Gong MCP | OAuth Gong connector for AI agents

CALL ANY TOOL

List a rep's calls, fetch a single call, pull a transcript, push an Engage flow. Same toolkit, every framework, no auth plumbing to maintain.

gong_calls_list

List calls

List Gong calls with optional filters for date range, workspace, and call IDs. Returns metadata including title, duration, participants, and direction.

Parameters

Name

Type

Required

Description

from_date_time

string

Optional

ISO 8601 start filter

to_date_time

string

Optional

ISO 8601 end filter

workspace_id

string

Optional

Gong workspace ID

cursor

string

Optional

Pagination cursor for next page

gong_calls_get

Get calls (extensive)

gong_calls_transcript_get

Get call transcripts

gong_engage_tasks_list

List Engage tasks

gong_engage_flows_list

List Engage flows

gong_engage_prospects_assign

Assign prospects to flow

gong_engage_task_complete

Complete Engage task

gong_stats_interaction

Get interaction statistics

gong_scorecards_list

List scorecards

gong_coaching_get

Get coaching data

gong_users_list

List users

gong_trackers_list

List trackers

Build your Agent

Drop the toolkit in, point it at the rep, and your agent can read Gong calls, transcripts, and coaching data from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gong"], toolNames: ["gong_calls_list", "gong_call_transcript_get", "gong_users_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
 filter: { connectionNames: ["gong"], toolNames: ["gong_calls_list", "gong_calls_get", "gong_transcript_get"] },
 pageSize: 100,
});

// shape tools as OpenAI function definitions
const llmTools = tools.map((t) => ({
 type: "function" as const,
 function: {
 name: t.tool.definition.name,
 description: t.tool.definition.description,
 parameters: t.tool.definition.input_schema,
 },
}));

const resp = await openai.responses.create({
 model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gong"], toolNames: ["gong_calls_list", "gong_call_get", "gong_users_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
 MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
 connectionParams: new StreamableHTTPConnectionParams({
 url: "https://mcp.scalekit.com/gong",
 headers: { Authorization: `Bearer ${userScopedToken}` },
 }}),
}});

const agent = new Agent({
 name: "agent", model: "gemini-2.0-flash",
 tools: await toolset.getTools(),
}});

Try these prompts

These are the questions sales leaders ask Gong every week. Copy any prompt, paste into your agent, watch it route to the right tool with the rep's scope.

Action & follow-up

Copy the prompt

Copied

What call tasks and follow-ups are assigned to me this week?

Copy the prompt

Copied

What did we commit to Acme on our last call?

Copy the prompt

Copied

What are the open questions from yesterday's call?

Copy the prompt

Copied

Draft a follow-up email based on my last call with Stripe.

Search & recall

Copy the prompt

Copied

Find every call where pricing was discussed.

Copy the prompt

Copied

What did [person] say about the roadmap?

Copy the prompt

Copied

Summarise everything discussed about [feature] across all recorded calls.

Copy the prompt

Copied

List all my calls from last month.

Prep & intel

Copy the prompt

Copied

What context do I need before my next call with this account?

Copy the prompt

Copied

Who was on my last call with [company] and what was decided?

Copy the prompt

Copied

Get the full transcript from my most recent call with [account].

SEE HOW AUTH WORKS

Each rep authorises Gong once. Every agent call after that uses their token, runs a scope check, and lands in an exportable audit trail.

1

Authorize

Your user connects

Gong

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Gong

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Gong

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Gong

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other deal intelligence agents and MCP connectors. Working code, live demos, fork what fits.

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

SALES

Sales call prep agent

Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.

Granola

Attio

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other agent connector libraries treat auth as a demo afterthought. Scalekit starts with rep identity, scope enforcement, and audit so production deploys hold up.

01.

Bot calls break rep-level analytics

A shared Gong token looks fine in a demo. In production, every call retrieved looks like it came from a service account. Audit logs break. Per-rep scoping breaks. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared bot token
token = "sk_gong_shared_xxx"
audit → bot_service_account
rep_filter → broken

// scalekit · per-user
token = resolve(user_id)
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Gong today. Chorus, Salesforce, HubSpot tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Gong as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Gong oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Gong?

Yes. Pass a tool name filter to listScopedTools so the deal intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Gong.

What happens when a user revokes Gong access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent pull call transcripts for any rep?

Only for reps the authorizing user can already see in Gong. Manager-level access surfaces team transcripts. IC-level access stays scoped to that rep. Scalekit respects Gong's native permissions.

Gong

Tools your deal intelligence agent reaches for on Gong, scoped per user.