How to integrate Order Desk MCP with Autogen

This guide walks you through connecting Order Desk to AutoGen using the Composio tool router. By the end, you'll have a working Order Desk agent that can look up orders, add order items, create shipments, add order notes, and manage your inventory through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Order Desk account through Composio's Order Desk 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
Order Desk logoOrder Desk
Api Key

Order Desk is an order management platform for ecommerce orders, shipments, inventory, and store data. It helps teams centralize fulfillment workflows across multiple ecommerce integrations.

20 Tools

Introduction

This guide walks you through connecting Order Desk to AutoGen using the Composio tool router. By the end, you'll have a working Order Desk agent that can look up orders, add order items, create shipments, add order notes, and manage your inventory through natural language commands.

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

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

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

The Order Desk MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Order Desk account. It provides structured and secure access to your orders, shipments, inventory, and store data, so your agent can find orders, manage line items, track shipments, update inventory, and organize orders on your behalf.

  • Order search and review: Have your agent find matching orders and retrieve their addresses, items, shipments, notes, discounts, and other details.
  • Order item management: Let the agent list, add, update, or remove line items from an existing order.
  • Shipment management: Direct your agent to create shipment records, review an order's shipments, update shipment details, or remove incorrect records.
  • Inventory management: Instruct your agent to search, create, review, update, or delete inventory items using details such as SKU, name, location, or update time.
  • Order organization and store context: Have your agent add permanent history notes, move orders into the right folder, and review store settings such as locale, timezone, and folder names.

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

Supported Tools

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

Add Order History Note

Append a timestamped note permanently to an existing order's history.

Add Order Item

Add one line item to an existing order.

Add Order Items

Add two to 10 line items sequentially to the same order and return a result for every processed item.

Create Inventory Item

Create one inventory item with a unique SKU and return its positive Order Desk ID and complete created representation.

Create Inventory Items

Create two to 10 inventory items sequentially and return each created ID or error.

Create Shipments

Create one or more shipment records across orders in one request and report the success or error returned for every shipment.

Delete Inventory Item

Permanently delete one inventory item by its positive Order Desk ID.

Delete Order Item

Permanently remove one line item from an order.

Delete Shipment

Permanently remove one shipment record from an order.

Get Inventory Item

Get one inventory item by its positive Order Desk ID.

Get Order

Get one order and its addresses, line items, shipments, metadata, notes, and discounts by Order Desk internal ID.

Get Store Metadata

Return safe store identity, locale, timezone, page-size settings, and folder IDs and names without exposing credentials or email configuration.

List Inventory Items

Search inventory items in the connected store by ID, SKU, name, metadata, manufacturer SKU, location, or update time.

List Order Items

Return all line items for one order.

List Orders

Find orders in the connected store using at least one narrowing filter and return one bounded page.

List Order Shipments

Return all shipments recorded for one order.

Move Orders

Move one or more orders to exactly one destination folder selected by positive ID or exact name, with a result for every order.

Update Inventory Items

Safely update selected fields on one or more inventory items while preserving every omitted field.

Update Order Item

Safely update selected fields on one order line item while preserving every omitted field.

Update Shipment

Safely update selected fields on one shipment while preserving every omitted field.

FRAMEWORKS

How to build Order Desk MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Order Desk MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Order Desk MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Order Desk MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Order Desk MCP with Claude Cowork

Codex logo

Codex

Use Order Desk MCP with Codex

OpenClaw logo

OpenClaw

Use Order Desk MCP with OpenClaw

Hermes logo

Hermes

Use Order Desk MCP with Hermes

CLI logo

CLI

Use Order Desk MCP with CLI

Google ADK logo

Google ADK

Use Order Desk MCP with Google ADK

LangChain logo

LangChain

Use Order Desk MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Order Desk MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Order Desk MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Order Desk MCP with LlamaIndex

CrewAI logo

CrewAI

Use Order Desk MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Order Desk.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Order Desk 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