How to integrate Unisender MCP with Autogen

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

Introduction

This guide walks you through connecting Unisender to AutoGen using the Composio tool router. By the end, you'll have a working Unisender agent that can send an sms campaign to new signups, create a new email list segment, check status of yesterday's email campaign through natural language commands.

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

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

Supported Tools & Triggers

Tools
Check Email StatusTool to check the delivery status of emails sent via sendEmail method.
Create Email TemplateTool to create a new email template for mass campaigns in UniSender.
Create FieldTool to create a new custom field for contact data in UniSender.
Create ListTool to create a new contact list for organizing thematic email campaigns in UniSender.
Create Subscriber NoteTool to create a note for a subscriber contact in UniSender.
Delete FieldTool to remove a custom field from the Unisender system.
Delete ListTool to permanently delete a contact list from your UniSender account.
Delete Subscriber NoteTool to delete a subscriber note from UniSender by its ID.
Delete TagTool to delete a tag by its ID and remove it from all associated contacts.
Delete TemplateTool to remove a template from the UniSender account.
Exclude Contact from ListsTool to remove contacts from specified lists or all lists in UniSender.
Export ContactsTool to export contact data from UniSender lists for synchronization.
Get CampaignsTool to retrieve list of campaigns from Unisender within a specified date range.
Get Campaign StatusTool to check the current status of a campaign in UniSender.
Get ContactTool to get information about a single contact from UniSender.
Get Contact Field ValuesTool to retrieve custom field values for a specific contact identified by email address.
Get FieldsTool to retrieve all custom user-defined fields for contact personalization and data management.
Get ListsTool to retrieve all existing mailing lists associated with the account.
Get MessagesTool to retrieve list of all messages with body and attachments.
Get Sender Domain ListTool to retrieve information about sender domains and their DKIM status.
Get TagsTool to retrieve all custom tags/labels for contact segmentation.
Get TemplateTool to retrieve detailed information about a specific email template by its ID.
Get TemplatesTool to retrieve list of all templates with full content including body.
Import Contacts (Bulk)Tool to bulk import contacts to UniSender with maximum 500 contacts per call.
Check if Contact is in ListsTool to check if a contact exists in specified mailing lists based on and/or conditions.
List MessagesTool to list all messages without body and attachments.
List TemplatesTool to list email templates without body content.
Subscribe Contact to ListsTool to add contacts to one or multiple mailing lists with optional tags and field values.
Unsubscribe ContactTool to unsubscribe contacts from mailing lists in UniSender.
Update Email TemplateTool to update an existing email template for mass campaigns.
Update FieldTool to modify parameters of an existing custom field in UniSender.
Update ListTool to update the parameters of an existing contact list in UniSender.
Update Subscriber NoteTool to update the content of an existing subscriber note in UniSender.

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

How to build Unisender MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Unisender MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Unisender MCP with Claude Agent SDK

Google ADK

Google ADK

Use Unisender MCP with Google ADK

LangChain

LangChain

Use Unisender MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Unisender MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Unisender MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Unisender MCP with LlamaIndex

CrewAI

CrewAI

Use Unisender MCP with CrewAI

Claude Code

Claude Code

Use Unisender MCP with Claude Code

Codex

Codex

Use Unisender MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Unisender 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 Unisender 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