Summary MCP
Generates AI-powered daily and weekly productivity summaries by analyzing your Slack messages, Google Calendar events, and Gmail activity with automated scheduling and smart filtering.
README
Summary MCP
AI-powered daily and weekly productivity summaries from Slack, Calendar, and Gmail
An MCP (Model Context Protocol) server that provides comprehensive productivity summaries by analyzing your Slack messages, Calendar events, and Gmail activity.
🌟 Features
- 📅 Daily Summaries: Concise end-of-day wrap-ups with tomorrow's preview
- 📊 Weekly Summaries: Comprehensive 7-day productivity analysis
- ⚡ Quick Stats: Fast metrics without full summary generation
- 📈 Period Comparison: Compare productivity across different weeks
- 📁 File Management: List and retrieve past summaries
- 🤖 Automated Generation: Scheduled daily (Mon-Fri 8:30 AM) and weekly (Mon 9:00 AM) summaries
- 🚫 Smart Filtering: Automatically excludes personal conversations (sports, politics, entertainment)
🚀 Quick Start
Installation
- Clone and setup:
cd ~/shopify-projects
git clone <repo-url> summary-mcp
cd summary-mcp
npm install
- Configure Cursor MCP:
Add to
~/.cursor/mcp.json:
{
"mcpServers": {
"summary-mcp": {
"type": "stdio",
"command": "node",
"args": ["/Users/philipbloch/shopify-projects/summary-mcp/src/index.js"],
"env": {}
}
}
}
- Install Automation (optional):
./scripts/install-automation.sh
This sets up:
- Daily summaries: Monday-Friday at 8:30 AM PT
- Weekly summaries: Mondays at 9:00 AM PT
📖 Available Tools
1. generate_daily_summary
Generate a concise daily productivity summary.
Parameters:
date(optional): Date in YYYY-MM-DD format (default: today)output_format:html,markdown,both, orjsonsave_to_file: Whether to save to summaries folder (default: true)include_sections: Array of sections to include
Example:
Generate my daily summary and save to summaries folder
2. generate_weekly_summary
Generate a comprehensive weekly productivity summary.
Parameters:
days_back(optional): Number of days to analyze (default: 7)start_date/end_date(optional): Custom date rangeoutput_format:html,markdown,both, orjsonsave_to_file: Whether to save to summaries folder (default: true)
Example:
Generate my weekly summary for the last 7 days
3. get_quick_stats
Get quick productivity metrics without generating a full summary.
Parameters:
days_back(optional): Number of days to analyze (default: 7)start_date/end_date(optional): Custom date range
Example:
Show me quick stats for the past week
4. list_summaries
List previously generated summaries.
Parameters:
limit: Max results (default: 10)sort:newestoroldestformat: Filter byhtml,markdown, orall
5. get_summary
Retrieve a specific summary by filename or date range.
Parameters:
filename: Specific summary filestart_date/end_date: Find by date rangeformat: Returnhtml,markdown, orboth
6. compare_periods
Compare productivity between two time periods.
Parameters:
period1: { start_date, end_date }period2: { start_date, end_date }metrics: Array of metrics to compare
📁 Project Structure
summary-mcp/
├── src/
│ ├── index.js # MCP server entry point
│ ├── config.js # Configuration
│ ├── tools/
│ │ ├── index.js # Tool definitions
│ │ ├── handler.js # Tool routing
│ │ ├── generate-daily-summary.js
│ │ ├── generate-summary.js
│ │ ├── list-summaries.js
│ │ ├── get-summary.js
│ │ ├── quick-stats.js
│ │ └── compare-periods.js
│ ├── analyzers/
│ │ ├── slack-analyzer.js
│ │ ├── calendar-analyzer.js
│ │ └── gmail-analyzer.js
│ └── utils/
│ ├── date-utils.js
│ └── file-utils.js
├── scripts/
│ ├── generate-daily-summary.sh
│ ├── generate-weekly-summary.sh
│ ├── install-automation.sh
│ └── uninstall-automation.sh
├── summaries/ # Generated summaries
├── logs/ # Automation logs
├── com.philipbloch.dailysummary.plist
├── com.philipbloch.weeklysummary.plist
└── package.json
🤖 Automation
Schedules
- Daily Summary: Monday-Friday at 8:30 AM PT
- Weekly Summary: Mondays at 9:00 AM PT
Managing Automation
Install:
./scripts/install-automation.sh
Uninstall:
./scripts/uninstall-automation.sh
Check Status:
launchctl list | grep philipbloch
View Logs:
# Daily summary logs
tail -f logs/daily-summary-*.log
# Weekly summary logs
tail -f logs/weekly-summary-*.log
# LaunchD logs
tail -f logs/launchd-daily.out.log
tail -f logs/launchd-weekly.out.log
Manual Trigger
Daily Summary:
./scripts/generate-daily-summary.sh
Weekly Summary:
./scripts/generate-weekly-summary.sh
🛠️ Development
Running the Server
# Start the server
npm start
# Development mode with auto-reload
npm run dev
Testing
npm test
Debug Mode
Set DEBUG=true in your environment to enable detailed logging:
{
"mcpServers": {
"summary-mcp": {
"type": "stdio",
"command": "node",
"args": ["/Users/philipbloch/shopify-projects/summary-mcp/src/index.js"],
"env": {
"DEBUG": "true"
}
}
}
}
📊 Data Sources
The MCP server integrates with:
- Slack MCP: Messages, threads, reactions
- Google Calendar: Events, attendees, meeting duration
- Gmail: Emails, threads, important contacts
🚫 Content Filtering
By default, Summary MCP filters out personal conversations about sports, politics, and entertainment to keep your summaries focused on work.
- Enabled by default - Only work-related content in summaries
- Easily toggle - Set
CONTENT_FILTERING_ENABLED=falsein.envto disable - Customizable - Add your own keywords and topics to filter
See FILTERING.md for complete documentation.
🎨 Output Formats
Format Generation Rules
Daily & Weekly Summaries: Generate both .html and .md by default
- Can optionally generate JSON for programmatic access
- Default:
output_format: 'both'
Period Comparisons: Generate both .html and .md only (no JSON)
- Optimized for human-readable trend analysis
- Default:
output_format: 'both'
HTML
Professional, Shopify-branded styling with:
- Syntax highlighting
- Interactive sections
- Visual metrics
- Print-friendly layout
- Perfect for sharing and presentations
Markdown
Clean, portable text format:
- Easy to edit
- Version control friendly
- Great for notes and documentation
- Plain text searchable
JSON (Daily/Weekly only)
Structured data for:
- Programmatic access
- Custom processing
- Integration with other tools
- Not available for comparisons
🔒 Privacy
All data processing happens locally. The MCP server:
- ✅ Reads data from your connected services
- ✅ Processes summaries locally
- ✅ Saves to your local filesystem
- ❌ Never sends data to external services
- ❌ No cloud processing or storage
🐛 Troubleshooting
Automation not running?
- Check if jobs are loaded:
launchctl list | grep philipbloch
- Check logs:
tail -f logs/launchd-daily.err.log
tail -f logs/launchd-weekly.err.log
- Verify Cursor is running (required for automation)
Summaries not saving?
Ensure the summaries directory exists:
mkdir -p ~/shopify-projects/summary-mcp/summaries
MCP server not responding?
- Restart Cursor
- Check MCP config in
~/.cursor/mcp.json - Verify Node.js is installed:
node --version
📝 License
MIT
👤 Author
Philip Bloch philip.bloch@shopify.com
Need Help? Check the AUTOMATION.md for detailed automation setup and troubleshooting.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.