How to integrate Whatsapp MCP with Autogen

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

30 min · no commitment · see it on your stack

Whatsapp logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Whatsapp to AutoGen using the Composio tool router. By the end, you'll have a working Whatsapp agent that can send contact card to new lead, get business profile details for support, list all approved message templates through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Whatsapp account through Composio's Whatsapp MCP server.

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

Also integrate Whatsapp with

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 Whatsapp
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Whatsapp tools
  • Run a live chat loop where you ask the agent to perform Whatsapp 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 Whatsapp MCP server, and what's possible with it?

The Whatsapp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your WhatsApp Business account. It provides structured and secure access to your business messaging platform, so your agent can perform actions like sending messages, managing templates, retrieving business info, and automating customer interactions on your behalf.

  • Automated messaging and contact sharing: Let your agent send messages or share contacts directly with customers who have initiated a conversation, making follow-ups and support quick and seamless.
  • Template management and automation: Easily create, retrieve, and delete WhatsApp message templates for marketing or transactional outreach, and keep your approved messages organized.
  • Business profile and phone management: Fetch and update business profile details or pull a full list of WhatsApp Business phone numbers connected to your account for easy management.
  • Media access and metadata retrieval: Direct your agent to download sent media or fetch detailed information about uploaded files—perfect for handling customer attachments or verifying uploads.
  • Template approval and status tracking: Automatically check the approval status of message templates, so your agent knows which templates are ready to use or need revision.

Supported Tools & Triggers

Tools
Triggers
Create message templateCreate a new message template for the WhatsApp Business Account.
Delete message templateDelete a message template from the WhatsApp Business Account by name.
Get business profileGet the business profile information for a WhatsApp Business phone number.
Get media infoGet metadata and download URL for uploaded WhatsApp media.
Get message templatesGet all message templates for the WhatsApp Business Account.
Get phone numberRetrieve detailed information about a specific WhatsApp Business phone number.
Get phone numbersRetrieve all phone numbers registered to your WhatsApp Business Account.
Get template statusGet the status and details of a specific message template.
Send contactsSend contacts WhatsApp number.
Send interactive buttonsSend an interactive button message with up to 3 reply buttons to a WhatsApp user.
Send interactive listSend an interactive list message to a WhatsApp number.
Send locationSend a location message with coordinates, name, and address to a WhatsApp user.
Send mediaSend a media message to a WhatsApp number.
Send media bySend media using a media ID from previously uploaded media.
Send messageSend a text message to a WhatsApp user.
Send template messageSend a template message to a WhatsApp number.
Upload mediaUpload media files (images, videos, audio, documents, stickers) to WhatsApp servers.

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

You will need:

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

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 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 Whatsapp via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Whatsapp connections to use

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 Whatsapp session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["whatsapp"]
    )
    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 Whatsapp tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Whatsapp assistant agent with MCP tools
    agent = AssistantAgent(
        name="whatsapp_assistant",
        description="An AI assistant that helps with Whatsapp 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 Whatsapp tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Whatsapp 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 Whatsapp 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 Whatsapp 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 Whatsapp session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["whatsapp"]
    )
    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 Whatsapp assistant agent with MCP tools
        agent = AssistantAgent(
            name="whatsapp_assistant",
            description="An AI assistant that helps with Whatsapp 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 Whatsapp 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 Whatsapp 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 Whatsapp, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Whatsapp MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Whatsapp MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Whatsapp MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Whatsapp MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Whatsapp MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Whatsapp MCP with Claude Cowork

Codex logo

Codex

Use Whatsapp MCP with Codex

Cursor logo

Cursor

Use Whatsapp MCP with Cursor

OpenClaw logo

OpenClaw

Use Whatsapp MCP with OpenClaw

Hermes logo

Hermes

Use Whatsapp MCP with Hermes

CLI logo

CLI

Use Whatsapp MCP with CLI

Google ADK logo

Google ADK

Use Whatsapp MCP with Google ADK

LangChain logo

LangChain

Use Whatsapp MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Whatsapp MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Whatsapp MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Whatsapp MCP with LlamaIndex

CrewAI logo

CrewAI

Use Whatsapp MCP with CrewAI

OpenCode logo

OpenCode

Use Whatsapp MCP with OpenCode

VS Code logo

VS Code

Use Whatsapp MCP with VS Code

FAQ

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

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

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen 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 Whatsapp tools.

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

Yes, absolutely. You can configure which Whatsapp 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 Whatsapp 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↗