How to integrate Shopify MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Shopify Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Shopify to CrewAI using the Composio tool router. By the end, you'll have a working Shopify agent that can create a new product called 'summer t-shirt', add product id 1234 to 'holiday specials' collection, delete the image with id 5678 from product id 4321, create a new customer with email john@example.com through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Shopify account through Composio's Shopify 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 a Composio API key and configure your Shopify connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Shopify
  • Build a conversational loop where your agent can execute Shopify operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

What is the Shopify MCP server, and what's possible with it?

The Shopify MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Shopify account. It provides structured and secure access to your store, so your agent can perform actions like managing products, processing orders, handling collections, organizing images, and managing customers on your behalf.

  • Product management and automation: Let your agent create new products, update existing listings, or delete products from your Shopify store quickly and accurately.
  • Order creation and fulfillment: Direct your agent to generate new orders, associate them with customers, and streamline your sales process with minimal manual input.
  • Collection organization: Ask your agent to create custom collections, add products to collections, or remove collections to keep your store categories organized and up to date.
  • Product image handling: Have your agent add new images to products, count existing images for inventory tracking, or remove outdated images from your catalog.
  • Customer management: Automate the creation of new customer records, making it easy to onboard shoppers and keep your CRM current without lifting a finger.

Supported Tools & Triggers

Tools
Add product to custom collectionAdds a product to an existing *custom collection*, optionally specifying its `position` if the collection is manually sorted.
Count product imagesRetrieves the total count of images for a shopify product, useful for inventory management or display logic; the provided `product id` must exist in the store.
Create a custom collectionCreates a new custom collection in a shopify store, requiring a unique title for manually curated product groupings (e.
Create CustomerTool to create a new customer in shopify.
Create an orderCreates a new order in shopify, typically requiring line items; if `customer id` is provided, it must correspond to an existing customer.
Create a productCreates a new product in a shopify store; a product title is generally required.
Create Product ImageTool to create a new product image for a given product.
Delete custom collectionPermanently deletes a custom collection from a shopify store using its `collection id`; this action is irreversible and requires a valid, existing `collection id`.
Delete a productDeletes a specific, existing product from a shopify store using its unique product id; this action is irreversible.
Delete product imageDeletes a specific image from a product in shopify, requiring the `product id` of an existing product and the `image id` of an image currently associated with that product.
Get All CustomersRetrieves customer records from a shopify store, with options for filtering, selecting specific fields, and paginating through the results.
Get collection by IDRetrieves a specific shopify collection by its `collection id`, optionally filtering returned data to specified `fields`.
Get collectsRetrieves a list of collects from a shopify store, where a collect links a product to a custom collection.
Get collects countRetrieves the total count of collects (product-to-collection associations) in a shopify store.
Get custom collectionsRetrieves a list of custom collections from a shopify store, optionally filtered by ids, product id, or handle.
Get custom collections countRetrieves the total number of custom collections in a shopify store.
Get CustomerRetrieves detailed information for a specific customer from a shopify store, provided their valid and existing `customer id`.
Get customer ordersRetrieves all orders for a specific, existing customer in shopify using their unique customer id.
Get order listRetrieves a list of orders from shopify using default api settings and filters.
Get order by idRetrieves a specific shopify order by its unique id, which must correspond to an existing order.
Get productRetrieves details for an existing shopify product using its unique product id.
Get product imageRetrieves detailed information for a specific product image, identified by its id and its associated product id, from a shopify store.
Get Product ImagesRetrieves all images for a shopify product, specified by its `product id` which must correspond to an existing product.
Get productsRetrieves a list of products from a shopify store.
Get products countRetrieves the total, unfiltered count of all products in a shopify store.
Get products in collectionRetrieves all products within a specified shopify collection, requiring a valid `collection id`.
Get Shop DetailsRetrieves comprehensive administrative information about the authenticated shopify store, as defined by the shopify api.
Update OrderUpdates the phone number for an existing shopify order, identified by its id; pass `phone=none` to remove the current phone number.

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

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Shopify connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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 crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Shopify via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Shopify MCP URL

Create a Composio Tool Router session for Shopify

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["shopify"],
)
url = session.mcp.url
What's happening:
  • You create a Shopify only session through Composio
  • Composio returns an MCP HTTP URL that exposes Shopify tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Shopify Assistant",
    goal="Help users interact with Shopify through natural language commands",
    backstory=(
        "You are an expert assistant with access to Shopify tools. "
        "You can perform various Shopify operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Shopify MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Shopify operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Shopify related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_shopify_agent.py

Complete Code

Here's the complete code to get you started with Shopify and CrewAI:

python
# file: crewai_shopify_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Shopify session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["shopify"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Shopify assistant agent
    toolkit_agent = Agent(
        role="Shopify Assistant",
        goal="Help users interact with Shopify through natural language commands",
        backstory=(
            "You are an expert assistant with access to Shopify tools. "
            "You can perform various Shopify operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Shopify operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Shopify related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Shopify through Composio's Tool Router. The agent can perform Shopify operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Shopify MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Shopify MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Shopify MCP with Claude Agent SDK

Google ADK

Google ADK

Use Shopify MCP with Google ADK

LangChain

LangChain

Use Shopify MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Shopify MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Shopify MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Shopify MCP with LlamaIndex

FAQ

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

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

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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 Shopify tools.

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

Yes, absolutely. You can configure which Shopify 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 Shopify 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