How to integrate Clickmeeting MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Clickmeeting logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Clickmeeting to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Clickmeeting agent that can schedule a new webinar for next week, add attendee to upcoming training session, generate pdf report for yesterday's session through natural language commands.

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

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

Also integrate Clickmeeting with

TL;DR

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

The Clickmeeting MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Clickmeeting account. It provides structured and secure access to your webinars and meetings, so your agent can perform actions like scheduling conferences, managing contacts, generating reports, handling recordings, and more—all on your behalf.

  • Automated conference creation and scheduling: Seamlessly instruct your agent to create new meetings or webinars, helping you organize virtual events in seconds.
  • Contact management and attendee registration: Have your agent add or pre-register participants as contacts before scheduling or starting events, ensuring a smooth entry process.
  • Recording management and cleanup: Direct your agent to delete specific recordings or clear all session recordings for a conference room, keeping your account tidy and compliant.
  • Instant session analytics and reporting: Ask your agent to generate detailed PDF reports for any session, so you can quickly access valuable insights and analytics.
  • Easy access and participation links: Let your agent generate autologin URLs for participants, allowing direct, hassle-free entry to your meetings without manual logins.

Supported Tools & Triggers

Tools
Create Access TokensTool to generate access tokens for conference participants.
Create ConferenceTool to create a new conference.
Create ContactTool to create a new contact in your ClickMeeting account.
Delete ConferenceTool to delete a specific conference.
Delete FilePermanently delete a file from the ClickMeeting file library.
Delete RecordingPermanently delete a specific recording from a conference room.
Delete RecordingsTool to delete all recordings for a conference room.
Download FileDownload the content of a specific file from the ClickMeeting file library.
Generate Autologin HashGenerate an autologin hash for a conference participant.
Generate Session PDF ReportGenerates a PDF report containing analytics and details for a specific conference session.
Get Chat DetailsTool to retrieve details of a specific chat session.
Get ChatsTool to retrieve a list of all chat sessions.
Get Conference DetailsRetrieve detailed information about a specific ClickMeeting conference room.
Get Conference FilesRetrieves the list of files uploaded to a specific conference room's file library.
Get ConferencesRetrieve a list of conference rooms from your ClickMeeting account filtered by status.
Get Conference SessionsRetrieves past sessions for a conference room.
Get Conference SkinsRetrieves a list of available conference room skins that can be used to customize the appearance of webinar/meeting rooms.
Get File DetailsRetrieve detailed information about a specific file from the ClickMeeting file library.
Get File LibraryRetrieve a list of files from the ClickMeeting file library.
Get Phone GatewaysRetrieve available phone dial-in numbers for ClickMeeting webinars.
Ping APITool to check API service status.
Get RegistrationsTool to retrieve registrations for a conference room by status.
Get Session AttendeesRetrieves the list of attendees who participated in a specific session of a conference room.
Get Session DetailsRetrieve detailed statistics for a specific past conference session.
Get Session Poll DetailsTool to retrieve details of a specific poll conducted during a session.
Get Session Q&A HistoryTool to retrieve the Q&A history for a specific session.
Get Session RecordingsRetrieve all recordings for a conference room.
Get Session RegistrationsRetrieve registrations for a specific session within a conference room.
Get Session Survey DetailsTool to retrieve details of a specific survey/poll conducted during a session.
Get Session SurveysRetrieves the list of surveys conducted during a specific conference session.
Get Time Zone ListRetrieves all available time zones supported by ClickMeeting.
Get Time Zone List by CountryRetrieve available time zones for a specific country by ISO 3166-1 alpha-2 country code.
Get Token By EmailTool to retrieve access tokens assigned to a specific email address for a token-protected conference room.
List Access TokensTool to retrieve all generated access tokens for a token-protected conference room.
List Registrations By StatusTool to retrieve registered participants of a conference room filtered by registration status.
Register ParticipantTool to register a participant for a conference room.
Send InvitationTool to send invitation emails to participants for a ClickMeeting conference.
Update ConferenceTool to update an existing conference room's parameters.
Upload FileUpload a file to the ClickMeeting file library.

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

Prerequisites

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

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.

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

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

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

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: ["clickmeeting"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Clickmeeting 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 Clickmeeting-related tools through the MCP protocol

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 Clickmeeting tools that the agent can use

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 clickmeeting, 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

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 Clickmeeting 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 Clickmeeting 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: ["clickmeeting"],
  });

  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 clickmeeting, 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 Clickmeeting 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.

How to build Clickmeeting MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Clickmeeting MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Clickmeeting MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Clickmeeting MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Clickmeeting MCP with Claude Cowork

Codex logo

Codex

Use Clickmeeting MCP with Codex

OpenClaw logo

OpenClaw

Use Clickmeeting MCP with OpenClaw

Hermes logo

Hermes

Use Clickmeeting MCP with Hermes

CLI logo

CLI

Use Clickmeeting MCP with CLI

Google ADK logo

Google ADK

Use Clickmeeting MCP with Google ADK

LangChain logo

LangChain

Use Clickmeeting MCP with LangChain

Mastra AI logo

Mastra AI

Use Clickmeeting MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Clickmeeting MCP with LlamaIndex

CrewAI logo

CrewAI

Use Clickmeeting MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Clickmeeting MCP?

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

Can I use Tool Router MCP with Vercel AI SDK v6?

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 Clickmeeting tools.

Can I manage the permissions and scopes for Clickmeeting while using Tool Router?

Yes, absolutely. You can configure which Clickmeeting 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.

How safe is my data with Composio Tool Router?

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 Clickmeeting data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗