How to integrate Mailtrap MCP with Autogen

GET STARTED FOR FREE
Framework Integration Gradient
Mailtrap Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Mailtrap to AutoGen using the Composio tool router. By the end, you'll have a working Mailtrap agent that can send a test email to marketing team, list all emails sent from mailtrap today, create a new inbox for transactional testing through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Mailtrap account through Composio's Mailtrap 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 Mailtrap
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Mailtrap tools
  • Run a live chat loop where you ask the agent to perform Mailtrap 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 Mailtrap MCP server, and what's possible with it?

The Mailtrap MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mailtrap account. It provides structured and secure access so your agent can perform Mailtrap operations on your behalf.

Supported Tools & Triggers

Tools
Clean InboxTool to clean an inbox in Mailtrap by deleting all messages.
Create ContactTool to create a new contact in Mailtrap.
Create Contact EventTool to create a contact event in Mailtrap.
Create Contact ExportTool to create a contact export job for a Mailtrap account.
Create Contact FieldTool to create a custom contact field in Mailtrap.
Create Contact ListTool to create a new contact list in Mailtrap.
Create Email TemplateTool to create a new email template in Mailtrap account.
Create Sending DomainTool to create a new sending domain in Mailtrap.
Delete ContactTool to delete a contact from a Mailtrap account.
Delete Contact FieldTool to delete a contact field by its ID.
Delete Contact ListTool to delete a contact list by its ID.
Delete Email TemplateTool to delete an email template from a Mailtrap account.
Delete ProjectTool to delete a project from Mailtrap.
Delete Sending DomainTool to delete a sending domain from a Mailtrap account.
Get Billing UsageTool to retrieve current billing cycle usage for an account.
Get ContactTool to retrieve a contact by UUID or email address from Mailtrap.
Get Contact ExportTool to retrieve the status of a contact export.
Get Contact FieldTool to retrieve contact field details by field ID.
Get Contact Import StatusTool to retrieve the status of a contact import operation.
Get Contact ListTool to retrieve a specific contact list by its ID.
Get Email TemplateTool to retrieve details of a specific email template by ID.
Get Inbox AttributesTool to retrieve inbox attributes from Mailtrap.
Get Message HTML BodyTool to retrieve the HTML body of a message from Mailtrap.
Get Permission ResourcesTool to retrieve all resources in account for permission management.
Get Project by IDTool to retrieve project details from Mailtrap by project ID.
Get Sending DomainTool to retrieve sending domain details from Mailtrap.
Get Sending StatsTool to retrieve email sending statistics from Mailtrap for a specific account.
Get Sending Stats by CategoriesTool to retrieve email sending statistics grouped by categories.
Get Sending Stats by DateTool to retrieve email sending statistics aggregated by date.
Get Sending Stats by DomainsTool to retrieve sending statistics grouped by domains for a Mailtrap account.
Get Sending Stats by ESPTool to retrieve email sending statistics grouped by email service providers (ESPs) for a specified date range.
Import ContactsTool to import contacts in bulk to Mailtrap.
List AccountsTool to list all Mailtrap accounts you have access to.
List Contact FieldsTool to get all contact fields for a Mailtrap account.
List Contact ListsTool to retrieve all contact lists for a Mailtrap account.
List Email TemplatesTool to retrieve all email templates for a Mailtrap account.
List InboxesTool to get a list of inboxes for a Mailtrap account.
List Messages in InboxTool to get messages from a Mailtrap inbox.
List ProjectsTool to get a list of projects for a Mailtrap account.
List Sending DomainsTool to list all sending domains for a Mailtrap account.
List Email SuppressionsTool to list suppressed email addresses for a Mailtrap account.
Mark Inbox as ReadTool to mark all messages in a Mailtrap inbox as read.
Reset Inbox CredentialsTool to reset SMTP credentials for a Mailtrap inbox.
Update contactTool to update an existing contact in Mailtrap.
Update Contact FieldTool to update a contact field in Mailtrap.
Update Contact ListTool to update a contact list's name in Mailtrap.
Update Email TemplateTool to update an existing email template in Mailtrap account.
Update inboxTool to update an inbox's settings in Mailtrap.
Update projectTool to update a project's name in Mailtrap.

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

How to build Mailtrap MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Mailtrap MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Mailtrap MCP with Claude Agent SDK

Google ADK

Google ADK

Use Mailtrap MCP with Google ADK

LangChain

LangChain

Use Mailtrap MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Mailtrap MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Mailtrap MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Mailtrap MCP with LlamaIndex

CrewAI

CrewAI

Use Mailtrap MCP with CrewAI

Claude Code

Claude Code

Use Mailtrap MCP with Claude Code

Codex

Codex

Use Mailtrap MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Mailtrap 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 Mailtrap 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