How to integrate Bigmailer MCP with Autogen

This guide walks you through connecting Bigmailer to AutoGen using the Composio tool router. By the end, you'll have a working Bigmailer agent that can create a new welcome campaign for brand x, list all brands i manage in bigmailer, get your bigmailer account user details through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Bigmailer account through Composio's Bigmailer MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Bigmailer logoBigmailer
Api Key

BigMailer is an email marketing platform for managing multiple brands with white-labeling and automation. It helps teams streamline campaigns and simplify integration with Amazon SES.

57 Tools

Introduction

This guide walks you through connecting Bigmailer to AutoGen using the Composio tool router. By the end, you'll have a working Bigmailer agent that can create a new welcome campaign for brand x, list all brands i manage in bigmailer, get your bigmailer account user details through natural language commands.

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

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

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

The Bigmailer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bigmailer account. It provides structured and secure access to your email marketing platform, so your agent can perform actions like creating transactional campaigns, retrieving your brands, and managing user account details on your behalf.

  • Automated transactional campaign creation: Have your agent quickly set up new transactional email campaigns for any of your brands, with full control over content, sender details, and subject lines.
  • Brand management and discovery: Let your agent list and organize all brands associated with your Bigmailer account, providing a clear overview for multi-brand operations.
  • User account information retrieval: Easily check your authenticated user details to verify API connectivity and view essential account information in real time.
  • Multi-brand marketing workflow automation: Empower your agent to streamline campaign launches and brand management across multiple business entities from one place.

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 Bigmailer 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 Bigmailer 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 Bigmailer 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 Bigmailer session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bigmailer"]
    )
    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 Bigmailer 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 Bigmailer assistant agent with MCP tools
    agent = AssistantAgent(
        name="bigmailer_assistant",
        description="An AI assistant that helps with Bigmailer 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 Bigmailer 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 Bigmailer 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 Bigmailer 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 Bigmailer 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 Bigmailer session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bigmailer"]
    )
    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 Bigmailer assistant agent with MCP tools
        agent = AssistantAgent(
            name="bigmailer_assistant",
            description="An AI assistant that helps with Bigmailer 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 Bigmailer 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 Bigmailer 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 Bigmailer, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Bigmailer action and event your agent gets out of the box.

Create Brand

Tool to create a new brand in BigMailer.

Create Brand Property

Tool to create a brand property in BigMailer.

Create Bulk Campaign

Tool to create a bulk email campaign in BigMailer.

Create Contact

Tool to create a new contact in BigMailer within a specified brand.

Create Contact Batch

Tool to create a batch of contacts in BigMailer for a specific brand.

Create Field

Tool to create a custom field in a BigMailer brand.

Create List

Creates a new contact list within a specified brand in BigMailer.

Create Segment

Tool to create a segment in BigMailer for a specific brand.

Create Suppression List

Tool to upload a suppression list for a brand in BigMailer.

Create Template

Tool to create a new email or page template in BigMailer.

Create Transactional Campaign

Creates a new transactional campaign within a specified brand in BigMailer.

Create User

Tool to create a new user in BigMailer.

Delete Brand Property

Tool to delete a brand property from a brand in BigMailer.

Delete Contact

Tool to delete a contact from a brand in BigMailer.

Delete Custom Field

Deletes a custom field from a specified brand in BigMailer.

Delete List

Tool to delete a list from BigMailer.

Delete Segment

Tool to delete a segment from a brand in BigMailer.

Delete Template

Tool to delete a template from BigMailer.

Delete User

Tool to delete a user from BigMailer.

Get Brand

Tool to retrieve detailed information about a specific brand by its ID.

Get Brand Property

Tool to retrieve a specific brand property by its ID for a given brand.

Get Bulk Campaign

Tool to retrieve detailed information about a specific bulk campaign in BigMailer.

Get Contact

Tool to retrieve detailed information about a specific contact from BigMailer.

Get Contact Batch Status

Tool to retrieve the status and results of a contact batch upload in BigMailer.

Get Custom Field

Tool to retrieve a custom field from a BigMailer brand.

Get List

Tool to retrieve details of a specific list within a brand.

Get Segment

Tool to retrieve a specific segment from BigMailer by brand ID and segment ID.

Get Suppression List

Tool to retrieve details of a specific suppression list for a brand in BigMailer.

Get Template

Tool to retrieve detailed information about a specific template by its ID.

Get Transactional Campaign

Tool to retrieve detailed information about a specific transactional campaign in BigMailer.

Get User

Tool to retrieve detailed information about a specific user by their ID.

Get User Information

This tool retrieves information about the authenticated user in BigMailer using the GET /me endpoint.

List All Brands

This tool retrieves a list of all brands associated with the authenticated BigMailer account.

List Brand Properties

Tool to retrieve a list of brand properties for a specific brand in BigMailer.

List Bulk Campaigns

Tool to list bulk campaigns for a specified brand in BigMailer.

List Connections

Tool to list all connections in your BigMailer account.

List Contacts

Tool to list contacts for a brand in BigMailer.

List Fields

Tool to list custom fields for a brand in BigMailer.

List Contact Lists

Tool to retrieve all contact lists for a specified brand in BigMailer.

List Message Types

Tool to list message types for a specific brand in BigMailer.

List Segments

Tool to list segments for a brand in BigMailer.

List Senders

Tool to list all senders configured for a specific brand in BigMailer.

List Suppression Lists

Tool to list suppression lists for a specific brand.

List Templates

Tool to list templates for a brand in BigMailer.

List Transactional Campaigns

Tool to list transactional campaigns for a specified brand in BigMailer.

List Users

Tool to list all users in your BigMailer account.

Update Brand

Tool to update a brand in BigMailer.

Update Brand Property

Tool to update a brand property in BigMailer.

Update Bulk Campaign

Tool to update an existing bulk campaign in BigMailer.

Update Contact

Tool to update an existing contact in BigMailer.

Update Field

Tool to update a custom field in BigMailer.

Update List

Tool to update a list in BigMailer.

Update Segment

Tool to update an existing segment in BigMailer.

Update Template

Tool to update an existing email or page template in BigMailer.

Update Transactional Campaign

Tool to update a transactional campaign in BigMailer.

Update User

Tool to update a user in BigMailer.

Upsert Contact

Tool to create or update a contact in a BigMailer brand.

FAQ

Frequently asked questions

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

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 Bigmailer tools.

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

Start with Bigmailer.It takes 30 seconds.

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

Start building