambee MCP with Pydantic AI

AutoGen logo

AutoGen

Use Ambee MCP with AutoGen

FAQ

Frequently asked questions

Start with Ambee.It takes 30 seconds.

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

Start building