airbyte-agent-intercom 0.1.76

Airbyte Intercom Connector for AI platforms

Intercom

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

Intercom is a customer messaging platform that enables businesses to communicate with customers through chat, email, and in-app messaging. This connector provides read-only access to core Intercom entities including contacts, conversations, companies, teams, admins, tags, and segments for customer support analytics and insights.

Example questions

The Intercom connector is optimized to handle prompts like these.

• List all contacts in my Intercom workspace
• List all companies in Intercom
• What teams are configured in my workspace?
• Show me all admins in my Intercom account
• List all tags used in Intercom
• Show me all customer segments
• Show me details for a recent contact
• Show me details for a recent company
• Show me details for a recent conversation
• Show me conversations from the last week
• List conversations assigned to team {team_id}
• Show me open conversations

Unsupported questions

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

• Create a new contact in Intercom
• Send a message to a customer
• Delete a conversation
• Update company information
• Assign a conversation to an admin
• Create a new tag

Installation

uv pip install airbyte-agent-intercom

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_intercom import IntercomConnector
from airbyte_agent_intercom.models import IntercomAuthConfig

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

@agent.tool_plain # assumes you're using Pydantic AI
@IntercomConnector.tool_utils
async def intercom_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. 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_intercom import IntercomConnector, AirbyteAuthConfig

connector = IntercomConnector(
    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
@IntercomConnector.tool_utils
async def intercom_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
Contacts	List, Get, Search
Conversations	List, Get, Search
Companies	List, Get, Search
Teams	List, Get, Search
Admins	List, Get
Tags	List, Get
Segments	List, Get

Authentication

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

Intercom API docs

See the official Intercom API reference.

Version information

• Package version: 0.1.76
• Connector version: 0.1.8
• Generated with Connector SDK commit SHA: cb4380e76ac5cbc67b9089f94522be1bbe9f8d73
• Changelog: View changelog