SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Google Meet MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Google Meet MCP. Schedule a new video meeting for tomorrow, list all meetings i hosted last week, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Google Meet logoGoogle Meet
Oauth2

Google Meet is a secure video conferencing platform for virtual meetings, chat, and screen sharing. It helps teams connect, collaborate, and communicate seamlessly from anywhere.

25 Tools

Introduction

This guide walks you through connecting Google Meet to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Google Meet agent that can create meeting spaces, fetch recordings and transcripts, list participants, read smart notes, and end active conferences through natural language commands.

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

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

Also integrate Google Meet with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Google Meet MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Meet account. It provides structured and secure access to your meeting spaces, conferences, participants, recordings, and transcripts, so your agent can create meetings, update meeting settings, review attendance, retrieve recordings, and read transcripts on your behalf.

  • Meeting creation and configuration: Have your agent create new Google Meet spaces and update the settings of existing spaces.
  • Conference management: Direct your agent to review past conferences or end a conference that is currently active.
  • Participant and attendance review: Let the agent list meeting participants and inspect their individual attendance sessions.
  • Recording retrieval: Instruct your agent to find recordings associated with a completed conference.
  • Transcript review: Have your agent retrieve structured transcript entries with speaker, timing, and spoken text details.

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: ["googlemeet"],
  });

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

  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 googlemeet, 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 Google Meet 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 Google Meet action and event your agent gets out of the box.

Batch Update Google Meet Members

Update 1 to 500 Google Meet members in one space in a single batch.

Create Google Meet Space

Creates a new Google Meet space with optional access controls, moderation, recording, or transcription settings, without attaching it to a calendar event.

Create Member

Create a member in a Google Meet space, optionally assigning a co-host role.

Delete Google Meet Space Member

Deletes a member who was previously assigned roles in a Google Meet space.

End active conference

Ends an active conference in a specified Google Meet space, immediately dropping active participants.

Get conference record by name

Tool to get a specific conference record by its resource name.

Get Meet details

Retrieve details of a Google Meet space using its unique identifier.

Get Member

Get a configured Google Meet space member by resource name, including their email and meeting role.

Get Participant

Get a Google Meet conference participant by resource name, including their identity and first-join/last-leave times.

Get Participant Details

Retrieves detailed information about a specific participant session from a Google Meet conference record.

Get Recording

Get a Google Meet recording's metadata by resource name, including its state, timestamps, and Google Drive destination when available.

Get recordings by conference record ID

Retrieves recordings from Google Meet for a given conference record ID.

Get Smart Note

Get metadata for a Google Meet smart note generated by Take Notes with Gemini.

Get Transcript

Retrieves a specific transcript by its resource name.

Get Transcript Entry

Fetches a single transcript entry by resource name for targeted inspection or incremental processing.

Get transcripts by conference record ID

Lists a page of transcripts for a Google Meet conference record, with a continuation token when more results are available.

List Conference Records

Tool to list conference records.

List Members

List configured members of a Google Meet space, including their email and meeting role.

List Participants

Lists the participants in a conference record.

List Participant Sessions

Lists a page of participant sessions for a specific participant in a Google Meet conference, including session start and end times.

List Recordings

Tool to list recording resources from a conference record.

List Smart Notes

List metadata for smart notes generated by Take Notes with Gemini in a Google Meet conference.

List Transcript Entries

Tool to list structured transcript entries (speaker/time/text segments) for a specific Google Meet transcript.

Update Google Meet Member

Update an existing Google Meet space member's email or meeting role.

Update Google Meet Space

Updates the configuration of an existing Google Meet space, including access, moderation and artifact settings, using a supplied or automatically derived update mask.

FRAMEWORKS

How to build Google Meet MCP Agent with another framework

Claude Code logo

Claude Code

Use Google Meet MCP with Claude Code

Cursor logo

Cursor

Use Google Meet MCP with Cursor

ChatGPT logo

ChatGPT

Use Google Meet MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Google Meet MCP with Claude Cowork

Antigravity logo

Antigravity

Use Google Meet MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Google Meet MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Google Meet MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Google Meet MCP with Grok Bot

Muse logo

Muse

Use Google Meet MCP with Muse

Codex logo

Codex

Use Google Meet MCP with Codex

Grok Build logo

Grok Build

Use Google Meet MCP with Grok Build

VS Code logo

VS Code

Use Google Meet MCP with VS Code

OpenCode logo

OpenCode

Use Google Meet MCP with OpenCode

OpenClaw logo

OpenClaw

Use Google Meet MCP with OpenClaw

Hermes logo

Hermes

Use Google Meet MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Google Meet MCP with Atomic Agent

Pi logo

Pi

Use Google Meet MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Google Meet MCP with DeepSeek Harness

Google ADK logo

Google ADK

Use Google Meet MCP with Google ADK

LangChain logo

LangChain

Use Google Meet MCP with LangChain

Mastra AI logo

Mastra AI

Use Google Meet MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Google Meet MCP with LlamaIndex

CrewAI logo

CrewAI

Use Google Meet MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Google Meet MCP with Pydantic AI

AutoGen logo

AutoGen

Use Google Meet MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Google Meet MCP server, the agents and LLMs can only access a fixed set of Google Meet tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Google Meet 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 Google Meet tools.

Yes, absolutely. You can configure which Google Meet 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 Google Meet data and credentials are handled as safely as possible.

Start with Google Meet.It takes 30 seconds.

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

Start building