How to integrate Mx technologies MCP with Autogen

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

Introduction

This guide walks you through connecting Mx technologies to AutoGen using the Composio tool router. By the end, you'll have a working Mx technologies agent that can create a manual account for a user, list account numbers for a specific member, fetch rewards for a connected member, get a configurable widget url for a user through natural language commands.

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

The Mx technologies 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 technologies account. It provides structured and secure access to financial data aggregation and account management features, so your agent can perform actions like creating accounts, managing members, fetching financial rewards, and handling account ownership on your behalf.

  • Automated account creation and management: Let your agent create new manual accounts, partner accounts, and user SSO accounts for seamless onboarding and testing.
  • Member aggregation and connection: Instruct your agent to create members and initiate aggregation of financial products across institutions, streamlining financial data collection.
  • Rewards and incentives tracking: Have your agent fetch and aggregate member rewards data after account connections, so you never miss out on incentives.
  • Secure access to account details: Direct your agent to list account owners, retrieve account numbers by member, and access configurable widget URLs for enhanced user interactions.
  • Credential and API management: Use your agent to retrieve API credentials for audience services, streamlining authentication flows and integrations.

Supported Tools & Triggers

Tools
Cancel Partner AccountTool to cancel (disable) a client account under a partner account.
Create accountTool to create a manual account for a given user.
Retrieve Audience API CredentialsTool to retrieve audience api credentials.
Create memberTool to create a member and start aggregating specified financial products.
Create Partner AccountTool to create a new client account under a partner account.
Create Partner Account User SSOTool to create a new partner account user with single sign-on enabled.
Fetch rewardsTool to initiate rewards aggregation for a specific member.
Get configurable widget URLTool to retrieve a configurable widget url for a user.
List Account Numbers by MemberTool to list account numbers for a specific member.
List account ownersTool to list account owners associated with a member's account.
List account owners by memberTool to list account owners for a specific member.
List accountsTool to list all accounts for a user.
List budgetsTool to list budgets for a specific user.
List categoriesTool to list all categories for a user.
List challengesTool to list mfa challenges for a member.
List Connect Widget URLsTool to list connect widget urls for a user.
List favorite institutionsTool to list partner favorite institutions, sorted by popularity.
List goalsTool to list goals for a specific user.
List institution credentialsTool to list credential fields required by a given institution.
List institutionsTool to list financial institutions supported by mx.
List member accountsTool to list accounts for a specific member.
List membersTool to list members associated with a specific user.
List rewardsTool to list rewards associated with a specific user and member.
List statements by memberTool to list statements for a member.
List taggingsTool to list all taggings for a specific user.
List tagsTool to list all tags for a user.
List transactionsTool to list transactions for a user.
List transactions by memberTool to list transactions for a member.
List usersTool to list users.
Read accountTool to retrieve details for a specific account.
Read account balanceTool to retrieve the available balance for a specific account.
Read categoryTool to retrieve a default category by guid.
Read FDX accountTool to return details for the specified fdx account.

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

How to build Mx technologies MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Mx technologies MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Mx technologies MCP with Claude Agent SDK

Google ADK

Google ADK

Use Mx technologies MCP with Google ADK

LangChain

LangChain

Use Mx technologies MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Mx technologies MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Mx technologies MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Mx technologies MCP with LlamaIndex

CrewAI

CrewAI

Use Mx technologies MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Mx technologies 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 technologies 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