Skip to main content

Airbyte Notion Connector for AI platforms

Project description

Notion

The Notion agent connector is a Python package that equips AI agents to interact with Notion 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.

Notion is an all-in-one workspace for notes, docs, wikis, projects, and collaboration. This connector provides read access to Notion workspaces including users, pages, data sources, blocks, and comments through the Notion REST API (version 2025-09-03). It enables querying workspace structure, page content, data source schemas, and collaboration data for productivity analysis and content management insights.

Example questions

The Notion connector is optimized to handle prompts like these.

  • List all users in my Notion workspace
  • Show me all pages in my Notion workspace
  • What data sources exist in my Notion workspace?
  • Get the details of a specific page by ID
  • List child blocks of a specific page
  • Show me comments on a specific page
  • What is the schema of a specific data source?
  • Who are the bot users in my workspace?
  • Find pages created in the last week
  • List data sources that have been recently edited
  • Show me all archived pages

Unsupported questions

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

  • Create a new page in Notion
  • Update a data source property
  • Delete a block
  • Add a comment to a page

Installation

uv pip install airbyte-agent-notion

Usage

Connectors can run in open source or hosted mode.

Open source

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

from airbyte_agent_notion import NotionConnector
from airbyte_agent_notion.models import NotionAccessTokenAuthConfig

connector = NotionConnector(
    auth_config=NotionAccessTokenAuthConfig(
        token="<Notion internal integration token (starts with ntn_ or secret_)>"
    )
)

@agent.tool_plain # assumes you're using Pydantic AI
@NotionConnector.tool_utils
async def notion_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

Hosted

In hosted mode, API credentials are stored securely in Airbyte Cloud. 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.

from airbyte_agent_notion import NotionConnector, AirbyteAuthConfig

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

@agent.tool_plain # assumes you're using Pydantic AI
@NotionConnector.tool_utils
async def notion_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

Full documentation

Entities and actions

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

Entity Actions
Users List, Get, Search
Pages List, Get, Search
Data Sources List, Get, Search
Blocks List, Get, Search
Comments List

Authentication

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

Notion API docs

See the official Notion API reference.

Version information

  • Package version: 0.1.30
  • Connector version: 0.1.10
  • Generated with Connector SDK commit SHA: fbc0bacdabf9b1de67621333cd97edee9c444de4
  • Changelog: View changelog

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

airbyte_agent_notion-0.1.30.tar.gz (171.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

airbyte_agent_notion-0.1.30-py3-none-any.whl (197.5 kB view details)

Uploaded Python 3

File details

Details for the file airbyte_agent_notion-0.1.30.tar.gz.

File metadata

  • Download URL: airbyte_agent_notion-0.1.30.tar.gz
  • Upload date:
  • Size: 171.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.12

File hashes

Hashes for airbyte_agent_notion-0.1.30.tar.gz
Algorithm Hash digest
SHA256 9b05aa3e0097df9510fd079f370e601202e24f9f4b4479aad6a1957436a16563
MD5 2fff33a30318b9d827922143ef7dd18b
BLAKE2b-256 02b25ea136f27d01c243c4ebeb2fff3a70c3a858e73c429e2653c051fc1768b4

See more details on using hashes here.

File details

Details for the file airbyte_agent_notion-0.1.30-py3-none-any.whl.

File metadata

File hashes

Hashes for airbyte_agent_notion-0.1.30-py3-none-any.whl
Algorithm Hash digest
SHA256 de64047a85386c7c526582aae08ff298aee97d5ae4b329faafca7f0ecce9322f
MD5 8cad4d0618faba1baaff338f09927cc7
BLAKE2b-256 b0679f53838c9f8aaa3edd2a458197b3fbd5390a730cc31047117a58d320014c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page