How to integrate Bigmailer MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Bigmailer logo
OpenAI Agents SDK logo
divider

Introduction

This guide walks you through connecting Bigmailer to the OpenAI Agents SDK 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 OpenAI Agents SDK 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 necessary dependencies
  • Initialize Composio and create a Tool Router session for Bigmailer
  • Configure an AI agent that can use Bigmailer as a tool
  • Run a live chat session where you can ask the agent to perform Bigmailer operations

What is OpenAI 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 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.

Supported Tools & Triggers

Tools
Create BrandTool to create a new brand in BigMailer.
Create Brand PropertyTool to create a brand property in BigMailer.
Create Bulk CampaignTool to create a bulk email campaign in BigMailer.
Create ContactTool to create a new contact in BigMailer within a specified brand.
Create Contact BatchTool to create a batch of contacts in BigMailer for a specific brand.
Create FieldTool to create a custom field in a BigMailer brand.
Create ListCreates a new contact list within a specified brand in BigMailer.
Create SegmentTool to create a segment in BigMailer for a specific brand.
Create Suppression ListTool to upload a suppression list for a brand in BigMailer.
Create TemplateTool to create a new email or page template in BigMailer.
Create Transactional CampaignCreates a new transactional campaign within a specified brand in BigMailer.
Create UserTool to create a new user in BigMailer.
Delete Brand PropertyTool to delete a brand property from a brand in BigMailer.
Delete ContactTool to delete a contact from a brand in BigMailer.
Delete Custom FieldDeletes a custom field from a specified brand in BigMailer.
Delete ListTool to delete a list from BigMailer.
Delete SegmentTool to delete a segment from a brand in BigMailer.
Delete TemplateTool to delete a template from BigMailer.
Delete UserTool to delete a user from BigMailer.
Get BrandTool to retrieve detailed information about a specific brand by its ID.
Get Brand PropertyTool to retrieve a specific brand property by its ID for a given brand.
Get Bulk CampaignTool to retrieve detailed information about a specific bulk campaign in BigMailer.
Get ContactTool to retrieve detailed information about a specific contact from BigMailer.
Get Contact Batch StatusTool to retrieve the status and results of a contact batch upload in BigMailer.
Get Custom FieldTool to retrieve a custom field from a BigMailer brand.
Get ListTool to retrieve details of a specific list within a brand.
Get SegmentTool to retrieve a specific segment from BigMailer by brand ID and segment ID.
Get Suppression ListTool to retrieve details of a specific suppression list for a brand in BigMailer.
Get TemplateTool to retrieve detailed information about a specific template by its ID.
Get Transactional CampaignTool to retrieve detailed information about a specific transactional campaign in BigMailer.
Get UserTool to retrieve detailed information about a specific user by their ID.
Get User InformationThis tool retrieves information about the authenticated user in BigMailer using the GET /me endpoint.
List All BrandsThis tool retrieves a list of all brands associated with the authenticated BigMailer account.
List Brand PropertiesTool to retrieve a list of brand properties for a specific brand in BigMailer.
List Bulk CampaignsTool to list bulk campaigns for a specified brand in BigMailer.
List ConnectionsTool to list all connections in your BigMailer account.
List ContactsTool to list contacts for a brand in BigMailer.
List FieldsTool to list custom fields for a brand in BigMailer.
List Contact ListsTool to retrieve all contact lists for a specified brand in BigMailer.
List Message TypesTool to list message types for a specific brand in BigMailer.
List SegmentsTool to list segments for a brand in BigMailer.
List SendersTool to list all senders configured for a specific brand in BigMailer.
List Suppression ListsTool to list suppression lists for a specific brand.
List TemplatesTool to list templates for a brand in BigMailer.
List Transactional CampaignsTool to list transactional campaigns for a specified brand in BigMailer.
List UsersTool to list all users in your BigMailer account.
Update BrandTool to update a brand in BigMailer.
Update Brand PropertyTool to update a brand property in BigMailer.
Update Bulk CampaignTool to update an existing bulk campaign in BigMailer.
Update ContactTool to update an existing contact in BigMailer.
Update FieldTool to update a custom field in BigMailer.
Update ListTool to update a list in BigMailer.
Update SegmentTool to update an existing segment in BigMailer.
Update TemplateTool to update an existing email or page template in BigMailer.
Update Transactional CampaignTool to update a transactional campaign in BigMailer.
Update UserTool to update a user in BigMailer.
Upsert ContactTool to create or update a contact in a BigMailer brand.

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

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Bigmailer 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 Bigmailer.

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 Bigmailer Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["bigmailer"]
)

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 bigmailer.
  • The router checks the user's Bigmailer connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Bigmailer.
  • This approach keeps things lightweight and lets the agent request Bigmailer 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 Bigmailer. "
        "Help users perform Bigmailer 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 Bigmailer 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 Bigmailer 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 Bigmailer.
  • 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 Bigmailer and OpenAI 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=["bigmailer"]
)
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 Bigmailer. "
        "Help users perform Bigmailer 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 Bigmailer MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Bigmailer.

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 Bigmailer MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Bigmailer MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Bigmailer MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bigmailer MCP with Claude Cowork

Codex logo

Codex

Use Bigmailer MCP with Codex

OpenClaw logo

OpenClaw

Use Bigmailer MCP with OpenClaw

Hermes logo

Hermes

Use Bigmailer MCP with Hermes

CLI logo

CLI

Use Bigmailer MCP with CLI

Google ADK logo

Google ADK

Use Bigmailer MCP with Google ADK

LangChain logo

LangChain

Use Bigmailer MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Bigmailer MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Bigmailer MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Bigmailer MCP with LlamaIndex

CrewAI logo

CrewAI

Use Bigmailer MCP with CrewAI

FAQ

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

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.

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 Bigmailer tools.

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

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.

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 Bigmailer 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.

Get started for freeGet a demo↗