Connect AI agents to the Gong MCP server

Setup

1. Install the SDK

   • Node.js
   • Python

   npm install @scalekit-sdk/node dotenv

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Create the Gong MCP connection

   In AgentKit > Connections, create a Gong MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

   Scalekit credentials are available for Gong, so you don't need to register an OAuth app. To show your own app on the consent screen, use your own credentials instead.

   Use your own OAuth app

   Register your Scalekit environment with Gong so Scalekit handles the OAuth flow and token lifecycle for your users. Create a Gong OAuth integration, then add its Client ID and Client Secret to your Scalekit connection.

   1. Copy the redirect URI from Scalekit

      • In the Scalekit dashboard, go to AgentKit > Connections > Create Connection. Find Gong MCP and click Create.

      • Click Use your own credentials and copy the redirect URI. It looks like https://<SCALEKIT_ENVIRONMENT_URL>/sso/v1/oauth/<CONNECTION_ID>/callback.

   2. Create an OAuth integration in Gong

      • Sign in to Gong and go to Admin Center > API.

      • Click the Integrations tab.

      • Click Create Integration.

        

   3. Configure the integration’s scopes and URLs

      • Under Required authorization scopes, select the scopes your agent needs (for example, calls and transcript read access).

      • Go to the URLs & endpoints tab and fill in:

        • Redirect URI needed for the OAuth authorization code flow — paste the redirect URI you copied from Scalekit
        • Link to your integration’s “privacy policy” page and “terms & conditions” page — a URL your organization controls (Gong requires both fields even for private integrations)
        • Link to your integration’s help article — a URL your organization controls
        • Link to page in your integration where authorization process begins — the same redirect URI from Scalekit works here for a private integration

      • Click Save.

        

   4. Copy your Client ID and Client Secret

      • Back on the Integrations tab, find your integration in the table.
      • Copy the Client ID.
      • Click Show secret to reveal and copy the Client Secret.

   5. Add credentials in Scalekit

      • Return to the connection you created in Scalekit and enter:
        • Client ID — from your Gong integration
        • Client Secret — from your Gong integration
      • Click Save.

4. Authorize a user and make your first call

   • Node.js
   • Python

   1
   import { ScalekitClient } from '@scalekit-sdk/node'
   2
   import 'dotenv/config'
   3
   import { createInterface } from 'node:readline/promises'
   4
   
   5
   const scalekit = new ScalekitClient(
   6
     process.env.SCALEKIT_ENVIRONMENT_URL,
   7
     process.env.SCALEKIT_CLIENT_ID,
   8
     process.env.SCALEKIT_CLIENT_SECRET,
   9
   )
   10
   const actions = scalekit.actions
   11
   
   12
   const connector = 'gongmcp'
   13
   const identifier = 'user_123'
   14
   
   15
   // Generate an authorization link for the user
   16
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   17
   console.log('Authorize Gong MCP:', link)
   18
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   19
   await rl.question('Press Enter after authorizing...')
   20
   rl.close()
   21
   
   22
   // Make your first call
   23
   const result = await actions.executeTool({
   24
     connector,
   25
     identifier,
   26
     toolName: 'gongmcp_ask_account',
   27
     toolInput: { crmAccount: 'Cisco Systems Inc', question: 'YOUR_QUESTION' },
   28
   })
   29
   console.log(result)

   npx tsx quickstart.mts

   Each user signs in once. See Authorize a user for the full flow and statuses.