Notion authentication
This page documents the authentication and configuration options for the Notion agent connector.
Hosted mode (most cases)
In hosted mode, create the connector through the Airbyte Agent CLI or API, then execute operations using the CLI, Python SDK, or API. If you need a step-by-step guide, see the developer quickstart.
OAuth
Use the CLI for hosted OAuth connector creation when possible. It opens the hosted setup flow and avoids passing connector secrets through the command line:
airbyte-agent login
airbyte-agent connectors create --json '{
"workspace": "<your_workspace_name>",
"name": "notion"
}'
For API-first use cases, create a connector with OAuth credentials directly.
credentials fields you need:
| Field Name | Type | Required | Description |
|---|---|---|---|
client_id | str | Yes | Your Notion OAuth integration's client ID |
client_secret | str | Yes | Your Notion OAuth integration's client secret |
access_token | str | Yes | OAuth access token obtained through the Notion authorization flow |
Example request:
curl -X POST "https://api.airbyte.ai/api/v1/integrations/connectors" \
-H "Authorization: Bearer <YOUR_BEARER_TOKEN>" \
-H "Content-Type: application/json" \
-d '{
"workspace_name": "<WORKSPACE_NAME>",
"connector_type": "Notion",
"name": "My Notion Connector",
"credentials": {
"client_id": "<Your Notion OAuth integration's client ID>",
"client_secret": "<Your Notion OAuth integration's client secret>",
"access_token": "<OAuth access token obtained through the Notion authorization flow>"
}
}'
Token
Create a connector with Token credentials.
credentials fields you need:
| Field Name | Type | Required | Description |
|---|---|---|---|
token | str | Yes | Notion internal integration token (starts with ntn_ or secret_) |
Example request:
curl -X POST "https://api.airbyte.ai/api/v1/integrations/connectors" \
-H "Authorization: Bearer <YOUR_BEARER_TOKEN>" \
-H "Content-Type: application/json" \
-d '{
"workspace_name": "<WORKSPACE_NAME>",
"connector_type": "Notion",
"name": "My Notion Connector",
"credentials": {
"token": "<Notion internal integration token (starts with ntn_ or secret_)>"
}
}'
Execution
After creating the connector, execute operations using the CLI, Python SDK, or API.
If your Airbyte client can access multiple organizations, set the default organization with airbyte-agent organizations use, include organization_id in AirbyteAuthConfig, or include X-Organization-Id in raw API calls.
CLI
Authenticate with Airbyte:
airbyte-agent login
Create the connector. The CLI opens the hosted setup flow:
airbyte-agent connectors create --json '{
"workspace": "<your_workspace_name>",
"name": "notion"
}'
Describe the connector to see its supported entities and actions:
airbyte-agent connectors describe --json '{
"workspace": "<your_workspace_name>",
"name": "notion"
}'
Execute an action:
airbyte-agent connectors execute --json '{
"workspace": "<your_workspace_name>",
"name": "notion",
"entity": "<entity>",
"action": "<action>",
"params": {}
}'
Python SDK
The connect() factory returns a fully typed NotionConnector 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.notion import NotionConnector
connector = connect("notion", workspace_name="<your_workspace_name>")
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@NotionConnector.tool_utils
async def notion_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.notion import NotionConnector
connector = connect("notion", workspace_name="<your_workspace_name>")
@tool
@NotionConnector.tool_utils
async def notion_execute(entity: str, action: str, params: dict | None = None):
"""Execute Notion 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.notion import NotionConnector
connector = connect("notion", 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)
@NotionConnector.tool_utils(framework="openai_agents")
async def notion_execute(entity: str, action: str, params: dict | None = None):
"""Execute Notion 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="Notion Assistant", tools=[notion_execute])
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.notion import NotionConnector
connector = connect("notion", workspace_name="<your_workspace_name>")
mcp = FastMCP("Notion Agent")
@mcp.tool
@NotionConnector.tool_utils
async def notion_execute(entity: str, action: str, params: dict | None = None):
"""Execute Notion 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
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.notion import NotionConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = NotionConnector(
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
@NotionConnector.tool_utils
async def notion_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.notion import NotionConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = NotionConnector(
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
@NotionConnector.tool_utils
async def notion_execute(entity: str, action: str, params: dict | None = None):
"""Execute Notion 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.notion import NotionConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = NotionConnector(
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)
@NotionConnector.tool_utils(framework="openai_agents")
async def notion_execute(entity: str, action: str, params: dict | None = None):
"""Execute Notion 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="Notion Assistant", tools=[notion_execute])
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.notion import NotionConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = NotionConnector(
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("Notion Agent")
@mcp.tool
@NotionConnector.tool_utils
async def notion_execute(entity: str, action: str, params: dict | None = None):
"""Execute Notion connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
API
curl -X POST 'https://api.airbyte.ai/api/v1/integrations/connectors/<connector_id>/execute' \
-H 'Authorization: Bearer <YOUR_BEARER_TOKEN>' \
-H 'X-Organization-Id: <YOUR_ORGANIZATION_ID>' \
-H 'Content-Type: application/json' \
-d '{"entity": "<entity>", "action": "<action>", "params": {}}'
Open source mode
In open source mode, provide API credentials directly to the connector.
OAuth
credentials fields you need:
| Field Name | Type | Required | Description |
|---|---|---|---|
client_id | str | Yes | Your Notion OAuth integration's client ID |
client_secret | str | Yes | Your Notion OAuth integration's client secret |
access_token | str | Yes | OAuth access token obtained through the Notion authorization flow |
Example request:
from airbyte_agent_sdk.connectors.notion import NotionConnector
from airbyte_agent_sdk.connectors.notion.models import NotionOauth20AuthConfig
connector = NotionConnector(
auth_config=NotionOauth20AuthConfig(
client_id="<Your Notion OAuth integration's client ID>",
client_secret="<Your Notion OAuth integration's client secret>",
access_token="<OAuth access token obtained through the Notion authorization flow>"
)
)
Token
credentials fields you need:
| Field Name | Type | Required | Description |
|---|---|---|---|
token | str | Yes | Notion internal integration token (starts with ntn_ or secret_) |
Example request:
from airbyte_agent_sdk.connectors.notion import NotionConnector
from airbyte_agent_sdk.connectors.notion.models import NotionAccessTokenAuthConfig
connector = NotionConnector(
auth_config=NotionAccessTokenAuthConfig(
token="<Notion internal integration token (starts with ntn_ or secret_)>"
)
)