docs/ai-agents/connectors/facebook-marketing/README.md
The Facebook-Marketing agent connector is a Python package that equips AI agents to interact with Facebook-Marketing 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.
Facebook Marketing API connector for managing ad campaigns, ad sets, ads, creatives, and accessing performance insights, pixel configuration, and event quality data. This connector provides read access to Facebook Ads Manager data for analytics and reporting purposes.
The Facebook-Marketing connector is optimized to handle prompts like these.
The Facebook-Marketing connector isn't currently able to handle prompts like these.
uv pip install airbyte-agent-facebook-marketing
Connectors can run in open source or hosted mode.
In open source mode, you provide API credentials directly to the connector.
from airbyte_agent_facebook_marketing import FacebookMarketingConnector
from airbyte_agent_facebook_marketing.models import FacebookMarketingServiceAccountKeyAuthenticationAuthConfig
connector = FacebookMarketingConnector(
auth_config=FacebookMarketingServiceAccountKeyAuthenticationAuthConfig(
account_key="<Facebook long-lived access token for Service Account authentication>"
)
)
@agent.tool_plain # assumes you're using Pydantic AI
@FacebookMarketingConnector.tool_utils
async def facebook_marketing_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
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_facebook_marketing import FacebookMarketingConnector, AirbyteAuthConfig
connector = FacebookMarketingConnector(
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
@FacebookMarketingConnector.tool_utils
async def facebook_marketing_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
This connector supports the following entities and actions. For more details, see this connector's full reference documentation.
| Entity | Actions |
|---|---|
| Current User | Get |
| Ad Accounts | List, Search |
| Campaigns | List, Create, Get, Update, Search |
| Ad Sets | List, Create, Get, Update, Search |
| Ads | List, Create, Get, Update, Search |
| Ad Creatives | List, Search |
| Ads Insights | List, Search |
| Ad Account | Get, Search |
| Custom Conversions | List, Search |
| Images | List, Search |
| Videos | List, Search |
| Pixels | List, Get |
| Pixel Stats | List |
| Ad Library | List |
For all authentication options, see the connector's authentication documentation.
See the official Facebook-Marketing API reference.