How to integrate Adtraction MCP with Autogen

This guide walks you through connecting Adtraction to AutoGen using the Composio tool router. By the end, you'll have a working Adtraction agent that can list this month's adtraction commissions, create tracking link for campaign, summarize transactions by partner program through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Adtraction account through Composio's Adtraction MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Adtraction logoAdtraction
Api Key

Adtraction is an affiliate marketing platform for partner programs, tracking links, transactions, commissions, statistics, and payments. It helps advertisers and publishers manage performance marketing with clear reporting and payout workflows.

22 Tools

Introduction

This guide walks you through connecting Adtraction to AutoGen using the Composio tool router. By the end, you'll have a working Adtraction agent that can list this month's adtraction commissions, create tracking link for campaign, summarize transactions by partner program through natural language commands.

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

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

Also integrate Adtraction with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The Adtraction MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Adtraction account. It provides structured and secure access to your partner programs, tracking links, performance data, transactions, commissions, and payments, so your agent can discover programs, create tracking links, analyze results, review earnings, and monitor payments on your behalf.

  • Program and offer discovery: Have your agent find partner programs, browse new programs and categories, review applications, and list available coupons, vouchers, and offers.
  • Tracking link and product workflows: Direct your agent to create affiliate tracking links, search products, and find product feeds for approved channels and advertiser programs.
  • Performance and commission reporting: Let the agent retrieve clicks and performance statistics, summarize commissions, and compare results across channels, programs, days, or campaigns.
  • Transaction and payment review: Instruct your agent to list recent or historical transactions, check account balances, review payments and their included transactions, or download payment specifications.
  • Tracking health monitoring: Have your agent check recent tracking errors and filter them by channel or program so you can investigate attribution issues.

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

Supported Tools

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

Create Tracking Link

Generate an externally usable Adtraction affiliate tracking URL for an approved channel and advertiser program.

Download Payment PDF

Download a partner payment specification as a PDF file.

Get Partner Balance

Retrieve pending, confirmed, invoiced, payable, and total Adtraction partner balances in one currency.

Get Commission Summary

Summarize Adtraction partner commission by commission type, payment status, or transaction status.

Get Partner Statistics

Retrieve aggregate Adtraction partner performance overall or grouped by channel, day, selected EPI dimensions, or program.

List Program Applications

List the connected partner's program applications, optionally filtered by program or channel.

List Partner Channels

List approved partner channels or retrieve a specific channel by ID.

List Clicks

List Adtraction click events in a date range with attribution, program, channel, market, and currency filters.

List Program Commission Types

List commission types for an Adtraction program, optionally using a channel for segment-specific rates.

List Currencies

List currencies available to the connected Adtraction partner account.

List Latest Transactions

Return a requested number of the connected partner's latest Adtraction transactions.

List Markets

List Adtraction markets and their numeric IDs and ISO country codes for use in program discovery, category, and reporting tools.

List New Programs

List recently added partner programs in an Adtraction market.

List Offers

List coupons, vouchers, and offers available to the connected Adtraction partner, optionally filtered by market, program, or channel.

List Payments

List partner payments, optionally filtered by currency and payment ID.

List Payment Transactions

List the transactions included in a specific partner payment.

List Product Feeds

List product feeds available for an advertiser program and approved partner channel.

List Program Categories

List program categories and program counts for an Adtraction market.

List Tracking Errors

List tracking errors recorded in the connected Adtraction partner account during the last seven days, optionally filtered by channel or program.

List Transactions

List Adtraction partner transactions in a date range with status, attribution, payment, market, currency, program, and channel filters.

Search Products

Search the Adtraction partner product database using text, program, market, currency, stock, price, and sort filters.

Search Programs

Find Adtraction partner programs in a market, optionally filtered by program, channel, approval status, and lifecycle status.

FRAMEWORKS

How to build Adtraction MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Adtraction MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Adtraction MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Adtraction MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Adtraction MCP with Claude Cowork

Codex logo

Codex

Use Adtraction MCP with Codex

OpenClaw logo

OpenClaw

Use Adtraction MCP with OpenClaw

Hermes logo

Hermes

Use Adtraction MCP with Hermes

CLI logo

CLI

Use Adtraction MCP with CLI

Google ADK logo

Google ADK

Use Adtraction MCP with Google ADK

LangChain logo

LangChain

Use Adtraction MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Adtraction MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Adtraction MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Adtraction MCP with LlamaIndex

CrewAI logo

CrewAI

Use Adtraction MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Adtraction 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 Adtraction data and credentials are handled as safely as possible.

Start with Adtraction.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies