How to integrate Mailcoach MCP with Autogen

This guide walks you through connecting Mailcoach to AutoGen using the Composio tool router. By the end, you'll have a working Mailcoach agent that can create a new email campaign for product launch, add a subscriber to the weekly newsletter list, tag all subscribers interested in webinars through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Mailcoach account through Composio's Mailcoach MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Mailcoach logoMailcoach
Api Key

Mailcoach is an email marketing platform for managing campaigns and subscribers. It helps you reach your audience efficiently with streamlined email delivery and automation.

56 Tools

Introduction

This guide walks you through connecting Mailcoach to AutoGen using the Composio tool router. By the end, you'll have a working Mailcoach agent that can create a new email campaign for product launch, add a subscriber to the weekly newsletter list, tag all subscribers interested in webinars through natural language commands.

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

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

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

The Mailcoach MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mailcoach account. It provides structured and secure access to your email marketing platform, so your agent can manage campaigns, organize subscriber lists, create templates, and automate email workflows on your behalf.

  • Email campaign creation and scheduling: Direct your agent to launch new campaigns, send emails to specific lists, or set up campaign schedules based on your marketing needs.
  • Subscriber list and segmentation management: Let your agent create new email lists, add or confirm subscribers, and apply tags for better audience segmentation and targeting.
  • Template management and customization: Instruct your agent to create, update, or organize reusable email templates and transactional templates for efficient campaign building.
  • Automated suppression and bounce handling: Have your agent add suppressions for bounced or blocked addresses, keeping your lists clean and compliant with deliverability best practices.
  • Bulk subscriber import and data enrichment: Enable your agent to import subscribers via CSV, append new data to existing imports, and streamline growth of your contact lists.

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

Supported Tools

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

Add Mailcoach Campaign

Tool to create a new Mailcoach campaign.

Add Email List

Tool to create a new email list.

Add suppression

Tool to add a suppression entry.

Add Tag to Email List

Tool to create a new tag within a specific email list.

Add Tags to Subscriber

Add tags to a subscriber for segmentation and targeting.

Add Transactional Email Template

Creates a new email template in Mailcoach via POST /api/templates.

Append to Subscriber Import

Tool to append CSV data to an existing subscriber import.

Confirm Subscriber

Confirm a subscriber's subscription to an email list (double opt-in confirmation).

Create Segment for Email List

Tool to create a new segment within an email list.

Create Subscriber Import

Creates a new subscriber import in Mailcoach.

Delete Campaign

Tool to delete a campaign by UUID.

Delete Email List

Tool to delete an email list by UUID.

Delete Segment from Email List

Tool to delete a segment from an email list.

Delete Subscriber

Permanently delete a subscriber by UUID from Mailcoach.

Delete Subscriber Import

Tool to delete a subscriber import by its UUID.

Delete Suppression

Tool to delete a suppression entry by UUID.

Delete Tag from Email List

Tool to delete a tag from an email list.

Delete Template

Tool to delete a template by UUID.

Delete Transactional Mail

Tool to delete a transactional mail send record by its UUID.

Get All Campaigns

Tool to retrieve all campaigns.

Get All Sent Items

Tool to retrieve all sent items.

Get All Subscriber Imports

Tool to retrieve all subscriber imports.

Get All Suppressions

Retrieve a paginated list of all email suppression entries from Mailcoach.

Get All Tags

Tool to retrieve all tags for a specific email list.

Get All Templates

Tool to retrieve all templates.

Get All Transactional Email Templates

Tool to retrieve all transactional email templates.

Get Campaign Bounces

Tool to retrieve bounced subscribers of a sent campaign with pagination support.

Get Campaign Clicks

Tool to retrieve clicks from a sent campaign with pagination support.

Get Campaign Opens

Tool to retrieve all opens for a sent campaign with pagination support.

Get Campaign Unsubscribes

Tool to retrieve unsubscribes from a sent campaign with pagination support.

Get Email Lists

Tool to retrieve all email lists.

Get Segment

Tool to retrieve details of a specific segment.

Get Specific Campaign

Tool to retrieve details of a specific Mailcoach campaign.

Get Specific Email List

Retrieve detailed information about a specific Mailcoach email list by its UUID.

Get Specific Subscriber

Tool to retrieve a specific subscriber.

Get Specific Suppression

Tool to retrieve a specific suppression entry.

Get Specific Tag

Tool to retrieve details of a specific tag.

Get Specific Template

Retrieves the full details of a specific Mailcoach email template by its UUID.

Get Subscriber Import

Tool to retrieve details of a specific subscriber import by UUID.

Get Transactional Mail

Tool to retrieve details of a specific transactional email by its UUID.

Get User

Tool to retrieve details of the currently authenticated user.

List Segments

Tool to retrieve all segments for a specific email list.

List Subscribers

Tool to list all subscribers from a specific email list with pagination support.

List Transactional Mails

Tool to retrieve all transactional email records.

Remove Tags from Subscriber

Tool to remove tags from a subscriber.

Resend Subscriber Confirmation

Tool to resend confirmation email to a subscriber.

Start Subscriber Import

Starts processing a subscriber import that is in 'draft' status.

Subscribe To Email List

Subscribe (or update) a subscriber to an email list.

Unsubscribe Subscriber

Unsubscribe a subscriber from their email list in Mailcoach.

Update Campaign

Tool to update an existing Mailcoach campaign.

Update Email List

Tool to update an existing email list.

Update Segment

Tool to update an existing segment within an email list.

Update Subscriber

Tool to update a subscriber.

Update Subscriber Import

Tool to update an existing subscriber import.

Update Tag

Tool to update an existing tag within an email list.

Update Template

Updates an existing email template in Mailcoach.

FAQ

Frequently asked questions

With a standalone Mailcoach MCP server, the agents and LLMs can only access a fixed set of Mailcoach tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mailcoach 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 Mailcoach tools.

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

Start with Mailcoach.It takes 30 seconds.

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

Start building