Airtable

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

The Airtable agent connector is a Python package that equips AI agents to interact with Airtable 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.

Airtable is a cloud-based platform that combines the simplicity of a spreadsheet with the power of a database. This connector provides access to bases, tables, and records for data analysis and workflow automation.

Example prompts

The Airtable connector is optimized to handle prompts like these.

List all my Airtable bases
What tables are in my first base?
Show me the schema for tables in a base
List records from a table in my base
Show me recent records from a table
What fields are in a table?
List records where Status is 'Done' in table tblXXX
Find records created last week in table tblXXX
Show me records updated in the last 30 days in base appXXX

Unsupported prompts

The Airtable connector isn't currently able to handle prompts like these.

Create a new record in Airtable
Update a record in Airtable
Delete a record from Airtable
Create a new table
Modify table schema

Entities and actions

This connector supports the following entities and actions. For more details, see this connector's full reference documentation.

Entity	Actions
Bases	List, Context Store Search
Tables	List, Context Store Search
Records	List, Get

Airtable API docs

See the official Airtable API reference.

SDK installation

uv pip install airbyte-agent-sdk

SDK usage

Connectors can run in hosted or open source mode.

Hosted

In hosted mode, API credentials are stored securely in Airbyte Agents. 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.

The connect() factory returns a fully typed AirtableConnector 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.airtable import AirtableConnector

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

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

@agent.tool_plain
@AirtableConnector.tool_utils
async def airtable_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.airtable import AirtableConnector

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

@tool
@AirtableConnector.tool_utils
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable 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.airtable import AirtableConnector

connector = connect("airtable", 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)
@AirtableConnector.tool_utils(framework="openai_agents")
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable 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="Airtable Assistant", tools=[airtable_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.airtable import AirtableConnector

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

mcp = FastMCP("Airtable Agent")

@mcp.tool
@AirtableConnector.tool_utils
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable 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
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.airtable import AirtableConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = AirtableConnector(
    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
@AirtableConnector.tool_utils
async def airtable_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.airtable import AirtableConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = AirtableConnector(
    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
@AirtableConnector.tool_utils
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable 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.airtable import AirtableConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

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

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.airtable import AirtableConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = AirtableConnector(
    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("Airtable Agent")

@mcp.tool
@AirtableConnector.tool_utils
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

Open source

In open source mode, you provide API credentials directly to the connector.

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.airtable import AirtableConnector
from airbyte_agent_sdk.connectors.airtable.models import AirtableAuthConfig

connector = AirtableConnector(
    auth_config=AirtableAuthConfig(
        personal_access_token="<Airtable Personal Access Token. See https://airtable.com/developers/web/guides/personal-access-tokens>"
    )
)

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

@agent.tool_plain
@AirtableConnector.tool_utils
async def airtable_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.airtable import AirtableConnector
from airbyte_agent_sdk.connectors.airtable.models import AirtableAuthConfig

connector = AirtableConnector(
    auth_config=AirtableAuthConfig(
        personal_access_token="<Airtable Personal Access Token. See https://airtable.com/developers/web/guides/personal-access-tokens>"
    )
)

@tool
@AirtableConnector.tool_utils
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable 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.airtable import AirtableConnector
from airbyte_agent_sdk.connectors.airtable.models import AirtableAuthConfig

connector = AirtableConnector(
    auth_config=AirtableAuthConfig(
        personal_access_token="<Airtable Personal Access Token. See https://airtable.com/developers/web/guides/personal-access-tokens>"
    )
)

# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@AirtableConnector.tool_utils(framework="openai_agents")
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable 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="Airtable Assistant", tools=[airtable_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.airtable import AirtableConnector
from airbyte_agent_sdk.connectors.airtable.models import AirtableAuthConfig

connector = AirtableConnector(
    auth_config=AirtableAuthConfig(
        personal_access_token="<Airtable Personal Access Token. See https://airtable.com/developers/web/guides/personal-access-tokens>"
    )
)

mcp = FastMCP("Airtable Agent")

@mcp.tool
@AirtableConnector.tool_utils
async def airtable_execute(entity: str, action: str, params: dict | None = None):
    """Execute Airtable connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

Authentication

For all authentication options, see the connector's authentication documentation.

Version information

Connector version: 1.0.8

Example prompts​

Unsupported prompts​

Entities and actions​

Airtable API docs​

SDK installation​

SDK usage​

Hosted​

Open source​

Authentication​

Version information​