Intercom authentication

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

This page documents the authentication and configuration options for the Intercom agent connector.

Authentication

Open source execution

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

OAuth

This authentication method isn't available for this connector.

Token

credentials fields you need:

Field Name	Type	Required	Description
`access_token`	`str`	Yes	Your Intercom API Access Token

Example request:

from airbyte_agent_sdk.connectors.intercom import IntercomConnector
from airbyte_agent_sdk.connectors.intercom.models import IntercomAuthConfig

connector = IntercomConnector(
    auth_config=IntercomAuthConfig(
        access_token="<Your Intercom API Access Token>"
    )
)

Hosted execution

In hosted mode, you first create a connector via the Airbyte Agent API (providing your OAuth or Token credentials), then execute operations using either the Python SDK or API. If you need a step-by-step guide, see the developer quickstart.

OAuth

This authentication method isn't available for this connector.

Bring your own OAuth flow

This authentication method isn't available for this connector.

Token

Create a connector with Token credentials.

credentials fields you need:

Field Name	Type	Required	Description
`access_token`	`str`	Yes	Your Intercom API Access Token

replication_config fields you need:

Field Name	Type	Required	Description
`start_date`	`str (date-time)`	Yes	UTC date and time in the format YYYY-MM-DDTHH:mm:ssZ from which to start replicating data.

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": "Intercom",
    "name": "My Intercom Connector",
    "credentials": {
      "access_token": "<Your Intercom API Access Token>"
    },
    "replication_config": {
      "start_date": "<UTC date and time in the format YYYY-MM-DDTHH:mm:ssZ from which to start replicating data.>"
    }
  }'

Execution

After creating the connector, execute operations using either the Python SDK or API. If your Airbyte client can access multiple organizations, include organization_id in AirbyteAuthConfig and X-Organization-Id in raw API calls.

Python SDK

The connect() factory returns a fully typed IntercomConnector 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.intercom import IntercomConnector

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

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

@agent.tool_plain
@IntercomConnector.tool_utils
async def intercom_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.intercom import IntercomConnector

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

@tool
@IntercomConnector.tool_utils
async def intercom_execute(entity: str, action: str, params: dict | None = None):
    """Execute Intercom 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.intercom import IntercomConnector

connector = connect("intercom", 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)
@IntercomConnector.tool_utils(framework="openai_agents")
async def intercom_execute(entity: str, action: str, params: dict | None = None):
    """Execute Intercom 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="Intercom Assistant", tools=[intercom_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.intercom import IntercomConnector

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

mcp = FastMCP("Intercom Agent")

@mcp.tool
@IntercomConnector.tool_utils
async def intercom_execute(entity: str, action: str, params: dict | None = None):
    """Execute Intercom 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.intercom import IntercomConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = IntercomConnector(
    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
@IntercomConnector.tool_utils
async def intercom_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.intercom import IntercomConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = IntercomConnector(
    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
@IntercomConnector.tool_utils
async def intercom_execute(entity: str, action: str, params: dict | None = None):
    """Execute Intercom 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.intercom import IntercomConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

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

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.intercom import IntercomConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = IntercomConnector(
    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("Intercom Agent")

@mcp.tool
@IntercomConnector.tool_utils
async def intercom_execute(entity: str, action: str, params: dict | None = None):
    """Execute Intercom 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": {}}'

Authentication​

Open source execution​

OAuth​

Token​

Hosted execution​

OAuth​

Bring your own OAuth flow​

Token​

Execution​

Authentication

Open source execution

OAuth

Token

Hosted execution

OAuth

Bring your own OAuth flow

Token

Execution