SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Botbaba MCP with Autogen

Connect Autogen 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 AutoGen 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 AutoGen 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 ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Botbaba
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Botbaba tools
  • Run a live chat loop where you ask the agent to perform Botbaba operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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 step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Botbaba account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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 dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Botbaba via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Botbaba connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Botbaba session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["botbaba"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Botbaba tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Botbaba assistant agent with MCP tools
    agent = AssistantAgent(
        name="botbaba_assistant",
        description="An AI assistant that helps with Botbaba operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Botbaba tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Botbaba related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Botbaba tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Botbaba and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Botbaba session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["botbaba"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Botbaba assistant agent with MCP tools
        agent = AssistantAgent(
            name="botbaba_assistant",
            description="An AI assistant that helps with Botbaba operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Botbaba related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Botbaba through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Botbaba, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
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

Vercel AI SDK logo

Vercel AI SDK

Use Botbaba MCP with Vercel AI SDK

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

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