Automating Meeting Sharing with Claude Code + a Custom Fireflies MCP

How I built a Fireflies connector in 10 minutes and used it to share several months of customer calls with my team

The Problem: Automating Meeting Sharing

I had several months of customer calls sitting in Fireflies. Hundreds of conversations with prospects, customers, and partners—each one containing insights about objections, feature requests, and competitive intel.

The problem? They were locked away. Only the meeting host could see each recording.

Sharing them manually would mean opening each meeting in Fireflies, navigating to settings, updating the privacy level, and repeating this 64 times. That's the kind of task that gets pushed to "later" indefinitely.

The Approach: use Fireflies MCP and Claude Code

I wanted to use Claude Code with an MCP (Model Context Protocol) server to automate this. MCP lets AI assistants interact with external tools through a standardized interface—perfect for giving Claude access to Fireflies.

Why Not Use the Official Fireflies MCP?

Fireflies has an official MCP server that's great for querying meeting data. It's optimized for the most common use case: extracting insights from your calls—summarizing discussions, pulling action items, analyzing sentiment across meetings.

But for this workflow, I needed write operations:

• set_transcript_privacy — Change who can access a recording
• update_transcript_channel — Organize transcripts
• create_soundbite — Create clips from transcripts

The official MCP focuses on read access. That's a reasonable design decision—most users want to query their data, not modify it programmatically. But it meant I needed something different.

Building My Own Fireflies MCP with StackOne's Falcon Connector Engine

Here's where it gets interesting. Instead of writing a custom MCP server from scratch, I used StackOne's AI Connector Builder to create a Fireflies connector in about 10 minutes.

The Falcon Connector Engine is StackOne's foundation powering 200+ pre-built connectors. It lets you define connectors using YAML configurations, and once deployed, they automatically expose through multiple protocols—including MCP for AI agents.

The AI Builder is an AI assistant that operates within your IDE (Claude Code, Cursor, or VS Code) and uses 20+ specialized MCP tools to automate the process:

1. Research — The agent autonomously discovers Fireflies' API documentation and endpoints
2. Config Building — Generates YAML configurations adhering to the Falcon spec
3. Validation — Validates syntax via CLI
4. Testing — Tests actions against the live API
5. Deploy — Push via npx @stackone/cli

The result is a YAML-defined connector that exposes Fireflies' full API surface—including the write operations I needed. StackOne then serves this as an MCP server I can connect to from Claude Code.

The Custom Fireflies MCP: Full Action Reference

Here's what my Fireflies connector exposes:

User Management

• get_user (GET) — Retrieve current API key owner info (user_id, name, email, admin status, transcript count, minutes consumed)
• list_users (LIST) — Retrieve all users within your Fireflies team

Contacts & Analytics

• list_contacts (LIST) — Retrieve meeting participants (email, name, picture, last meeting date)
• get_analytics (GET) — Team analytics: talk/listen ratios, sentiment, questions asked, filler words, meeting counts

Transcript Management

• list_transcripts (LIST) — List transcripts with filters (limit, skip, fromDate, toDate, host_email, keyword)
• get_transcript (GET) — Full transcript: sentences, speakers, summary, action items, media URLs
• set_transcript_privacy (UPDATE) — Change privacy level: link, owner, participants, teammatesandparticipants, teammates
• update_transcript_channel (UPDATE) — Move transcript to a specified channel

Soundbites (Clips)

• create_soundbite (CREATE) — Create a clip from transcript (start/end time, title, media type, privacy)
• get_soundbite (GET) — Retrieve soundbite details including captions and sources
• list_soundbites (LIST) — List soundbites (filter by mine, team, transcript)

Channels

• list_channels (LIST) — Retrieve available channels for organizing transcripts

12 actions total covering the full Fireflies API—reads and writes.

Step-by-Step: Automating Meeting Sharing with Claude Code + Custom Fireflies MCP

Prerequisites

• Claude Code installed
• StackOne account with the Fireflies connector configured
• Fireflies API key connected as a linked account

Step 1: Configure Claude Code

Follow the StackOne Claude Code guide to connect your MCP server. First, set your auth token in your shell profile, then add the MCP server via CLI:

# Set auth token in ~/.zshrc or ~/.bashrc
export STACKONE_AUTH_TOKEN=$(echo -n "{your_stackone_api_key}:" | base64)

# Add MCP server
claude mcp add \
  --transport http \
  --header "Authorization: Basic $STACKONE_AUTH_TOKEN" \
  fireflies \
  "https://api.stackone.com/mcp?x-account-id={your_fireflies_account_id}"

# Verify connection
claude mcp list

Step 2: Review Meetings

Start Claude Code and give it the task:

Review all my Fireflies meetings since September.
Identify customer and prospect calls—exclude internal meetings.
Write them to a local markdown file with: title, transcript ID, date,
attendees, and category (CUSTOMER, PROSPECT, PARTNER, etc).
Write to file progressively as you go.

What Claude does:

1. Calls list_transcripts with fromDate filter, paginating in batches of 50
2. Filters out internal meetings (1:1s, stand-ups, all-hands)
3. Identifies external companies from attendee domains
4. Writes each batch to a markdown file

Why "write progressively"? Context windows have limits. By writing to a file as it goes, Claude doesn't need to hold 850 meetings in memory. If the session runs long, nothing is lost.

Step 3: Curate the List

Review the generated file. Remove anything you don't want to share:

• Sensitive partner negotiations
• Investor calls
• Incomplete recordings

In my case: 85 identified → 64 kept.

Step 4: Bulk Update Privacy

Read the curated meeting file. For each meeting,
set sharing to "Teammates and Participants".

Claude:

1. Parses the markdown file
2. Extracts transcript IDs
3. Calls set_transcript_privacy for each—running calls in parallel batches
4. Confirms completion

Step 5: Verify

Check Fireflies. Your team now has access to 64 customer calls they couldn't see before.

What the Custom Fireflies Connector Unlocks

With full API access via MCP, you can build workflows like:

• Auto-organize by deal stage → Move transcripts to channels based on CRM opportunity status
• Generate highlight reels → Create soundbites from AI-identified key moments
• Team onboarding → Auto-share relevant customer calls with new hires
• Competitive intelligence → Tag and surface calls mentioning specific competitors

Building Your Own Custom Connector with StackOne

The pattern here isn't Fireflies-specific. If you need an MCP server for a tool that doesn't have one—or the existing one doesn't cover your use case—the AI Connector Builder can generate it from API docs.

Time investment: ~10 minutes to create, instant deployment via StackOne CLI.

Output: A production MCP server exposing the actions you need.

Resources

• Falcon Connector Engine Introduction
• AI Connector Builder Guide
• Claude Code + StackOne MCP Setup
• Claude Code Documentation

Get Started

1. Sign up for free for StackOne
2. Build a connector with the AI Connector Builder (or use an existing one)
3. Connect it to Claude Code
4. Start automating