How to integrate Zoom Team Chat MCP with Vercel AI SDK v6

This guide walks you through connecting Zoom Team Chat to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Zoom Team Chat agent that can create channels, manage shared spaces, add space members, bookmark messages, and set reminders through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Zoom Team Chat account through Composio's Zoom Team Chat 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
Zoom Team Chat logoZoom Team Chat
Oauth2

Zoom Team Chat is Zoom's persistent messaging service for channels, direct messages, threads, reactions, files, reminders, and shared spaces. It keeps team conversations organized and searchable inside the Zoom workspace.

44 Tools

Introduction

This guide walks you through connecting Zoom Team Chat to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Zoom Team Chat agent that can create channels, manage shared spaces, add space members, bookmark messages, and set reminders through natural language commands.

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

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

Also integrate Zoom Team Chat 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 Zoom Team Chat integration
  • Using Composio's Tool Router to dynamically load and access Zoom Team Chat 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 Zoom Team Chat MCP server, and what's possible with it?

The Zoom Team Chat MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoom Team Chat account. It provides structured and secure access to your messages, channels, contacts, reminders, and shared spaces, so your agent can send messages, manage channels, organize conversations, set reminders, and coordinate shared spaces on your behalf.

  • Messaging and thread management: Have your agent send messages to channels or contacts, schedule messages, retrieve conversations and threads, and delete messages you no longer need.
  • Channel coordination: Let the agent create, find, join, archive, or delete channels, invite members, and review channel membership.
  • Message organization: Direct your agent to pin, bookmark, react to, or mark messages as read or unread, then review pinned and bookmarked content.
  • Reminders and follow-ups: Instruct your agent to create message reminders, list upcoming reminders, or remove reminders after tasks are complete.
  • Contacts and shared spaces: Have your agent find company contacts, create and manage shared spaces, add or remove members, and organize channels within those spaces.

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: ["zoom_chat"],
  });

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

  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 zoom_chat, 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 Zoom Team Chat 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 Zoom Team Chat action and event your agent gets out of the box.

Add Shared Space Members

Add members to a Zoom Team Chat shared space by email address or Zoom user ID.

Archive or Unarchive Channels

Archive or unarchive up to 10 Zoom Team Chat channels in one call.

Bookmark or Unbookmark Message

Add or remove a bookmark on a Zoom Team Chat message.

Create Channel

Create a new Zoom Team Chat channel for the authenticated user, optionally inviting initial members by email.

Create Message Reminder

Set a reminder on a Zoom Team Chat message, either after a delay (delay_seconds) or at an absolute time (remind_time).

Create Shared Space

Create a Zoom Team Chat shared space (a container that groups related channels).

Delete Channel

Delete a Zoom Team Chat channel the user owns or is a member of.

Delete Message

Delete a Zoom Team Chat message the connected user sent, identified by message_id plus the conversation it lives in.

Delete Message Reminder

Delete the reminder set on a Zoom Team Chat message.

Delete Scheduled Message

Delete a scheduled (draft) Zoom Team Chat message before it is sent, identified by draft_id plus the conversation it is addressed to.

Delete Shared Space

Delete a Zoom Team Chat shared space.

Get Channel

Get full information about a Zoom Team Chat channel, including its settings.

Get Chat Contact

Get a single Zoom Team Chat contact by email or user ID, optionally with live presence status.

Get Message

Get a single Zoom Team Chat message by ID, including its deep-link URL.

Get Message Thread

Retrieve a Zoom Team Chat message's thread: the parent message plus its replies since a given time.

Get Shared Space

Get details of a Zoom Team Chat shared space, including its owner and settings.

Invite Channel Members

Invite members to a Zoom Team Chat channel by email address.

Join Channel

Join a public Zoom Team Chat channel as the authenticated user.

Leave Channel

Leave a Zoom Team Chat channel.

List Bookmarks

List the authenticated user's bookmarked Zoom Team Chat messages, optionally filtered to one channel (to_channel) or one 1:1 contact (to_contact).

List Channel Members

List the members of a Zoom Team Chat channel.

List Channels

List the Zoom Team Chat channels the authenticated user is a member of.

List Chat Contacts

List the authenticated user's Zoom Team Chat contacts.

List Messages

List Zoom Team Chat messages exchanged in a channel or a 1:1 conversation, newest first (defaults to today).

List Pinned Messages

List the pinned messages of a Zoom Team Chat channel.

List Reminders

List the authenticated user's Zoom Team Chat message reminders.

List Scheduled Messages

List the user's scheduled (draft) Zoom Team Chat messages queued to send to a channel or a 1:1 contact.

List Chat Sessions

List the user's recent Zoom Team Chat sessions (channels and 1:1 conversations) within a time window.

List Shared Space Channels

List the channels grouped inside a Zoom Team Chat shared space.

List Shared Space Members

List the members and administrators of a Zoom Team Chat shared space.

List Shared Spaces

List the Zoom Team Chat shared spaces the authenticated user belongs to.

Mark Message Read or Unread

Mark a Zoom Team Chat message as read or unread.

Move Channels Into/Out of Shared Space

Move existing Zoom Team Chat channels into or out of a shared space.

Pin or Unpin Message

Pin or unpin a message in a Zoom Team Chat channel.

React to Message

Add or remove an emoji reaction on a Zoom Team Chat message.

Remove Channel Member

Remove a single member from a Zoom Team Chat channel.

Remove Shared Space Members

Remove members or administrators from a Zoom Team Chat shared space by user ID or member ID (the shared space owner cannot be removed).

Search Channels

Search Zoom Team Chat channels by name — fuzzy keywords or an exact channel name — across the channels the user has joined or the org's public channels.

Search Company Contacts

Search the connected user's organization directory for contacts by keyword (first name, last name, or email address).

Send Message

Send a Zoom Team Chat message to a channel or a 1:1 contact, optionally as a thread reply (reply_main_message_id) or scheduled for later (scheduled_time).

Star or Unstar Conversation

Star or unstar a Zoom Team Chat channel or contact for the authenticated user.

Update Channel

Rename a Zoom Team Chat channel or update its type/settings.

Update Message

Edit the text of an existing Zoom Team Chat message.

Update Shared Space

Update a Zoom Team Chat shared space's name, description, or settings.

FRAMEWORKS

How to build Zoom Team Chat MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Zoom Team Chat MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Zoom Team Chat MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Zoom Team Chat MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Zoom Team Chat MCP with Claude Cowork

Codex logo

Codex

Use Zoom Team Chat MCP with Codex

OpenClaw logo

OpenClaw

Use Zoom Team Chat MCP with OpenClaw

Hermes logo

Hermes

Use Zoom Team Chat MCP with Hermes

CLI logo

CLI

Use Zoom Team Chat MCP with CLI

Google ADK logo

Google ADK

Use Zoom Team Chat MCP with Google ADK

LangChain logo

LangChain

Use Zoom Team Chat MCP with LangChain

Mastra AI logo

Mastra AI

Use Zoom Team Chat MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Zoom Team Chat MCP with LlamaIndex

CrewAI logo

CrewAI

Use Zoom Team Chat MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Zoom Team Chat 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 Zoom Team Chat data and credentials are handled as safely as possible.

Start with Zoom Team Chat.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Zoom Team Chat 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