Agent Connector

Connect your agents to Intercom

Production-ready access to your Intercom data with managed auth, parametric control, and the reliability your agents need to actually work.

Try it freeTalk to sales

Installation & Usage

Get start with the Intercom connector in minutes.

[01]

Install Package

Using uv or pip

BASH

Copy
uv pip install airbyte-agent-intercom

[02]

Import

Initialize and use

PYTHON

Copy
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>"
    )
)

[03]

Tool

Add tools to your agent

python

Copy
@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 {})

Supported Entities & Actions

Access all your Intercom data through a unified API

Lorem ipsum

Lorem ipsum

| Entity | Actions |\n|--------|---------|\n| Contacts | [List](./REFERENCE.md#contacts-list), [Create](./REFERENCE.md#contacts-create), [Get](./REFERENCE.md#contacts-get), [Update](./REFERENCE.md#contacts-update), [Search](./REFERENCE.md#contacts-search) |\n| Conversations | [List](./REFERENCE.md#conversations-list), [Get](./REFERENCE.md#conversations-get), [Search](./REFERENCE.md#conversations-search) |\n| Companies | [List](./REFERENCE.md#companies-list), [Create](./REFERENCE.md#companies-create), [Get](./REFERENCE.md#companies-get), [Update](./REFERENCE.md#companies-update), [Search](./REFERENCE.md#companies-search) |\n| Teams | [List](./REFERENCE.md#teams-list), [Get](./REFERENCE.md#teams-get), [Search](./REFERENCE.md#teams-search) |\n| Admins | [List](./REFERENCE.md#admins-list), [Get](./REFERENCE.md#admins-get) |\n| Tags | [List](./REFERENCE.md#tags-list), [Create](./REFERENCE.md#tags-create), [Get](./REFERENCE.md#tags-get) |\n| Notes | [Create](./REFERENCE.md#notes-create) |\n| Segments | [List](./REFERENCE.md#segments-list), [Get](./REFERENCE.md#segments-get) |\n| Internal Articles | [Create](./REFERENCE.md#internal-articles-create) |

View full reference documentation

Example Prompts

The Intercom connector is optimized to handle prompts like these

Lorem ipsum

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 - Create a new lead contact named 'Jane Smith' with email jane@example.com - Create an internal article titled 'Onboarding Guide' with instructions for new team members - Create a company named 'Acme Corp' with company_id 'acme-001' - Create a tag named 'VIP Customer' - Update the name of contact \{id\} to 'John Updated' - Add a note to contact \{id\} saying 'Followed up on support request' - Show me conversations from the last week - List conversations assigned to team \{team_id\} - Show me open conversations

View full reference documentation

Why Airbyte for AI Agents?

Built for production AI workloads with enterprise-grade reliability

Secure Authentication

Built-in OAuth 2.0 handling with automatic token refresh. No hard-coded credentials.

Agent-Native Design
Heading

Structured, LLM-friendly schemas optimized for AI agent consumption with natural language query support.

Production Ready

Battle-tested connectors with comprehensive error handling, logging, and retry logic.

Open Source

Fully open source under the MIT license. Contribute, customize, and extend freely.

Explore more connectorsTalk to sales

Works with your favorite frameworks

Use the Salesforce connector with any AI agent framework.

LangChain

CrewAI

LlamaIndex

AutoGen

OpenAI Agents SDK

Claude Agents SDK

Frequently Asked Questions

Didn't find your answer? Please don't hesitate to reach out.

How do I authenticate with Intercom?

The Intercom connector supports direct API authentication using an Intercom API Access Token in open source mode. In hosted mode, you authenticate via Airbyte Cloud credentials (client ID and client secret), with API credentials stored securely in Airbyte Cloud.

Can I use this connector with any AI agent framework?

The connector is compatible with any Python-based AI agent framework including LangChain, LlamaIndex, CrewAI, Pydantic AI, and custom implementations.

Does this connector support write operations?

Yes, the Intercom connector supports several write operations including creating and updating contacts, creating notes, creating internal articles, creating and updating companies, and creating tags. However, it does not currently support sending messages, deleting conversations, contacts, or companies, or assigning conversations to admins.

How is this different from the Airbyte data connector?

Agent connectors are specifically designed for AI agents and LLM applications. They provide natural language interfaces, optimized response formats, and seamless integration with agent frameworks, unlike traditional ETL-focused connectors.

Ready to connect your AI agents to Intercom?

Get started in minutes with our open-source connector.

Go to github
READ THE DOCS