Gong

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

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

Gong is a revenue intelligence platform that captures and analyzes customer interactions across calls, emails, and web conferences. This connector provides access to users, recorded calls with transcripts, activity statistics, scorecards, trackers, workspaces, coaching metrics, and library content for sales performance analysis and revenue insights.

Example prompts

The Gong connector is optimized to handle prompts like these.

List all users in my Gong account
Show me calls from last week
Get the transcript for a recent call
List all workspaces in Gong
Show me the scorecard configurations
What trackers are set up in my account?
Get coaching metrics for a manager
What are the activity stats for our sales team?
Find calls mentioning {keyword} this month
Show me calls for rep {user_id} in the last 30 days
Which calls had the longest duration last week?

Unsupported prompts

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

Create a new user in Gong
Delete a call recording
Update scorecard questions
Schedule a new meeting
Send feedback to a team member
Modify tracker keywords

Entities and actions

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

Entity	Actions
Users	List, Get, Context Store Search
Calls	List, Get, Context Store Search
Calls Extensive	List, Context Store Search
Call Audio	Download
Call Video	Download
Workspaces	List
Call Transcripts	List
Stats Activity Aggregate	List
Stats Activity Day By Day	List
Stats Interaction	List
Settings Scorecards	List, Context Store Search
Settings Trackers	List
Library Folders	List
Library Folder Content	List
Coaching	List
Stats Activity Scorecards	List, Context Store Search

Gong API docs

See the official Gong 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 GongConnector 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.gong import GongConnector

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

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

@agent.tool_plain
@GongConnector.tool_utils
async def gong_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.gong import GongConnector

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

@tool
@GongConnector.tool_utils
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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.gong import GongConnector

connector = connect("gong", 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)
@GongConnector.tool_utils(framework="openai_agents")
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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="Gong Assistant", tools=[gong_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.gong import GongConnector

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

mcp = FastMCP("Gong Agent")

@mcp.tool
@GongConnector.tool_utils
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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.gong import GongConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GongConnector(
    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
@GongConnector.tool_utils
async def gong_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.gong import GongConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GongConnector(
    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
@GongConnector.tool_utils
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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.gong import GongConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

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

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.gong import GongConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = GongConnector(
    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("Gong Agent")

@mcp.tool
@GongConnector.tool_utils
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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.gong import GongConnector
from airbyte_agent_sdk.connectors.gong.models import GongAccessKeyAuthenticationAuthConfig

connector = GongConnector(
    auth_config=GongAccessKeyAuthenticationAuthConfig(
        access_key="<Your Gong API Access Key>",
        access_key_secret="<Your Gong API Access Key Secret>"
    )
)

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

@agent.tool_plain
@GongConnector.tool_utils
async def gong_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.gong import GongConnector
from airbyte_agent_sdk.connectors.gong.models import GongAccessKeyAuthenticationAuthConfig

connector = GongConnector(
    auth_config=GongAccessKeyAuthenticationAuthConfig(
        access_key="<Your Gong API Access Key>",
        access_key_secret="<Your Gong API Access Key Secret>"
    )
)

@tool
@GongConnector.tool_utils
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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.gong import GongConnector
from airbyte_agent_sdk.connectors.gong.models import GongAccessKeyAuthenticationAuthConfig

connector = GongConnector(
    auth_config=GongAccessKeyAuthenticationAuthConfig(
        access_key="<Your Gong API Access Key>",
        access_key_secret="<Your Gong API Access Key Secret>"
    )
)

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

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.gong import GongConnector
from airbyte_agent_sdk.connectors.gong.models import GongAccessKeyAuthenticationAuthConfig

connector = GongConnector(
    auth_config=GongAccessKeyAuthenticationAuthConfig(
        access_key="<Your Gong API Access Key>",
        access_key_secret="<Your Gong API Access Key Secret>"
    )
)

mcp = FastMCP("Gong Agent")

@mcp.tool
@GongConnector.tool_utils
async def gong_execute(entity: str, action: str, params: dict | None = None):
    """Execute Gong 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: 0.1.23

Example prompts​

Unsupported prompts​

Entities and actions​

Gong API docs​

SDK installation​

SDK usage​

Hosted​

Open source​

Authentication​

Version information​