How to integrate AimTell MCP with Autogen

This guide walks you through connecting AimTell to AutoGen using the Composio tool router. By the end, you'll have a working AimTell agent that can list aimtell websites by subscriber count, create segment for cart abandoners, summarize campaign delivery analytics this week through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a AimTell account through Composio's AimTell MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

AimTell logoAimTell
Api Key

AimTell is a web push notification platform for managing websites, subscribers, campaigns, segments, and delivery analytics. Use it to send targeted browser notifications and measure engagement across your web push campaigns.

15 Tools

Introduction

This guide walks you through connecting AimTell to AutoGen using the Composio tool router. By the end, you'll have a working AimTell agent that can list aimtell websites by subscriber count, create segment for cart abandoners, summarize campaign delivery analytics this week through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a AimTell account through Composio's AimTell MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate AimTell with

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 AimTell
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call AimTell tools
  • Run a live chat loop where you ask the agent to perform AimTell 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 AimTell MCP server, and what's possible with it?

The AimTell MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your AimTell account. It provides structured and secure access to your websites, subscribers, campaigns, segments, notifications, and delivery analytics, so your agent can manage audiences, prepare campaigns, send push notifications, review results, and track delivery activity on your behalf.

  • Website and subscriber insights: Have your agent list your AimTell websites, browse subscribers, review their attributes and notification history, and filter audiences by segment.
  • Audience segment management: Let the agent create, update, list, or delete audience segments used to organize subscribers and target campaigns.
  • Campaign draft management: Direct your agent to create and revise manual campaign drafts, review campaigns across supported campaign types, or delete drafts you no longer need.
  • Targeted push notifications: Instruct your agent to send a one-off push notification to selected subscribers, a segment, an alias, or your website's full reachable audience.
  • Delivery and campaign reporting: Have your agent track daily metrics, review campaign sends, deliveries, bounces, clicks, conversions, and revenue where available, or inspect recent notification logs.

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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A AimTell account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

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 AimTell via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

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 AimTell connections to use
5

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 AimTell session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["aimtell"]
    )
    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 AimTell tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 AimTell assistant agent with MCP tools
    agent = AssistantAgent(
        name="aimtell_assistant",
        description="An AI assistant that helps with AimTell 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 AimTell tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any AimTell 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 AimTell 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 AimTell 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 AimTell session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["aimtell"]
    )
    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 AimTell assistant agent with MCP tools
        agent = AssistantAgent(
            name="aimtell_assistant",
            description="An AI assistant that helps with AimTell 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 AimTell 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 AimTell 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 AimTell, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every AimTell action and event your agent gets out of the box.

Create Manual Campaign

Create a manual push campaign as a draft only; this tool never schedules or sends it.

Create Segment

Create a named audience segment for a website from an AimTell segment definition.

Delete Manual Campaign

Permanently delete one manual campaign by ID.

Delete Segment

Permanently delete one audience segment by ID.

Get Analytics Over Time

Return a daily AimTell metric over a date range for all websites or one website.

Get Campaign Results

Return daily send, delivery, bounce, click, conversion, and available revenue results for a manual, event-triggered, RSS, or welcome campaign.

List Campaigns

Return one page of manual, event-triggered, RSS, or API push campaigns for an AimTell website.

List Notification Logs

Return one page from AimTell's sampled notification log for the last seven days, optionally filtered to one subscriber.

List Segments

Return all audience segments for an AimTell website, including the IDs and definitions used for subscriber filtering and campaign targeting.

List Subscribers

Return one page of subscribers for an AimTell website, optionally filtered by segment or subscriber ID and optionally including attributes or notification history.

List Websites

Return one page of websites available to the connected AimTell account, including site IDs needed by other tools.

Send Push Notification

Immediately send a one-off push notification to exactly one explicitly selected audience: subscriber IDs, one segment, one alias, or the website's full reachable audience.

Set Subscriber Attributes

Set custom attributes on one subscriber identified by subscriber UID, user alias, or email alias; supplied aliases may also be associated with the subscriber.

Update Manual Campaign

Update the content or targeting of an unscheduled, unsent, non-A/B manual campaign draft without scheduling or sending it.

Update Segment

Change the name or audience definition of an existing AimTell segment.

FAQ

Frequently asked questions

With a standalone AimTell MCP server, the agents and LLMs can only access a fixed set of AimTell tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from AimTell and many other apps based on the task at hand, all through a single MCP endpoint.

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 AimTell tools.

Yes, absolutely. You can configure which AimTell 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.

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 AimTell data and credentials are handled as safely as possible.

Start with AimTell.It takes 30 seconds.

Managed auth, hosted MCP servers, and every AimTell tool your agent needs.Free to start.

Start building