Meeting Chief Lite

Minimal meeting transcript sync and search MCP. Downloads meetings from Otter.ai, stores them in SQLite, and provides semantic search via MCP tools.

Features

• Otter.ai Sync: Download meeting transcripts automatically
• Semantic Search: Find relevant transcript chunks using embeddings
• Keyword Search: Fallback for exact text matching
• MCP Tools: 3 focused tools for Claude/Cursor integration

Tools

Quick Start

1. Configure Environment

cp .env.example .env
# Edit .env with your credentials:
# - OTTER_EMAIL
# - OTTER_PASSWORD
# - OPENROUTER_API_KEY

2. Run with Docker

# Build and run
docker compose up -d

# Or run directly
docker run -it \
  -e OTTER_EMAIL=your@email.com \
  -e OTTER_PASSWORD=yourpassword \
  -e OPENROUTER_API_KEY=sk-or-v1-xxx \
  -v meeting-chief-data:/data \
  ghcr.io/smcdonnell7/meeting-chief-lite

3. Configure MCP Client

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "meeting-chief-lite": {
      "command": "docker",
      "args": ["run", "-i", "--rm",
        "-e", "OTTER_EMAIL",
        "-e", "OTTER_PASSWORD", 
        "-e", "OPENROUTER_API_KEY",
        "-v", "meeting-chief-data:/data",
        "ghcr.io/smcdonnell7/meeting-chief-lite"
      ]
    }
  }
}

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "meeting-chief-lite": {
      "command": "docker",
      "args": ["run", "-i", "--rm",
        "-e", "OTTER_EMAIL=your@email.com",
        "-e", "OTTER_PASSWORD=yourpassword",
        "-e", "OPENROUTER_API_KEY=sk-or-v1-xxx",
        "-v", "meeting-chief-data:/data",
        "ghcr.io/smcdonnell7/meeting-chief-lite"
      ]
    }
  }
}

Usage Examples

# List recent meetings
meetings operation:list limit:10

# Get specific meeting
meetings operation:get id:meeting_123

# Search transcripts
search query:"API migration" mode:semantic

# Search with date filter
search query:"budget" after:2026-01-01

# Check system status
status operation:health

# Sync from Otter.ai
status operation:run_sync sync_days:30

# Generate embeddings for new meetings
status operation:generate_embeddings

Database

SQLite database with 7 tables:

• meetings - Meeting metadata and transcripts
• transcript_chunks - Parsed transcript segments
• transcript_vectors - Embeddings for semantic search
• embedding_jobs - Embedding generation queue
• sync_runs - Sync audit log
• speakers - People roster
• app_settings - Configuration

Development

# Install dependencies
npm install

# Build
npm run build

# Run locally
npm start

License

MIT