Google-Ads authentication

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

This page documents the authentication and configuration options for the Google-Ads 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": "google-ads"
}'

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	OAuth2 client ID from Google Cloud Console
`client_secret`	`str`	Yes	OAuth2 client secret from Google Cloud Console
`refresh_token`	`str`	Yes	OAuth2 refresh token
`developer_token`	`str`	Yes	Google Ads API developer token

replication_config fields you need:

Field Name	Type	Required	Description
`customer_id`	`str`	Yes	Comma-separated list of Google Ads customer IDs (10 digits each, no dashes).
`start_date`	`str (date)`	No	UTC date in YYYY-MM-DD format from which to start replicating data. Defaults to 2 years ago if not specified.
`conversion_window_days`	`int`	No	Number of days for the conversion attribution window. Default is 14. (default: `14`)

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": "Google-Ads",
    "name": "My Google-Ads Connector",
    "credentials": {
      "client_id": "<OAuth2 client ID from Google Cloud Console>",
      "client_secret": "<OAuth2 client secret from Google Cloud Console>",
      "refresh_token": "<OAuth2 refresh token>",
      "developer_token": "<Google Ads API developer token>"
    },
    "replication_config": {
      "customer_id": "<Comma-separated list of Google Ads customer IDs (10 digits each, no dashes).>",
      "start_date": "<UTC date in YYYY-MM-DD format from which to start replicating data. Defaults to 2 years ago if not specified.>",
      "conversion_window_days": "<Number of days for the conversion attribution window. Default is 14.>"
    }
  }'

Token

This authentication method isn't available for this connector.

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": "google-ads"
}'

Describe the connector to see its supported entities and actions:

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

Execute an action:

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

Python SDK

The connect() factory returns a fully typed GoogleAdsConnector 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.google_ads import GoogleAdsConnector

connector = connect("google-ads", workspace_name="<your_workspace_name>")

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

@agent.tool_plain
@GoogleAdsConnector.tool_utils
async def google_ads_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.google_ads import GoogleAdsConnector

connector = connect("google-ads", workspace_name="<your_workspace_name>")

@tool
@GoogleAdsConnector.tool_utils
async def google_ads_execute(entity: str, action: str, params: dict | None = None):
    """Execute Google-Ads 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.google_ads import GoogleAdsConnector

connector = connect("google-ads", 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)
@GoogleAdsConnector.tool_utils(framework="openai_agents")
async def google_ads_execute(entity: str, action: str, params: dict | None = None):
    """Execute Google-Ads 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="Google-Ads Assistant", tools=[google_ads_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.google_ads import GoogleAdsConnector

connector = connect("google-ads", workspace_name="<your_workspace_name>")

mcp = FastMCP("Google-Ads Agent")

@mcp.tool
@GoogleAdsConnector.tool_utils
async def google_ads_execute(entity: str, action: str, params: dict | None = None):
    """Execute Google-Ads 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.google_ads import GoogleAdsConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GoogleAdsConnector(
    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
@GoogleAdsConnector.tool_utils
async def google_ads_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.google_ads import GoogleAdsConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GoogleAdsConnector(
    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
@GoogleAdsConnector.tool_utils
async def google_ads_execute(entity: str, action: str, params: dict | None = None):
    """Execute Google-Ads 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.google_ads import GoogleAdsConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GoogleAdsConnector(
    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)
@GoogleAdsConnector.tool_utils(framework="openai_agents")
async def google_ads_execute(entity: str, action: str, params: dict | None = None):
    """Execute Google-Ads 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="Google-Ads Assistant", tools=[google_ads_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.google_ads import GoogleAdsConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GoogleAdsConnector(
    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("Google-Ads Agent")

@mcp.tool
@GoogleAdsConnector.tool_utils
async def google_ads_execute(entity: str, action: str, params: dict | None = None):
    """Execute Google-Ads 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	OAuth2 client ID from Google Cloud Console
`client_secret`	`str`	Yes	OAuth2 client secret from Google Cloud Console
`refresh_token`	`str`	Yes	OAuth2 refresh token
`developer_token`	`str`	Yes	Google Ads API developer token

Example request:

from airbyte_agent_sdk.connectors.google_ads import GoogleAdsConnector
from airbyte_agent_sdk.connectors.google_ads.models import GoogleAdsAuthConfig

connector = GoogleAdsConnector(
    auth_config=GoogleAdsAuthConfig(
        client_id="<OAuth2 client ID from Google Cloud Console>",
        client_secret="<OAuth2 client secret from Google Cloud Console>",
        refresh_token="<OAuth2 refresh token>",
        developer_token="<Google Ads API developer token>"
    )
)

Token

This authentication method isn't available for this connector.

Hosted mode (most cases)​

OAuth​

Token​

Execution​

Open source mode​

OAuth​

Token​

Hosted mode (most cases)

OAuth

Token

Execution

Open source mode

OAuth

Token