How to integrate Cloudcart MCP with CrewAI

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

Introduction

This guide walks you through connecting Cloudcart to CrewAI using the Composio tool router. By the end, you'll have a working Cloudcart agent that can add three t-shirts to a customer’s cart, create a new product called summer mug, register a new customer with email and name, create a variant for the classic hoodie product through natural language commands.

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

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

  • Product and inventory management: Add new products, create variants, and update your store catalog efficiently through your agent.
  • Customer onboarding and management: Register new customers or update existing profiles, enabling seamless customer experiences directly from your agent.
  • Order processing and cart handling: Let your agent create new orders, add items to carts, or clear carts to streamline the purchase flow.
  • Category and vendor organization: Create new product categories or onboard vendors, keeping your store organized and expanding easily.
  • Variant configuration and customization: Add or update product variants and their parameters, allowing your agent to manage different product options and custom attributes.

Supported Tools & Triggers

Tools
Add to CartTool to add an item to the cart.
Clear CartTool to remove all items from the specified cart.
Create CategoryTool to create a new category.
Create CustomerTool to create a new customer in cloudcart.
Create OrderTool to create a new order.
Create ProductTool to create a new product.
Create VariantTool to create a new product variant for a given product.
Create Variant OptionTool to create a new variant option for a specific product variant.
Create Variant ParameterTool to create a new variant parameter for a product variant.
Create VendorTool to create a new vendor via cloudcart api.
Delete CategoryTool to delete a category by its id.
Delete CustomerTool to delete a customer.
Delete OrderTool to delete an order.
Delete ProductTool to delete a product by its id.
Delete VendorTool to delete a vendor by its id.
Get CartTool to retrieve the current shopping cart.
Get CategoriesTool to retrieve a list of all categories.
Get CustomersTool to retrieve a list of all customers.
Get OrdersTool to retrieve a list of all orders.
Get Payment MethodsTool to retrieve all available payment methods.
Get ProductsTool to retrieve a list of products with optional filters.
Get Product With RelationsTool to retrieve a product with related entities.
Get Property Options RelationshipTool to retrieve property options relationship for a product.
Get Shipping MethodsTool to retrieve all available shipping methods.
Get VendorTool to retrieve details of a specific vendor.
List Order PaymentTool to retrieve a list of order payments.
List VendorsTool to retrieve a list of all vendors.
Remove from CartTool to remove an item from the cart.
Update Cart ItemTool to update the quantity of an item in the cart.
Update CategoryTool to update an existing category.
Update CustomerTool to update an existing customer.
Update OrderTool to update an existing order.
Update ProductTool to update an existing product's details.
Update VendorTool to update an existing vendor.

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 Cloudcart 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 Cloudcart 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 Cloudcart MCP URL

Create a Composio Tool Router session for Cloudcart

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["cloudcart"],
)
url = session.mcp.url
What's happening:
  • You create a Cloudcart only session through Composio
  • Composio returns an MCP HTTP URL that exposes Cloudcart 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="Cloudcart Assistant",
    goal="Help users interact with Cloudcart through natural language commands",
    backstory=(
        "You are an expert assistant with access to Cloudcart tools. "
        "You can perform various Cloudcart 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 Cloudcart 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 Cloudcart 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 Cloudcart 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_cloudcart_agent.py

Complete Code

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

python
# file: crewai_cloudcart_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 Cloudcart session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["cloudcart"],
    )
    url = session.mcp.url

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

    # Create Cloudcart assistant agent
    toolkit_agent = Agent(
        role="Cloudcart Assistant",
        goal="Help users interact with Cloudcart through natural language commands",
        backstory=(
            "You are an expert assistant with access to Cloudcart tools. "
            "You can perform various Cloudcart 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 Cloudcart 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 Cloudcart 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 Cloudcart through Composio's Tool Router. The agent can perform Cloudcart 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 Cloudcart MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Cloudcart MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Cloudcart MCP with Claude Agent SDK

Google ADK

Google ADK

Use Cloudcart MCP with Google ADK

LangChain

LangChain

Use Cloudcart MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Cloudcart MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Cloudcart MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Cloudcart MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Cloudcart 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 Cloudcart 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