Gong MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

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

   .env

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

3. Set up the connector

   Dashboard setup steps

   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.

        Testing vs. production

        By default, Scalekit creates the connection using its own shared credentials. This works for testing. Before going to production, follow the steps below to use your own Gong OAuth integration.

      • 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.

        Private by default

        New integrations default to Private, meaning OAuth only works for your own Gong account. Keep it private unless you’re building an integration for other Gong customers.

        

   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 and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'gongmcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Gong MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'gongmcp_ask_account',
     toolInput: { crmAccount: 'YOUR_CRMACCOUNT', question: 'YOUR_QUESTION' },
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "gongmcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Gong MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={"crmAccount":"YOUR_CRMACCOUNT","question":"YOUR_QUESTION"},
       tool_name="gongmcp_ask_account",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Account ask — Answer natural-language questions about a specific CRM account by analyzing Gong activities (calls and messages) within a defined time range
• Deal ask — Answer natural-language questions about a specific CRM deal or opportunity by analyzing Gong activities (calls and messages) within a defined time range
• Brief generate — Create a comprehensive structured brief about a CRM entity (account, deal, or contact) by analyzing Gong activities within a specified time period

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

gongmcp_ask_account#Answer natural-language questions about a specific CRM account by analyzing Gong activities (calls and messages) within a defined time range. Returns synthesized insights — not raw data.5 params▾

Answer natural-language questions about a specific CRM account by analyzing Gong activities (calls and messages) within a defined time range. Returns synthesized insights — not raw data.

NameTypeRequiredDescription

crmAccountstringrequiredThe CRM account name (e.g. 'Cisco Systems Inc') or direct CRM ID. Name lookup uses exact matching.

questionstringrequiredNatural-language question about the account. Ask for concepts, themes, risks, blockers, stakeholders, goals, or next steps rather than raw data.

fromDateTimestringoptionalOptional. Inclusive start of the activity window in ISO 8601 format with timezone. Provide both fromDateTime and toDateTime together, or omit both to default to the last 30 days.

toDateTimestringoptionalOptional. Inclusive end of the activity window in ISO 8601 format with timezone. Must be later than fromDateTime.

workspacestringoptionalRequired when the account has multiple workspaces. Accepts a numeric workspace ID or a workspace name (case-insensitive).

gongmcp_ask_deal#Answer natural-language questions about a specific CRM deal or opportunity by analyzing Gong activities (calls and messages) within a defined time range. Returns synthesized insights — not raw data.5 params▾

Answer natural-language questions about a specific CRM deal or opportunity by analyzing Gong activities (calls and messages) within a defined time range. Returns synthesized insights — not raw data.

NameTypeRequiredDescription

crmDealstringrequiredThe CRM deal/opportunity name (e.g. 'Acme Corp - Enterprise Q4') or direct CRM ID (e.g. '006EXAMPLE00001'). Name lookup uses exact matching.

questionstringrequiredNatural-language question about the deal. Ask about themes, risks, objections, competitive mentions, stakeholder concerns, negotiation progress, or next steps.

fromDateTimestringoptionalOptional. Inclusive start of the activity window in ISO 8601 format with timezone (e.g. 2025-08-01T00:00:00Z). Provide both fromDateTime and toDateTime together, or omit both to default to the last 30 days.

toDateTimestringoptionalOptional. Inclusive end of the activity window in ISO 8601 format with timezone. Must be later than fromDateTime.

workspacestringoptionalRequired when the account has multiple workspaces. Accepts a numeric workspace ID (e.g. '1234567890') or a workspace name (case-insensitive, e.g. 'Sales').

gongmcp_generate_brief#Create a comprehensive structured brief about a CRM entity (account, deal, or contact) by analyzing Gong activities within a specified time period. Returns multi-category insights for reviews and handovers.7 params▾

Create a comprehensive structured brief about a CRM entity (account, deal, or contact) by analyzing Gong activities within a specified time period. Returns multi-category insights for reviews and handovers.

NameTypeRequiredDescription

briefNamestringrequiredMust exactly match the name of a published brief configured in the Gong workspace (e.g. 'Business Goals', 'Pain Points', 'Key Players'). If the name does not match, the response lists available briefs.

crmEntitystringrequiredThe CRM entity name or ID. For ACCOUNT and DEAL, provide the name as it appears in CRM or its CRM ID. For CONTACT, provide the direct CRM contact ID.

entityTypestringrequiredThe type of CRM entity: ACCOUNT for companies, DEAL for opportunities, CONTACT for contacts/leads.

fromDateTimestringoptionalRequired when periodType is CUSTOM_RANGE. Inclusive start of the activity window in ISO 8601 format with timezone.

periodTypestringoptionalTime period to analyze. Defaults to LAST_90DAYS. Use CUSTOM_RANGE with fromDateTime/toDateTime for a custom window.

toDateTimestringoptionalRequired when periodType is CUSTOM_RANGE. Inclusive end of the activity window in ISO 8601 format with timezone.

workspacestringoptionalRequired when the account has multiple workspaces. Accepts a numeric workspace ID or a workspace name (case-insensitive).