How to integrate Gong MCP with Vercel AI SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Gong Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Gong to Vercel AI SDK 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 Vercel AI SDK 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:
  • How to set up and configure a Vercel AI SDK agent with Gong integration
  • Using Composio's Tool Router to dynamically load and access Gong tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

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

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

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 required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { experimental_createMCPClient as createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const { session } = await composio.create(composioUserID!, {
    toolkits: ["gong"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Gong tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Gong-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Gong tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to gong, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Gong tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Gong and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { experimental_createMCPClient as createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const { session } = await composio.create(composioUserID!, {
    toolkits: ["gong"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to gong, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Gong agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Gong MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Gong MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Gong MCP with Claude Agent SDK

Google ADK

Google ADK

Use Gong MCP with Google ADK

LangChain

LangChain

Use Gong MCP with LangChain

Mastra AI

Mastra AI

Use Gong MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Gong MCP with LlamaIndex

CrewAI

CrewAI

Use Gong MCP with CrewAI

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 Vercel AI SDK?

Yes, you can. Vercel AI SDK 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.

Book a call↗Get started for free