How to integrate Mailerlite MCP with Pydantic AI

This guide walks you through connecting Mailerlite to Pydantic AI 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 through natural language commands. This guide will help you understand how to give your Pydantic AI 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.

Get started for freeGet a demo
Mailerlite logoMailerlite
Api Key

MailerLite is an email marketing service for building, sending, and automating campaigns. It helps businesses reach audiences with beautiful emails, landing pages, and advanced automation.

86 Tools

Introduction

This guide walks you through connecting Mailerlite to Pydantic AI 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 through natural language commands.

This guide will help you understand how to give your Pydantic AI 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.

Also integrate Mailerlite with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Mailerlite
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Mailerlite workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Mailerlite
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Mailerlite
  • MCPServerStreamableHTTP connects to the Mailerlite MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Mailerlite
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["mailerlite"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Mailerlite tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
mailerlite_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[mailerlite_mcp],
    instructions=(
        "You are a Mailerlite assistant. Use Mailerlite tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Mailerlite endpoint
  • The agent uses GPT-5 to interpret user commands and perform Mailerlite operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Mailerlite.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Mailerlite API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Mailerlite and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Mailerlite
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["mailerlite"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    mailerlite_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[mailerlite_mcp],
        instructions=(
            "You are a Mailerlite assistant. Use Mailerlite tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Mailerlite.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

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

Conclusion

You've built a Pydantic AI agent that can interact with Mailerlite through Composio's Tool Router. With this setup, your agent can perform real Mailerlite actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Mailerlite for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

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

Add Product to Category

Tool to add a product to a category in an e-commerce shop.

Add Subscriber To Group

Tool to assign an existing subscriber to a group.

Create automation

Create automation

Create Campaign

Tool to create a new email campaign (draft) with specified type, content, and targeting.

Create E-commerce Cart Item

Tool to add an item to a shopping cart.

Create E-commerce Category

Tool to create a new product category for a shop.

Create/Update E-commerce Customer

Tool to create or update a customer record for a shop.

Create E-commerce Order

Tool to create a new order for a shop.

Create E-commerce Product

Tool to create a new product for an e-commerce shop.

Create E-commerce Shop

Tool to connect a new e-commerce shop.

Create Field

Tool to create a new custom field.

Create Group

Tool to create a new subscriber group.

Create Segment

Tool to create a new subscriber segment.

Create Subscriber

Tool to create or update (upsert) a subscriber by email.

Create Webhook

Tool to register a new webhook URL for specified event types.

Delete Automation

Tool to delete an automation workflow by ID.

Delete E-commerce Cart Item

Tool to remove an item from a cart in an e-commerce shop.

Delete E-commerce Category

Tool to delete a product category from an e-commerce shop by IDs.

Delete E-commerce Customer

Tool to delete a customer from an e-commerce shop by IDs.

Delete E-commerce Order

Tool to delete an order from a shop.

Delete E-commerce Product

Tool to delete a product from an e-commerce shop by IDs.

Delete E-commerce Shop

Tool to disconnect an e-commerce shop by ID.

Delete Field

Tool to delete a custom field.

Delete Group

Tool to delete a subscriber group by ID.

Delete Segment

Tool to delete a segment by ID.

Delete Subscriber

Tool to delete a subscriber by ID.

Delete Webhook

Tool to remove a webhook subscription by ID.

Execute Batch Request

Tool to execute multiple API requests in a single batch call (max 50 requests).

Forget Subscriber

Tool to forget a subscriber completely (GDPR compliant deletion).

Get Account Info

Tool to retrieve basic MailerLite account details.

Get Account Stats

Tool to retrieve usage statistics and performance metrics for the account.

Get Automation

Tool to retrieve details of a specific automation by ID.

Get Automation Activity

Tool to retrieve subscriber activity for a specific automation.

Get Campaign Languages

Tool to retrieve a list of all available campaign languages.

Get Campaigns

Tool to retrieve a list of all campaigns.

Get E-commerce Cart

Tool to fetch details of a specific cart by shop ID and cart ID.

Get E-commerce Cart Item

Tool to fetch details of a specific cart item by shop ID, cart ID, and item ID.

Get E-commerce Category

Tool to fetch details of a specific product category by shop and category ID.

Get E-commerce Customer

Tool to fetch details of a customer by shop and customer ID.

Get E-commerce Customers

Tool to list customers for a specific shop.

Get E-commerce Order

Tool to fetch details of a specific e-commerce order by shop ID and order ID.

Get E-commerce Product

Tool to fetch details of a specific e-commerce product by shop and product ID.

Get E-commerce Shop

Tool to fetch details of a specific e-commerce shop by ID.

Get E-commerce Shops

Tool to list all e-commerce shops connected to the account.

Get Fields

Tool to retrieve all custom fields defined in the account.

Get Group

Tool to retrieve details of a specific subscriber group by ID.

Get Groups

Tool to retrieve all subscriber groups.

Get Group Subscribers

Tool to list subscribers within a group by ID.

Get Import Status

Tool to retrieve the status and detailed report of a subscriber import operation by import ID.

Get Segment

Tool to retrieve a specific segment by ID.

Get Segments

Tool to retrieve all segments in the account.

Get Segment Subscribers

Tool to retrieve all subscribers belonging to a specific segment.

Get Subscriber

Tool to fetch a single subscriber by ID or email address.

Get Subscriber Activity

Tool to fetch the activity log for a specific subscriber.

Get Subscribers

Tool to retrieve all subscribers.

Get Subscribers Stats

Tool to get subscriber statistics for the account.

Get Webhook

Tool to retrieve details of a specific webhook by ID.

Get Webhooks

Tool to retrieve all configured webhooks.

Import E-commerce Categories

Tool to bulk import categories to an e-commerce shop.

Import E-commerce Orders

Tool to bulk import orders to an e-commerce shop.

Import E-commerce Products

Tool to bulk import products to an e-commerce shop.

Import Subscribers to Group

Tool to bulk import multiple subscribers to a specific group.

List Automations

Tool to retrieve all automations in your MailerLite account.

List E-commerce Cart Items

Tool to list all items in a specific cart for an e-commerce shop.

List E-commerce Carts

Tool to list all carts for a specific shop.

List E-commerce Categories

Tool to list all product categories for a shop.

List E-commerce Category Products

Tool to list all products in a specific e-commerce category.

List E-commerce Orders

Tool to list all orders for a specific e-commerce shop.

List E-commerce Products

Tool to list all products for a specific e-commerce shop.

List Forms

Tool to retrieve all forms of a specific type (popup, embedded, or promotion).

List Timezones

Tool to retrieve all available timezones supported by MailerLite.

Remove Product From Category

Tool to remove a product from a category in an e-commerce shop.

Remove Subscriber From Group

Tool to remove a subscriber from a group by ID.

Set Double Opt-In

Tool to enable or disable double opt-in for new subscribers.

Update E-commerce Cart

Tool to update an existing cart's checkout URL or total price.

Update E-commerce Cart Item

Tool to update a cart item's quantity or properties in an e-commerce cart.

Update E-commerce Category

Tool to update an existing product category in an e-commerce shop.

Update E-commerce Customer

Tool to update a customer's data for a shop by IDs.

Update E-commerce Order

Tool to update an existing order's status or total price in an e-commerce shop.

Update E-commerce Product

Tool to update an existing product in an e-commerce shop by IDs.

Update E-commerce Shop

Tool to update settings of a connected e-commerce shop by ID.

Update Field

Tool to update the title of an existing custom field.

Update Group

Tool to update a group's name by ID.

Update Segment

Tool to rename an existing segment by ID.

Update Subscriber

Tool to update an existing subscriber's information by ID.

Update Webhook

Tool to update an existing MailerLite webhook.

FRAMEWORKS

How to build Mailerlite MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Mailerlite MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Mailerlite MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Mailerlite MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Mailerlite MCP with Claude Cowork

Codex logo

Codex

Use Mailerlite MCP with Codex

OpenClaw logo

OpenClaw

Use Mailerlite MCP with OpenClaw

Hermes logo

Hermes

Use Mailerlite MCP with Hermes

CLI logo

CLI

Use Mailerlite MCP with CLI

Google ADK logo

Google ADK

Use Mailerlite MCP with Google ADK

LangChain logo

LangChain

Use Mailerlite MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Mailerlite MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Mailerlite MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Mailerlite MCP with LlamaIndex

CrewAI logo

CrewAI

Use Mailerlite MCP with CrewAI

FAQ

Frequently asked questions

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.

Yes, you can. Pydantic AI 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.

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.

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.

Start with Mailerlite.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies