How to integrate Mailerlite MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Mailerlite Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Mailerlite to AutoGen using the Composio tool router. By the end, you'll have a working Mailerlite agent that can create a new subscriber group called vip customers, add a custom field for subscriber birthday, create a segment for recent e-commerce buyers, delete an automation workflow that's no longer used through natural language commands.

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

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

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

The Mailerlite MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mailerlite account. It provides structured and secure access to your email marketing tools, so your agent can create campaigns, manage subscribers, automate workflows, and oversee your shop integrations with ease.

  • Campaign automation and workflow management: Instruct your agent to create or delete automations, streamlining your email marketing processes and ensuring timely communication with your audience.
  • E-commerce customer and shop integration: Let your agent create, update, or remove e-commerce customers and shops for seamless sales tracking, customer onboarding, or data syncing.
  • Subscriber group and segment organization: Have your agent create custom fields, new subscriber groups, or targeted segments so you can send highly personalized campaigns.
  • Webhook registration for real-time updates: Direct your agent to set up webhooks for specific events, enabling instant notifications and integrations with other systems as actions happen in Mailerlite.
  • Efficient cleanup and management: Ask your agent to delete outdated automations, customers, or shops, helping you keep your Mailerlite workspace organized and up to date.

Supported Tools & Triggers

Tools
Create automationCreate automation
Create/Update E-commerce CustomerTool to create or update a customer record for a shop.
Create E-commerce ShopTool to connect a new e-commerce shop.
Create FieldTool to create a new custom field.
Create GroupTool to create a new subscriber group.
Create SegmentTool to create a new subscriber segment.
Create WebhookTool to register a new webhook url for specified event types.
Delete AutomationTool to delete an automation workflow by id.
Delete E-commerce CustomerTool to delete a customer from an e-commerce shop by ids.
Delete E-commerce ShopTool to disconnect an e-commerce shop by id.
Delete FieldTool to delete a custom field.
Delete GroupTool to delete a subscriber group by id.
Delete SegmentTool to delete a segment by id.
Delete SubscriberTool to delete a subscriber by id.
Delete WebhookTool to remove a webhook subscription by id.
Fetch Total E-commerce Customers CountTool to fetch total ecommerce customers count for a shop.
Get Account InfoTool to retrieve basic mailerlite account details.
Get Account StatsTool to retrieve usage statistics and performance metrics for the account.
Get AutomationTool to retrieve details of a specific automation by id.
Get CampaignsTool to retrieve a list of all campaigns.
Get E-commerce CustomerTool to fetch details of a customer by shop and customer id.
Get E-commerce CustomersTool to list customers for a specific shop.
Get E-commerce ShopTool to fetch details of a specific e-commerce shop by id.
Get E-commerce ShopsTool to list all e-commerce shops connected to the account.
Get FieldsTool to retrieve all custom fields defined in the account.
Get GroupsTool to retrieve all subscriber groups.
Get Group SubscribersTool to list subscribers within a group by id.
Get SegmentsTool to retrieve all segments in the account.
Get SubscribersTool to retrieve all subscribers.
Get WebhooksTool to retrieve all configured webhooks.
Set Double Opt-InTool to enable or disable double opt-in for new subscribers.
Update E-commerce CustomerTool to update a customer's data for a shop by ids.
Update E-commerce ShopTool to update settings of a connected e-commerce shop by id.
Update FieldTool to update the title of an existing custom field.
Update GroupTool to update a group's name by id.
Update SegmentTool to rename an existing segment by id.
Update SubscriberTool to update an existing subscriber's information by id.
Update WebhookTool to update an existing mailerlite webhook.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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 Mailerlite 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 Mailerlite 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 Mailerlite 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 Mailerlite session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["mailerlite"]
    )
    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 Mailerlite 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 Mailerlite assistant agent with MCP tools
    agent = AssistantAgent(
        name="mailerlite_assistant",
        description="An AI assistant that helps with Mailerlite 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 Mailerlite 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 Mailerlite 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 Mailerlite 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 Mailerlite and AutoGen:

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

How to build Mailerlite MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Mailerlite MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Mailerlite MCP with Claude Agent SDK

Google ADK

Google ADK

Use Mailerlite MCP with Google ADK

LangChain

LangChain

Use Mailerlite MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Mailerlite MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Mailerlite MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Mailerlite MCP with LlamaIndex

CrewAI

CrewAI

Use Mailerlite MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Mailerlite 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 Mailerlite 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.

Book a call↗Get started for free