Amazon-Seller-Partner
The Amazon-Seller-Partner agent connector is a Python package that equips AI agents to interact with Amazon-Seller-Partner 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 Amazon Selling Partner API (SP-API). Provides access to seller orders and order items, financial events and event groups, catalog item search and details, and report metadata. Supports OAuth 2.0 authentication via Login with Amazon (LWA) with automatic token refresh.
Example prompts
The Amazon-Seller-Partner connector is optimized to handle prompts like these.
- List all orders from the last 7 days
- Show me shipped orders from January 2024
- Show me order items for order 111-2222222-3333333
- List financial event groups from the last 90 days
- Show refund events from last month
- Search the catalog for wireless headphones
- Look up product details for ASIN B08N5WRWNW
- List completed reports from this week
- What are my top-selling products by order volume this month?
- Show orders with status Shipped from the last 30 days
- Find all refund financial events from last quarter
- Which orders have the highest total value this week?
- How many orders were canceled in the last 60 days?
- What service fees were charged last month?
Unsupported prompts
The Amazon-Seller-Partner connector isn't currently able to handle prompts like these.
- Create a new order
- Cancel an order
- Submit a new report request
- Update product listings
- Change the marketplace region
Entities and actions
This connector supports the following entities and actions. For more details, see this connector's full reference documentation.
| Entity | Actions |
|---|---|
| Orders | List, Get, Context Store Search |
| Order Items | List, Context Store Search |
| List Financial Event Groups | List, Context Store Search |
| List Financial Events | List, Context Store Search |
| Catalog Items | List, Get |
| Reports | List, Get |
Amazon-Seller-Partner API docs
See the official Amazon-Seller-Partner 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 AmazonSellerPartnerConnector 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.amazon_seller_partner import AmazonSellerPartnerConnector
connector = connect("amazon-seller-partner", workspace_name="<your_workspace_name>")
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_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.amazon_seller_partner import AmazonSellerPartnerConnector
connector = connect("amazon-seller-partner", workspace_name="<your_workspace_name>")
@tool
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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.amazon_seller_partner import AmazonSellerPartnerConnector
connector = connect("amazon-seller-partner", 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)
@AmazonSellerPartnerConnector.tool_utils(framework="openai_agents")
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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="Amazon-Seller-Partner Assistant", tools=[amazon_seller_partner_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.amazon_seller_partner import AmazonSellerPartnerConnector
connector = connect("amazon-seller-partner", workspace_name="<your_workspace_name>")
mcp = FastMCP("Amazon-Seller-Partner Agent")
@mcp.tool
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmazonSellerPartnerConnector(
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
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_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.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmazonSellerPartnerConnector(
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
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmazonSellerPartnerConnector(
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)
@AmazonSellerPartnerConnector.tool_utils(framework="openai_agents")
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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="Amazon-Seller-Partner Assistant", tools=[amazon_seller_partner_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmazonSellerPartnerConnector(
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("Amazon-Seller-Partner Agent")
@mcp.tool
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.connectors.amazon_seller_partner.models import AmazonSellerPartnerAuthConfig
connector = AmazonSellerPartnerConnector(
auth_config=AmazonSellerPartnerAuthConfig(
lwa_app_id="<Your Login with Amazon Client ID.>",
lwa_client_secret="<Your Login with Amazon Client Secret.>",
refresh_token="<The Refresh Token obtained via the OAuth authorization flow.>",
access_token="<Access token (optional if refresh_token is provided).>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_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.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.connectors.amazon_seller_partner.models import AmazonSellerPartnerAuthConfig
connector = AmazonSellerPartnerConnector(
auth_config=AmazonSellerPartnerAuthConfig(
lwa_app_id="<Your Login with Amazon Client ID.>",
lwa_client_secret="<Your Login with Amazon Client Secret.>",
refresh_token="<The Refresh Token obtained via the OAuth authorization flow.>",
access_token="<Access token (optional if refresh_token is provided).>"
)
)
@tool
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.connectors.amazon_seller_partner.models import AmazonSellerPartnerAuthConfig
connector = AmazonSellerPartnerConnector(
auth_config=AmazonSellerPartnerAuthConfig(
lwa_app_id="<Your Login with Amazon Client ID.>",
lwa_client_secret="<Your Login with Amazon Client Secret.>",
refresh_token="<The Refresh Token obtained via the OAuth authorization flow.>",
access_token="<Access token (optional if refresh_token is provided).>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@AmazonSellerPartnerConnector.tool_utils(framework="openai_agents")
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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="Amazon-Seller-Partner Assistant", tools=[amazon_seller_partner_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.amazon_seller_partner import AmazonSellerPartnerConnector
from airbyte_agent_sdk.connectors.amazon_seller_partner.models import AmazonSellerPartnerAuthConfig
connector = AmazonSellerPartnerConnector(
auth_config=AmazonSellerPartnerAuthConfig(
lwa_app_id="<Your Login with Amazon Client ID.>",
lwa_client_secret="<Your Login with Amazon Client Secret.>",
refresh_token="<The Refresh Token obtained via the OAuth authorization flow.>",
access_token="<Access token (optional if refresh_token is provided).>"
)
)
mcp = FastMCP("Amazon-Seller-Partner Agent")
@mcp.tool
@AmazonSellerPartnerConnector.tool_utils
async def amazon_seller_partner_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amazon-Seller-Partner 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