discovering-connectors
Discovering Connectors
Programmatic Discovery
from airbyte_agent_sdk import list_connectors
available = list_connectors()
# Returns sorted list of connector slugs: ["airtable", "asana", "github", ...]
Exploring a Connector's Capabilities
Each connector has documentation at:
https://github.com/airbytehq/airbyte-agent-sdk/tree/main/connectors/{name}
| File | What it tells you |
|---|---|
README.md |
Entities/actions table, install instructions, example questions |
AUTH.md |
Credential requirements (OAuth, API key, etc.), hosted setup |
REFERENCE.md |
Full entity/action parameters and schemas |
Read the connector's README first to understand what it can do.
Runtime Introspection
When a typed connector package is installed, use runtime methods for schema details:
from airbyte_agent_sdk import AirbyteAuthConfig
from airbyte_agent_sdk.connectors.stripe import StripeConnector
connector = StripeConnector(
auth_config=AirbyteAuthConfig(
airbyte_client_id=os.getenv("AIRBYTE_CLIENT_ID"),
airbyte_client_secret=os.getenv("AIRBYTE_CLIENT_SECRET"),
workspace_name=os.getenv("AIRBYTE_WORKSPACE_NAME", "default"),
)
)
# List all entities and their available actions
entities = connector.list_entities()
for entity in entities:
print(f"{entity['entity_name']}: {entity['available_actions']}")
# Get JSON schema for a specific entity
schema = connector.entity_schema("customers")
Note: list_entities() and entity_schema() require a typed connector (available after uv pip install airbyte-agent-sdk). They are not available on the generic HostedExecutor.
Auth Requirements
Read the connector's AUTH.md to understand what credentials are needed. For hosted mode (the default), API credentials are stored in Airbyte Cloud — you provide Airbyte client credentials instead.
References
More from airbytehq/airbyte-agent-sdk
airbyte-sdk-reference
Reference documentation for the Airbyte per-connector typed SDK packages
4bootstrapping-agent
Wires up an Airbyte connector for use in a PydanticAI or Claude SDK agent. Generates auth config, connector initialization, and tool_utils-decorated tool function. Use when adding a connector to an agent or setting up a new agent with a connector.
3building-multi-connector-agent
Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK. Scaffolds project structure, wires up connectors, composes tools, and creates a run loop. Use when building an agent with multiple connectors or scaffolding a new agent project.
3