Woocommerce
The Woocommerce agent connector is a Python package that equips AI agents to interact with Woocommerce 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.
Connector for the WooCommerce REST API (v3). Provides read access to a WooCommerce store's customers, orders, products, coupons, product categories, tags, reviews, attributes, variations, order notes, refunds, payment gateways, shipping methods, shipping zones, tax rates, and tax classes. Requires a WooCommerce store URL and REST API consumer key / consumer secret for authentication.
Example prompts
The Woocommerce connector is optimized to handle prompts like these.
- List all customers in WooCommerce
- Show me all orders
- List all products
- Show me all coupons
- List all product categories
- Show me the product reviews
- List all shipping zones
- Show me the tax rates
- List all payment gateways
- Find orders placed this month
- What are the top-selling products?
- Show me customers who have made purchases
- Find all coupons expiring this year
- What orders are still processing?
Unsupported prompts
The Woocommerce connector isn't currently able to handle prompts like these.
- Create a new product
- Update an order status
- Delete a customer
- Apply a coupon to an order
- Process a refund
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, Context Store Search |
| Products | List, Get, Context Store Search |
| Coupons | List, Get, Context Store Search |
| Product Categories | List, Get, Context Store Search |
| Product Tags | List, Get, Context Store Search |
| Product Reviews | List, Get, Context Store Search |
| Product Attributes | List, Get, Context Store Search |
| Product Variations | List, Get, Context Store Search |
| Order Notes | List, Get, Context Store Search |
| Refunds | List, Get, Context Store Search |
| Payment Gateways | List, Get, Context Store Search |
| Shipping Methods | List, Get, Context Store Search |
| Shipping Zones | List, Get, Context Store Search |
| Tax Rates | List, Get, Context Store Search |
| Tax Classes | List, Context Store Search |
Woocommerce API docs
See the official Woocommerce 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 WoocommerceConnector and reads AIRBYTE_CLIENT_ID / AIRBYTE_CLIENT_SECRET from the environment:
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
connector = connect("woocommerce", workspace_name="<your_workspace_name>")
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
from langchain_core.tools import tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
connector = connect("woocommerce", workspace_name="<your_workspace_name>")
@tool
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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
from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
connector = connect("woocommerce", 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)
@WoocommerceConnector.tool_utils(framework="openai_agents")
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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="Woocommerce Assistant", tools=[woocommerce_execute])
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
connector = connect("woocommerce", workspace_name="<your_workspace_name>")
mcp = FastMCP("Woocommerce Agent")
@mcp.tool
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = WoocommerceConnector(
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
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = WoocommerceConnector(
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
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = WoocommerceConnector(
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)
@WoocommerceConnector.tool_utils(framework="openai_agents")
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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="Woocommerce Assistant", tools=[woocommerce_execute])
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = WoocommerceConnector(
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("Woocommerce Agent")
@mcp.tool
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.connectors.woocommerce.models import WoocommerceAuthConfig
connector = WoocommerceConnector(
auth_config=WoocommerceAuthConfig(
api_key="<WooCommerce REST API consumer key (starts with ck_)>",
api_secret="<WooCommerce REST API consumer secret (starts with cs_)>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.connectors.woocommerce.models import WoocommerceAuthConfig
connector = WoocommerceConnector(
auth_config=WoocommerceAuthConfig(
api_key="<WooCommerce REST API consumer key (starts with ck_)>",
api_secret="<WooCommerce REST API consumer secret (starts with cs_)>"
)
)
@tool
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.connectors.woocommerce.models import WoocommerceAuthConfig
connector = WoocommerceConnector(
auth_config=WoocommerceAuthConfig(
api_key="<WooCommerce REST API consumer key (starts with ck_)>",
api_secret="<WooCommerce REST API consumer secret (starts with cs_)>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@WoocommerceConnector.tool_utils(framework="openai_agents")
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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="Woocommerce Assistant", tools=[woocommerce_execute])
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.woocommerce import WoocommerceConnector
from airbyte_agent_sdk.connectors.woocommerce.models import WoocommerceAuthConfig
connector = WoocommerceConnector(
auth_config=WoocommerceAuthConfig(
api_key="<WooCommerce REST API consumer key (starts with ck_)>",
api_secret="<WooCommerce REST API consumer secret (starts with cs_)>"
)
)
mcp = FastMCP("Woocommerce Agent")
@mcp.tool
@WoocommerceConnector.tool_utils
async def woocommerce_execute(entity: str, action: str, params: dict | None = None):
"""Execute Woocommerce 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: 1.0.5