How to integrate Mx toolbox MCP with Autogen

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

Introduction

This guide walks you through connecting Mx toolbox to AutoGen using the Composio tool router. By the end, you'll have a working Mx toolbox agent that can check if my domain is blacklisted, get current mx records for example.com, run a ping test on our mail server, fetch dkim record for marketing domain through natural language commands.

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

The Mx toolbox MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mx toolbox account. It provides structured and secure access to network diagnostic and email health tools, so your agent can perform actions like DNS lookups, blacklist checks, email authentication analysis, and connectivity testing on your behalf.

  • Automated DNS and MX record lookups: Instantly retrieve DNS, MX, DKIM, DMARC, and MTA-STS records for any domain to verify configuration and troubleshoot email delivery issues.
  • Blacklist monitoring and alerting: Check if your domain or IP is listed on common blacklists, helping you stay ahead of email deliverability problems and security risks.
  • Email authentication validation: Validate BIMI, DKIM, and DMARC records to ensure your domain's outgoing emails are properly authenticated and protected against spoofing.
  • Network and SMTP diagnostics: Run ping, HTTP, and SMTP lookups to diagnose connectivity issues, measure latency, or assess mail server responsiveness—no manual testing required.
  • Brand and security checks: Use BIMI and MTA-STS lookups to confirm your brand indicators and mail transport security policies are correctly published and compliant.

Supported Tools & Triggers

Tools
Lookup BIMI RecordTool to retrieve bimi (brand indicators for message identification) record for a domain.
Lookup BlacklistTool to perform a blacklist check on a domain or ip.
Lookup DKIM RecordTool to retrieve dkim records for a domain.
Lookup DMARC RecordTool to retrieve dmarc records for a domain.
Lookup DNS RecordsTool to retrieve dns records for a given domain.
HTTP LookupTool to perform an http test on a domain.
Lookup MTA-STS RecordTool to lookup mta-sts record for a domain.
Lookup MX RecordsTool to retrieve mx records for a given domain.
Ping LookupTool to perform a ping test on a specified domain or ip address.
SMTP LookupTool to perform an smtp test on the specified domain.
Lookup SPF RecordTool to retrieve spf records for a specified domain.
Monitor StatusTool to retrieve all monitor statuses.
Check UsageTool to retrieve api usage statistics.

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

How to build Mx toolbox MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Mx toolbox MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Mx toolbox MCP with Claude Agent SDK

Google ADK

Google ADK

Use Mx toolbox MCP with Google ADK

LangChain

LangChain

Use Mx toolbox MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Mx toolbox MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Mx toolbox MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Mx toolbox MCP with LlamaIndex

CrewAI

CrewAI

Use Mx toolbox MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Mx toolbox MCP?

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

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

Yes, absolutely. You can configure which Mx toolbox 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 Mx toolbox 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