Hubspot

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

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

HubSpot is a CRM platform that provides tools for marketing, sales, customer service, and content management. This connector provides access to contacts, companies, deals, tickets, and custom objects for customer relationship management and sales analytics.

Example prompts

The Hubspot connector is optimized to handle prompts like these.

List recent deals
List recent tickets
List companies in my CRM
List contacts in my CRM
Show me all deals from {company} this quarter
What are the top 5 most valuable deals in my pipeline right now?
Search for contacts in the marketing department at {company}
Give me an overview of my sales team's deals in the last 30 days
Identify the most active companies in our CRM this month
Compare the number of deals closed by different sales representatives
Find all tickets related to a specific product issue and summarize their status

Unsupported prompts

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

Create a new contact record for {person}
Update the contact information for {customer}
Delete the ticket from last week's support case
Schedule a follow-up task for this deal
Send an email to all contacts in the sales pipeline

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, API Search, Context Store Search
Companies	List, Get, API Search, Context Store Search
Deals	List, Get, API Search, Context Store Search
Tickets	List, Get, API Search, Context Store Search
Schemas	List, Get
Objects	List, Get

Hubspot API docs

See the official Hubspot 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 HubspotConnector 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.hubspot import HubspotConnector

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

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

@agent.tool_plain
@HubspotConnector.tool_utils
async def hubspot_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.hubspot import HubspotConnector

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

@tool
@HubspotConnector.tool_utils
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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.hubspot import HubspotConnector

connector = connect("hubspot", 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)
@HubspotConnector.tool_utils(framework="openai_agents")
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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="Hubspot Assistant", tools=[hubspot_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.hubspot import HubspotConnector

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

mcp = FastMCP("Hubspot Agent")

@mcp.tool
@HubspotConnector.tool_utils
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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.hubspot import HubspotConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = HubspotConnector(
    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
@HubspotConnector.tool_utils
async def hubspot_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.hubspot import HubspotConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = HubspotConnector(
    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
@HubspotConnector.tool_utils
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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.hubspot import HubspotConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

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

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.hubspot import HubspotConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = HubspotConnector(
    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("Hubspot Agent")

@mcp.tool
@HubspotConnector.tool_utils
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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.hubspot import HubspotConnector
from airbyte_agent_sdk.connectors.hubspot.models import HubspotPrivateAppAuthConfig

connector = HubspotConnector(
    auth_config=HubspotPrivateAppAuthConfig(
        private_app_token="<Access token from a HubSpot Private App>"
    )
)

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

@agent.tool_plain
@HubspotConnector.tool_utils
async def hubspot_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.hubspot import HubspotConnector
from airbyte_agent_sdk.connectors.hubspot.models import HubspotPrivateAppAuthConfig

connector = HubspotConnector(
    auth_config=HubspotPrivateAppAuthConfig(
        private_app_token="<Access token from a HubSpot Private App>"
    )
)

@tool
@HubspotConnector.tool_utils
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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.hubspot import HubspotConnector
from airbyte_agent_sdk.connectors.hubspot.models import HubspotPrivateAppAuthConfig

connector = HubspotConnector(
    auth_config=HubspotPrivateAppAuthConfig(
        private_app_token="<Access token from a HubSpot Private App>"
    )
)

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

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.hubspot import HubspotConnector
from airbyte_agent_sdk.connectors.hubspot.models import HubspotPrivateAppAuthConfig

connector = HubspotConnector(
    auth_config=HubspotPrivateAppAuthConfig(
        private_app_token="<Access token from a HubSpot Private App>"
    )
)

mcp = FastMCP("Hubspot Agent")

@mcp.tool
@HubspotConnector.tool_utils
async def hubspot_execute(entity: str, action: str, params: dict | None = None):
    """Execute Hubspot 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: 0.1.19

Example prompts​

Unsupported prompts​

Entities and actions​

Hubspot API docs​

SDK installation​

SDK usage​

Hosted​

Open source​

Authentication​

Version information​