Facebook-Marketing agent connector
Facebook Marketing API connector for managing ad campaigns, ad sets, ads, creatives, and accessing performance insights. This connector provides read access to Facebook Ads Manager data for analytics and reporting purposes.
Example questions
The Facebook-Marketing connector is optimized to handle prompts like these.
- List all active campaigns in my ad account
- Show me the ad sets with the highest daily budget
- What ads are currently running in campaign {campaign_name}?
- Show me the performance insights for the last 7 days
- Which campaigns have the most spend this month?
- List all ad creatives in my account
- What is the status of my campaigns?
- Show me ads with the highest click-through rate
- List all custom conversion events in my account
- Show me all ad images in my account
- What videos are available in my ad account?
Unsupported questions
The Facebook-Marketing connector isn't currently able to handle prompts like these.
- Create a new campaign
- Update the budget for this ad set
- Pause all ads in this campaign
- Delete this ad creative
Installation
uv pip install airbyte-agent-facebook-marketing
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_facebook-marketing import FacebookMarketingConnector
from airbyte_agent_facebook_marketing.models import FacebookMarketingAuthConfig
connector = FacebookMarketingConnector(
auth_config=FacebookMarketingAuthConfig(
access_token="<Facebook Marketing API access token>",
account_id="<Facebook Ad Account ID (without the act_ prefix)>"
)
)
@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 {})
Hosted
In hosted mode, API credentials are stored securely in Airbyte Cloud. You provide your Airbyte credentials instead.
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
connector = FacebookMarketingConnector(
external_user_id="<your_external_user_id>",
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 {})
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 |
|---|---|
| Campaigns | List, Get |
| Ad Sets | List, Get |
| Ads | List, Get |
| Ad Creatives | List |
| Ads Insights | List |
| Custom Conversions | List |
| Images | List |
| Videos | List |
Authentication and configuration
For all authentication and configuration options, see the connector's authentication documentation.
Facebook-Marketing API docs
See the official Facebook-Marketing API reference.
Version information
- Package version: 0.1.2
- Connector version: 1.0.1
- Generated with Connector SDK commit SHA: 5b20f488dec0e8f29410823753106603c23a4b65
- Changelog: View changelog