SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Botbaba MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Botbaba MCP. Deploy new chatbot to whatsapp channel, update chatbot greeting message instantly, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Botbaba logoBotbaba
Api Key

Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.

42 Tools

Introduction

This guide walks you through connecting Botbaba to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Botbaba agent that can send WhatsApp template messages, manage broadcasts and flows, update contacts and tags, edit message templates, and track message analytics through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Botbaba account through Composio's Botbaba 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 Botbaba 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 Botbaba integration
  • Using Composio's Tool Router to dynamically load and access Botbaba 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 Botbaba MCP server, and what's possible with it?

The Botbaba MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Botbaba account. It provides structured and secure access to your chatbot management platform, so your agent can perform actions like creating bots, updating conversation flows, managing integrations, deploying changes, and monitoring chatbot analytics on your behalf.

  • Bot creation and configuration: Instantly create new chatbots, set up welcome messages, and configure basic settings directly from your agent.
  • Conversational flow management: Update, organize, or refine conversation trees, intents, and responses for smarter, more natural chatbot interactions.
  • Integration with messaging platforms: Enable your agent to connect bots with channels like WhatsApp, Facebook Messenger, and web chat for seamless communication.
  • Real-time deployment and publishing: Push bot changes live or roll back updates—ensuring your chatbots stay current and relevant with minimal effort.
  • Analytics and performance monitoring: Automatically fetch usage statistics, analyze user engagement, and monitor bot performance to optimize conversational experiences.

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: ["botbaba"],
  });

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

  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 botbaba, 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 Botbaba 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 Botbaba action and event your agent gets out of the box.

Shopify Cart Creation Simulator

Tool to simulate a Shopify cart creation webhook payload.

Cart Creation Shopify Webhook

Tool to receive Shopify Cart Creation webhooks.

Cart Update Shopify Webhook

Tool to forward Shopify cart update events to BotBaba.

Shopify Checkout Creation Webhook Receiver

Forward a Shopify checkout creation webhook payload to BotBaba.

Checkout Update Shopify Webhook

Tool to forward Shopify checkout/update events to Botbaba.

Delete a broadcast campaign

Tool to delete a broadcast campaign.

Delete Contact

Tool to delete a contact.

Delete a conversation flow

Tool to delete a conversation flow.

Delete Tag

Tool to delete a tag.

Delete Template

Tool to delete a message template.

Delete a webhook subscription

Tool to delete a webhook subscription.

Execute Bot Action

Request execution of a bot action or workflow, optionally for a specific conversation.

Execute Bot Action By User

Tool to execute a bot action for specific users.

Get Bot Widget Settings

Retrieve widget configuration settings for a bot by ID.

Get Broadcast

Retrieve details of a broadcast by ID.

Get BotBaba Contact

Fetch a BotBaba contact by ID, returning available normalized contact fields.

Get Contact Analytics

Aggregate contact interaction metrics from messages, along with tag and broadcast counts.

Get Filename from Path

Tool to extract the filename from a file path.

Get Flow

Retrieve a flow by ID, including by matching a returned list.

Get Message

Retrieve a specific message by ID to check its delivery status after sending.

Get Message Analytics

Retrieve analytics for a specific message to help assess its delivery and engagement.

Get Template

Tool to retrieve details of a specific template.

Get Webhook

Retrieve details of a Botbaba webhook by ID to inspect its configuration, for example when investigating event deliveries.

List Broadcasts

Tool to list all broadcast campaigns.

List Flows

Tool to list all conversation flows with their IDs and metadata.

List Tags

Tool to list all tags.

List Templates

Tool to retrieve a paginated list of templates.

List Webhook Event Types

List webhook event type identifiers to help choose events when creating or updating a Botbaba webhook.

List Webhooks

Tool to list all registered webhooks.

Receive Shopify Order Cancellation Webhook

Acknowledge a supplied Shopify orders/cancelled webhook payload by returning success; the action does not verify the signature or process the order.

Order Fulfillment Simulator

Tool to simulate a Shopify order fulfillment webhook payload.

Order Fulfillment Shopify Webhook

Acknowledge a supplied Shopify fulfillment webhook payload and extract its fulfillment ID, order ID and status.

Order Payment Shopify Webhook

Acknowledge a supplied Shopify order payment webhook payload and extract order and payment details.

Send WhatsApp Template Message

Send a WhatsApp template message via Botbaba using the full message JSON from the Template UI.

Shopify Checkout Creation Simulator

Tool to simulate a Shopify checkout creation webhook payload.

Shopify Checkout Update Simulator

Tool to simulate a Shopify checkout update webhook payload.

Update Contact

Tool to update an existing contact.

Update Tag

Tool to update an existing tag.

Update Template

Update an existing Botbaba message template by ID, specifying the name, content, type or placeholder definitions to change.

Update Webhook

Update an existing webhook by ID, changing its callback URL, subscribed events, or activation status.

Gupshup WhatsApp Webhook Event Simulator

Tool to simulate Gupshup WhatsApp webhook events.

Forward Gupshup Webhook Message

Tool to forward inbound WhatsApp webhook events from Gupshup to Botbaba.

FRAMEWORKS

How to build Botbaba MCP Agent with another framework

Claude Code logo

Claude Code

Use Botbaba MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Botbaba MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Botbaba MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Botbaba MCP with Claude Agent SDK

Codex logo

Codex

Use Botbaba MCP with Codex

OpenClaw logo

OpenClaw

Use Botbaba MCP with OpenClaw

Hermes logo

Hermes

Use Botbaba MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Botbaba MCP with Atomic Agent

Google ADK logo

Google ADK

Use Botbaba MCP with Google ADK

LangChain logo

LangChain

Use Botbaba MCP with LangChain

Mastra AI logo

Mastra AI

Use Botbaba MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Botbaba MCP with LlamaIndex

CrewAI logo

CrewAI

Use Botbaba MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Botbaba MCP with Pydantic AI

AutoGen logo

AutoGen

Use Botbaba MCP with AutoGen

FAQ

Frequently asked questions

Start with Botbaba.It takes 30 seconds.

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

Start building