Granola authentication

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

This page documents the authentication and configuration options for the Granola 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

This authentication method isn't available for this connector.

Token

Create a connector with Token credentials.

credentials fields you need:

Field Name	Type	Required	Description
`api_key`	`str`	Yes	Granola API key. For a personal key, open the Granola desktop app and go to Settings > Connectors > API keys > Create new key. For an Enterprise API key, go to Settings > API > Create new key. On Enterprise plans, workspace admins must enable "Allow personal API keys" in Settings > Workspace > General before personal keys can be created.

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": "Granola",
    "name": "My Granola Connector",
    "credentials": {
      "api_key": "<Granola API key. For a personal key, open the Granola desktop app and go to Settings > Connectors > API keys > Create new key. For an Enterprise API key, go to Settings > API > Create new key. On Enterprise plans, workspace admins must enable "Allow personal API keys" in Settings > Workspace > General before personal keys can be created.>"
    }
  }'

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": "granola"
}'

Describe the connector to see its supported entities and actions:

airbyte-agent connectors describe --json '{
  "workspace": "<your_workspace_name>",
  "name": "granola"
}'

Execute an action:

airbyte-agent connectors execute --json '{
  "workspace": "<your_workspace_name>",
  "name": "granola",
  "entity": "<entity>",
  "action": "<action>",
  "params": {}
}'

Python SDK

The connect() factory returns a fully typed GranolaConnector 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.granola import GranolaConnector

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

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

@agent.tool_plain
@GranolaConnector.tool_utils
async def granola_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.granola import GranolaConnector

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

@tool
@GranolaConnector.tool_utils
async def granola_execute(entity: str, action: str, params: dict | None = None):
    """Execute Granola 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.granola import GranolaConnector

connector = connect("granola", 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)
@GranolaConnector.tool_utils(framework="openai_agents")
async def granola_execute(entity: str, action: str, params: dict | None = None):
    """Execute Granola 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="Granola Assistant", tools=[granola_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.granola import GranolaConnector

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

mcp = FastMCP("Granola Agent")

@mcp.tool
@GranolaConnector.tool_utils
async def granola_execute(entity: str, action: str, params: dict | None = None):
    """Execute Granola 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

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.granola import GranolaConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GranolaConnector(
    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
@GranolaConnector.tool_utils
async def granola_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.granola import GranolaConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GranolaConnector(
    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
@GranolaConnector.tool_utils
async def granola_execute(entity: str, action: str, params: dict | None = None):
    """Execute Granola 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.granola import GranolaConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GranolaConnector(
    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)
@GranolaConnector.tool_utils(framework="openai_agents")
async def granola_execute(entity: str, action: str, params: dict | None = None):
    """Execute Granola 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="Granola Assistant", tools=[granola_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.granola import GranolaConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GranolaConnector(
    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("Granola Agent")

@mcp.tool
@GranolaConnector.tool_utils
async def granola_execute(entity: str, action: str, params: dict | None = None):
    """Execute Granola 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

This authentication method isn't available for this connector.

Token

credentials fields you need:

Field Name	Type	Required	Description
`api_key`	`str`	Yes	Granola API key. For a personal key, open the Granola desktop app and go to Settings > Connectors > API keys > Create new key. For an Enterprise API key, go to Settings > API > Create new key. On Enterprise plans, workspace admins must enable "Allow personal API keys" in Settings > Workspace > General before personal keys can be created.

Example request:

from airbyte_agent_sdk.connectors.granola import GranolaConnector
from airbyte_agent_sdk.connectors.granola.models import GranolaAuthConfig

connector = GranolaConnector(
    auth_config=GranolaAuthConfig(
        api_key="<Granola API key. For a personal key, open the Granola desktop app and go to Settings > Connectors > API keys > Create new key. For an Enterprise API key, go to Settings > API > Create new key. On Enterprise plans, workspace admins must enable "Allow personal API keys" in Settings > Workspace > General before personal keys can be created.>"
    )
)

Hosted mode (most cases)​

OAuth​

Token​

Execution​

Open source mode​

OAuth​

Token​

Hosted mode (most cases)

OAuth

Token

Execution

Open source mode

OAuth

Token