Shopify

This connector is optimized for AI agents. For the data replication connector, see Shopify.

The Shopify agent connector is a Python package that equips AI agents to interact with Shopify through strongly typed, well-documented tools. It's ready to use directly in your Python app, in an agent framework, or exposed through an MCP.

Shopify is an e-commerce platform that enables businesses to create online stores, manage products, process orders, and handle customer relationships. This connector provides access to Shopify Admin REST API for reading store data including customers, orders, products, inventory, and more.

Example prompts

The Shopify connector is optimized to handle prompts like these.

List all customers in my Shopify store
Show me details for a recent customer
What products do I have in my store?
List all locations for my store
Show me inventory levels for a recent location
Show me all draft orders
List all custom collections in my store
Show me details for a recent order
Show me product variants for a recent product
Show me orders from the last 30 days
Show me abandoned checkouts from this week
What price rules are currently active?

Unsupported prompts

The Shopify connector isn't currently able to handle prompts like these.

Create a new customer in Shopify
Update product pricing
Delete an order
Process a refund
Send shipping notification to customer
Create a new discount code

Entities and actions

This connector supports the following entities and actions. For more details, see this connector's full reference documentation.

Entity	Actions
Customers	List, Get, Context Store Search
Orders	List, Get
Products	List, Get
Product Variants	List, Get, Context Store Search
Product Images	List, Get, Context Store Search
Abandoned Checkouts	List, Context Store Search
Locations	List, Get, Context Store Search
Inventory Levels	List, Context Store Search
Inventory Items	List, Get, Context Store Search
Shop	Get, Context Store Search
Price Rules	List, Get, Context Store Search
Discount Codes	List, Get, Context Store Search
Custom Collections	List, Get, Context Store Search
Smart Collections	List, Get, Context Store Search
Collects	List, Get, Context Store Search
Draft Orders	List, Get, Context Store Search
Fulfillments	List, Get, Context Store Search
Order Refunds	List, Get, Context Store Search
Transactions	List, Get
Tender Transactions	List, Context Store Search
Countries	List, Get, Context Store Search
Metafield Shops	List, Get, Context Store Search
Metafield Customers	List, Context Store Search
Metafield Products	List, Context Store Search
Metafield Orders	List, Context Store Search
Metafield Draft Orders	List, Context Store Search
Metafield Locations	List, Context Store Search
Metafield Product Variants	List, Context Store Search
Metafield Smart Collections	List, Context Store Search
Metafield Product Images	List, Context Store Search
Customer Address	List, Get
Fulfillment Orders	List, Get, Context Store Search

Shopify API docs

See the official Shopify API reference.

SDK installation

uv pip install airbyte-agent-sdk

SDK usage

Connectors can run in hosted or open source mode.

Hosted

In hosted mode, API credentials are stored securely in Airbyte Agents. You provide your Airbyte credentials instead. If your Airbyte client can access multiple organizations, also set organization_id.

This example assumes you've already authenticated your connector with Airbyte. See Authentication to learn more about authenticating. If you need a step-by-step guide, see the hosted execution tutorial.

The connect() factory returns a fully typed ShopifyConnector and reads AIRBYTE_CLIENT_ID / AIRBYTE_CLIENT_SECRET from the environment:

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector

connector = connect("shopify", workspace_name="<your_workspace_name>")

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector

connector = connect("shopify", workspace_name="<your_workspace_name>")

@tool
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    # connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector

connector = connect("shopify", workspace_name="<your_workspace_name>")

# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@ShopifyConnector.tool_utils(framework="openai_agents")
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

agent = Agent(name="Shopify Assistant", tools=[shopify_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector

connector = connect("shopify", workspace_name="<your_workspace_name>")

mcp = FastMCP("Shopify Agent")

@mcp.tool
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

Or pass credentials explicitly (equivalent, useful when you're not loading them from the environment):

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ShopifyConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ShopifyConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

@tool
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    # connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ShopifyConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@ShopifyConnector.tool_utils(framework="openai_agents")
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

agent = Agent(name="Shopify Assistant", tools=[shopify_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ShopifyConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

mcp = FastMCP("Shopify Agent")

@mcp.tool
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

Open source

In open source mode, you provide API credentials directly to the connector.

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.connectors.shopify.models import ShopifyAuthConfig

connector = ShopifyConnector(
    auth_config=ShopifyAuthConfig(
        api_key="<Your Shopify Admin API access token>"
    )
)

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.connectors.shopify.models import ShopifyAuthConfig

connector = ShopifyConnector(
    auth_config=ShopifyAuthConfig(
        api_key="<Your Shopify Admin API access token>"
    )
)

@tool
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    # connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.connectors.shopify.models import ShopifyAuthConfig

connector = ShopifyConnector(
    auth_config=ShopifyAuthConfig(
        api_key="<Your Shopify Admin API access token>"
    )
)

# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@ShopifyConnector.tool_utils(framework="openai_agents")
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

agent = Agent(name="Shopify Assistant", tools=[shopify_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.shopify import ShopifyConnector
from airbyte_agent_sdk.connectors.shopify.models import ShopifyAuthConfig

connector = ShopifyConnector(
    auth_config=ShopifyAuthConfig(
        api_key="<Your Shopify Admin API access token>"
    )
)

mcp = FastMCP("Shopify Agent")

@mcp.tool
@ShopifyConnector.tool_utils
async def shopify_execute(entity: str, action: str, params: dict | None = None):
    """Execute Shopify connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

Authentication

For all authentication options, see the connector's authentication documentation.

Version information

Connector version: 0.1.13

Example prompts​

Unsupported prompts​

Entities and actions​

Shopify API docs​

SDK installation​

SDK usage​

Hosted​

Open source​

Authentication​

Version information​