Fathom Tools Reference

Overview

When you connect Fathom to your MCP server, you get 3 additional tools that provide comprehensive access to your meeting data. These tools work together to list meetings, retrieve transcripts, and analyze meeting details.

Available Tools

Typical Workflows

Discovery → Transcript Retrieval

Example natural language command:

"Show me my Fathom meetings from last week, then create a mind
 from the product planning meeting"

Meeting Analysis Workflow

Example natural language command:

"Analyze my client meetings from this month and show me
 all action items and key decisions"

Tool Details

fathom_list_meetings

Purpose: List meetings with summaries and metadata

Key Features:

• Date range filtering (from/to dates)
• Pagination support for large result sets
• Returns meeting IDs, titles, participants, duration, date
• Includes AI-generated summaries

When to use:

• Finding specific meetings by date
• Discovering available meetings before retrieval
• Building meeting inventories
• Quick overview of recent discussions

View full documentation →

fathom_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 team discussions
• Analyzing customer feedback
• Extracting individual speaker segments
• Training AI on actual conversations

View full documentation →

fathom_get_meeting_details

Purpose: Get comprehensive meeting information and AI-generated insights

Key Features:

• AI-generated meeting summary
• Extracted action items and tasks
• Key topics and discussion points
• Full participant list with roles
• Recording and transcript URLs

When to use:

• Quick review of meeting outcomes
• Tracking action items across meetings
• Understanding meeting context before downloading transcripts
• Building meeting databases with insights

View full documentation →

Integration with Mind Reasoner

Creating Minds from Fathom Meetings

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

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

Natural language example:

"Create minds for all team members from our sprint planning
 meetings in the last month"

AI automatically orchestrates all steps.

Bulk Mind Creation

Process multiple meetings at once:

"Find all my 1-on-1 meetings from Q4, create a mind for
 each person I met with, and train them on our conversations"

The AI will:

• List and filter meetings by type/date
• Retrieve transcripts for all matching meetings
• Identify unique 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 meetings from this week"
"List meetings between November 1 and November 15"

By Participant:

"Find meetings with our product team"
"Show me all 1-on-1s with my direct reports"

By Topic:

"Find meetings about the Q4 roadmap"
"Show me client meetings from the enterprise segment"

Combining Tools

Get maximum value by using tools together:

"List my meetings from this week, get details on meetings
 with clients, and create minds for the client contacts"

This single command uses:

• fathom_list_meetings for discovery
• fathom_get_meeting_details for filtering
• fathom_get_transcript for retrieval
• Mind Reasoner tools for mind creation

Unique Fathom Features

AI-Generated Summaries

Fathom automatically generates meeting summaries:

• High-level overview of discussions
• Key decisions and outcomes
• Available directly in list results
• No need to read full transcripts for quick review

Action Item Extraction

Fathom identifies actionable items:

• Automatically extracted from conversations
• Assigned to participants when possible
• Includes due dates when mentioned
• Available via fathom_get_meeting_details

High-Quality Speaker Attribution

• Speaker names and emails provided directly
• Accurate identification via Fathom’s speaker detection
• No name-matching required (unlike Fireflies)

Limitations & Considerations

API Rate Limits

Fathom enforces API rate limits. The MCP server handles these automatically:

• 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:

• Meetings you have permissions to view in Fathom
• Meetings from your organization’s Fathom account
• Meetings that have been fully processed and transcribed

Speaker Attribution

• Speaker emails are provided directly by Fathom (accurate)
• Speakers are identified by Fathom’s AI
• External participants have full metadata when available

Next Steps