How to integrate Gong MCP with Autogen

Framework Integration Gradient
Gong Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Gong to AutoGen using the Composio tool router. By the end, you'll have a working Gong agent that can create a new gong meeting with my team, list user activity statistics for last week, add call recording media to a specific call, show all contacts linked to this phone number through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Gong account through Composio's Gong MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Gong
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Gong tools
  • Run a live chat loop where you ask the agent to perform Gong operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Gong MCP server, and what's possible with it?

The Gong MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gong account. It provides structured and secure access to your meetings, calls, and team collaboration data, so your agent can schedule meetings, analyze call recordings, generate user activity reports, and manage CRM integrations—all on your behalf.

  • Automated meeting scheduling and management: Have your agent create new Gong meetings, ensuring your team and clients are always connected at the right time.
  • Call recording upload and analysis: Let your agent add call media, process call recordings, and help organize your sales conversations for later review.
  • User activity and scorecard reporting: Direct your agent to generate detailed reports on team activity, review scorecards, and aggregate user statistics for performance insights.
  • Prospect and flow management: Assign prospects to sales flows, helping automate outreach and follow-ups directly from your CRM data.
  • CRM integration and data privacy controls: Enable your agent to manage CRM integrations and surface all records related to specific phone numbers, ensuring compliance and streamlined operations.

Supported Tools & Triggers

Tools
Add call media v2 calls id mediaAdds a call media, recorded by a telephony system (PBX) or other media recording facility.
Add new call v2 callsWhen using this endpoint, either provide a downloadMediaUrl or use the returned callId in a follow-up request to /v2/calls/{id}/media to upload the media file.
Aggregate activity by period via apiLists the aggregated activity of multiple users within the Gong system for each time period within the defined date range.
Aggregate user activity statisticsLists the activity of multiple users within the Gong system during a defined period.
Assign prospects to flowUse this endpoint to assign a number of prospects to a flow.
Create activity scorecards reportRetrieve all the answers for the scorecards that were reviewed during a specified date range, for calls that took place during a specified date range, for specific scorecards or for specific reviewed users.
Create a new gong meeting v2 meetingsWhen accessed through a Bearer token authorization method, this endpoint requires the scope 'api:meetings:user:create'.
Create permission profile v2 permission profileCreate a permission profile in a given workspace.
Data privacy for phone numberShows the elements in the Gong system that reference the given phone number.
Delete a generic crm integration v2 crm integrationsDeletes an existing CRM integration from the Gong platform.
Delete a gong meeting v2 meetingsWhen accessed through a Bearer token authorization method, this endpoint requires the scope 'api:meetings:user:delete'.
Delete users from call access listRemove individual user access from calls.
Erase data for email addressGiven an email address, this endpoint deletes from the Gong system any calls or email messages that reference this address.
Erase data for phone numberGiven a phone number, this endpoint deletes from the Gong system any leads or contacts with a matching phone number or mobile phone number.
Fetch all permission profilesReturns a list of all permission profiles.
Get Crm Integration Details.
Get crm objects v2 crm entitiesRetrieves CRM entities from the Gong platform.
Get permission profileReturns a permission profile.
Get request status v2 crm request statusThe GetCRMRequestStatus endpoint retrieves the current status of CRM integration requests in the Gong platform.
List all coaching metrics v2 coachingList all of the coaching metrics of a manager.
List all company workspaces v2 workspacesReturns a list of all workspaces including their details.
List all users v2 usersList all of the company's users.
List flows for crm prospectsGet the Gong Engage flows assigned to the given prospects.
List Folder CallsGiven a folder id, this endpoint retrieves a list of calls in it.
List gong engage flows v2 flowsEngage flows have the following visibility types: * Company: visible to everyone in the company, can only be edited by users with edit permissions.
List schema fields v2 crm entity schemaRetrieves the comprehensive schema of CRM entities in the Gong platform.
List users by filter v2 users extensiveList multiple Users.
Manage user call accessReturns a list of users who have received individual access to calls through the API.
Post a digital interaction v2 digital interactionWhen accessed through a Bearer token authorization method, this endpoint requires the scope 'api:digital-interactions:write'.
Post day by day activity statsRetrieve the daily activity of multiple users within the Gong system for a range of dates.
Post interaction filter statsReturns interaction stats for users based on calls that have Whisper turned on.
Post meeting integration statusWhen accessed through a Bearer token authorization method, this endpoint requires the scope 'api:meetings:integration:status'.
Register Crm IntegrationUpdates an existing CRM integration in the Gong platform.
Report content viewed eventPush engagement events into Gong and display them as events in Gong’s activity timeline, when a content is viewed by an external participant (for example, a contract was “viewed” by the prospect) When accessed through a Bearer token authorization method, this endpoint requires the scope 'api:engagement-data:write'.
Report Custom Engagement EventPush engagement events into Gong and display them as events in Gong’s activity timeline, when a content is engaged by an external participant (for example, a contract was “signed” by the prospect) When accessed through a Bearer token authorization method, this endpoint requires the scope 'api:engagement-data:write'.
Retrieve call data by date range v2 callsList calls that took place during a specified date range.
Retrieve data for a specific call v2 calls idRetrieve data for a specific call.
Retrieve data privacy info for email addressShows the elements in the Gong system that reference the given email address.
Retrieve filtered call detailsLists detailed call data for calls that took place during a specified date range, have specified call IDs or hosted by specified users.
Retrieve library folders v2 library foldersUse this endpoint to retrieve a list of public library folders.
Retrieve logs data by type and time range v2 logsList log entries that took place during a specified time range.
Retrieve manual crm call associationsReturns a list of all calls that were manually associated or re-associated with CRM account and deal/opportunity since a given time.
Retrieve scorecards details v2 settings scorecardsRetrieve all the scorecards within the Gong system.
Retrieve tracker details v2 settings trackersRetrieves details of all keyword trackers in the system or in a given workspace.
Retrieve transcripts of calls v2 calls transcriptReturns transcripts for calls that took place during the specified date period.
Retrieve User Settings HistoryRetrieve a specific user's settings history.
Retrieve users from permission profileReturns a list of all users whose access is controlled by the given permission profile.
Retrieve user v2 users idRetrieve a specific user.
Set User Call AccessGive individual users access to calls.
Update a gong meeting v2 meetings meetingidWhen accessed through a Bearer token authorization method, this endpoint requires the scope 'api:meetings:user:update'.
Update permission profile v2 permission profileUpdate a permission profile.
Update shared content eventPush engagement events into Gong and display them as events in Gong’s activity timeline, when a Gong user shares content with external participants (for example, a contract was “shared” by the account executive with his prospects) When accessed through a Bearer token authorization method, this endpoint requires the scope 'api:engagement-data:write'.
Upload crm objects v2 crm entitiesUploads CRM data files to the Gong platform for integration and analysis.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Gong account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Gong via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Gong connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Gong session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["gong"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Gong tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Gong assistant agent with MCP tools
    agent = AssistantAgent(
        name="gong_assistant",
        description="An AI assistant that helps with Gong operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Gong tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Gong related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Gong tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Gong and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Gong session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["gong"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Gong assistant agent with MCP tools
        agent = AssistantAgent(
            name="gong_assistant",
            description="An AI assistant that helps with Gong operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Gong related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Gong through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Gong, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Gong MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Gong MCP?

With a standalone Gong MCP server, the agents and LLMs can only access a fixed set of Gong tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Gong and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Gong tools.

Can I manage the permissions and scopes for Gong while using Tool Router?

Yes, absolutely. You can configure which Gong scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Gong data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.