Gong Tools Reference

Access sales call recordings and transcripts through 3 MCP tools
Setup Required

These tools require Gong integration to be configured. See the Gong Setup Guide for configuration instructions.

Overview

When you connect Gong to your MCP server, you get 3 additional tools that provide comprehensive access to your sales call data. These tools work together to list calls, retrieve transcripts, and analyze call details.

Available Tools

ToolPurposeCommon Use Cases
gong_list_callsList call recordings with metadataFind recent calls, filter by date, discover call IDs
gong_get_transcriptGet detailed transcriptsCreate minds, analyze conversations, extract speaker segments
gong_get_call_detailsGet call analyticsAnalyze topics, review speaker stats, understand call structure

Typical Workflows

Discovery → Transcript Retrieval

1

List Calls

Use gong_list_calls to find calls of interest, filter by date range, get call IDs

2

Get Transcript

Use gong_get_transcript with a call ID to retrieve the full conversation with speaker attribution

3

Create Mind

Upload the transcript to Mind Reasoner to create a digital mind of a participant

Example natural language command:

"Show me my Gong calls from last week, then create a mind
from the call with our enterprise prospect"

Call Analysis Workflow

1

List Calls

Find calls to analyze based on date, participants, or other criteria

2

Get Call Details

Use gong_get_call_details to get analytics: topics discussed, speaker stats, call structure

3

Deep Dive

For interesting calls, get full transcripts to extract specific segments

Example natural language command:

"Analyze my top 5 longest calls this month and show me
the main topics discussed and speaker participation rates"

Tool Details

gong_list_calls

Purpose: List call recordings with metadata and optional date filtering

Key Features:

  • Date range filtering (from/to dates)
  • Pagination support for large result sets
  • Returns call IDs, titles, participants, duration, date

When to use:

  • Finding specific calls by date
  • Discovering available calls before retrieval
  • Building call inventories
  • Filtering to calls of interest

View full documentation →

gong_get_transcript

Purpose: Retrieve detailed transcripts with full speaker attribution

Key Features:

  • Complete conversation text
  • Speaker names and email addresses
  • Timestamp information
  • Structured by speaker turns

When to use:

  • Creating minds from sales conversations
  • Analyzing customer objections and responses
  • Extracting individual speaker segments
  • Training AI on actual conversations

View full documentation →

gong_get_call_details

Purpose: Get comprehensive call analytics and metadata

Key Features:

  • Participant details (names, emails, roles)
  • Topics discussed during the call
  • Call structure (agenda items, phases)
  • Speaker statistics (talk time, word count)

When to use:

  • Understanding call dynamics before downloading transcripts
  • Analyzing topic coverage across calls
  • Evaluating speaker participation
  • Identifying high-value calls for mind creation

View full documentation →

Integration with Mind Reasoner

Creating Minds from Gong Calls

The most common workflow combines Gong tools with Mind Reasoner tools:

  1. Discovery: Use gong_list_calls to find relevant calls
  2. Retrieval: Use gong_get_transcript to get the full conversation
  3. Mind Creation: Use Mind Reasoner create_mind to create a digital entity
  4. Upload: Upload the Gong transcript as training data
  5. Training: Create snapshot and wait for AI training to complete
  6. Simulation: Run predictions based on the sales conversation patterns

Natural language example:

"Create minds for all the customer-facing participants
in my Gong calls from the last quarter"

AI automatically orchestrates all steps, handling pagination, transcript retrieval, and mind creation.

Bulk Mind Creation

Process multiple calls at once:

"Find all my discovery calls from Q4, create a mind for
each prospect, and train them on their segments of the conversation"

The AI will:

  • List and filter calls by type/date
  • Retrieve transcripts for all matching calls
  • Identify prospect participants
  • Create individual minds
  • Extract relevant transcript segments per person
  • Upload and train each mind

Tips for Effective Use

Filtering Strategies

By Date:

"Show me calls from the first week of November"
"List calls between October 15 and October 30"

By Participant:

"Find calls with prospects in the enterprise segment"
"Show me all calls where Sarah from our team participated"

By Call Characteristics:

"Find my longest calls this month"
"Show me calls that lasted more than 45 minutes"

Combining Tools

Get maximum value by using tools together:

"List my calls from this week, get details on the top 3
by duration, and if any discussed pricing objections,
create minds from those conversations"

This single command uses:

  • gong_list_calls for discovery
  • gong_get_call_details for filtering
  • gong_get_transcript for retrieval
  • Mind Reasoner tools for mind creation

Limitations & Considerations

API Rate Limits

Gong enforces API rate limits. The MCP server handles these automatically, but be aware:

  • Bulk operations may take time if rate limited
  • Error messages will indicate when to retry
  • Consider spreading large operations over time

Data Access

You can only access:

  • Calls you have permissions to view in Gong
  • Calls from your organization’s Gong account
  • Transcripts that have been fully processed

Speaker Attribution

  • Speaker emails are provided directly by Gong (accurate)
  • Speakers are identified by Gong’s voice recognition
  • External participants may have limited metadata

Next Steps

📖

Individual Tool Docs

Explore detailed documentation for each Gong tool with parameters and examples.

🔧

Setup Guide

If you haven’t configured Gong yet, follow the setup guide.

Gong Setup →
💡

Workflow Examples

See complete examples of Gong + Mind Reasoner workflows.

Quickstart Guide →