How to integrate Mailcoach MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Mailcoach Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Mailcoach to the OpenAI Agents SDK 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, confirm a subscriber's double opt-in registration through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK 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.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Mailcoach
  • Configure an AI agent that can use Mailcoach as a tool
  • Run a live chat session where you can ask the agent to perform Mailcoach operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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.

Supported Tools & Triggers

Tools
Add Mailcoach CampaignTool to create a new mailcoach campaign.
Add Email ListTool to create a new email list.
Add suppressionTool to add a suppression entry.
Add Tag to Email ListTool to create a new tag within a specific email list.
Add Tags to SubscriberTool to add tags to a subscriber.
Add TemplateTool to create a new email template.
Add Transactional Email TemplateTool to create a new template that can be used for transactional emails.
Append to Subscriber ImportTool to append csv data to an existing subscriber import.
Confirm SubscriberTool to confirm a subscriber’s subscription.
Create Subscriber ImportTool to create a new subscriber import.
Delete CampaignTool to delete a campaign by uuid.
Delete Email ListTool to delete an email list by uuid.
Delete SendTool to delete a sent item by its uuid.
Delete SubscriberTool to delete a subscriber by uuid.
Delete Subscriber ImportTool to delete a subscriber import by its uuid.
Delete SuppressionTool to delete a suppression entry by uuid.
Delete Tag from Email ListTool to delete a tag from an email list.
Delete TemplateTool to delete a template by uuid.
Delete Transactional MailTool to delete a transactional mail by its uuid.
Get All CampaignsTool to retrieve all campaigns.
Get All Sent ItemsTool to retrieve all sent items.
Get All Subscriber ImportsTool to retrieve all subscriber imports.
Get All SuppressionsTool to list all suppression entries.
Get All TagsTool to retrieve all tags for a specific email list.
Get All TemplatesTool to retrieve all templates.
Get All Transactional Email TemplatesTool to retrieve all transactional email templates.
Get Email ListsTool to retrieve all email lists.
Get Specific CampaignTool to retrieve details of a specific mailcoach campaign.
Get Specific Email ListTool to retrieve a specific email list.
Get Specific SubscriberTool to retrieve a specific subscriber.
Get Specific SuppressionTool to retrieve a specific suppression entry.
Get Specific TagTool to retrieve details of a specific tag.
Get Specific TemplateTool to retrieve details of a specific template.
Get Transactional MailsTool to retrieve all transactional mail templates.
Remove Tags from SubscriberTool to remove tags from a subscriber.
Resend Subscriber ConfirmationTool to resend confirmation email to a subscriber.
Start Subscriber ImportTool to start processing a subscriber import.
Subscribe To Email ListTool to add or update a subscriber in an email list.
Unsubscribe SubscriberTool to unsubscribe a subscriber from an email list.
Update CampaignTool to update an existing mailcoach campaign.
Update Email ListTool to update an existing email list.
Update SubscriberTool to update a subscriber.
Update Subscriber ImportTool to update an existing subscriber import.
Update TagTool to update an existing tag within an email list.
Update TemplateTool to update an existing template's name or content.

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

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Mailcoach project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Mailcoach.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Mailcoach Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["mailcoach"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only mailcoach.
  • The router checks the user's Mailcoach connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Mailcoach.
  • This approach keeps things lightweight and lets the agent request Mailcoach tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Mailcoach. "
        "Help users perform Mailcoach operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Mailcoach and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Mailcoach operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Mailcoach.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Mailcoach and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["mailcoach"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Mailcoach. "
        "Help users perform Mailcoach operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Mailcoach MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Mailcoach.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Mailcoach MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Mailcoach MCP with Claude Agent SDK

Google ADK

Google ADK

Use Mailcoach MCP with Google ADK

LangChain

LangChain

Use Mailcoach MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Mailcoach MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Mailcoach MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Mailcoach MCP with LlamaIndex

CrewAI

CrewAI

Use Mailcoach MCP with CrewAI

FAQ

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

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.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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.

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

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.

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 Mailcoach data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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