Meetings MCP Server
Provides read-only access to Google Drive meeting transcripts and Google Calendar events, enabling AI assistants to search, analyze, and retrieve meeting insights.
README
Meetings MCP Server
A comprehensive Model Context Protocol (MCP) server that provides read-only access to Google Drive meeting transcripts and Google Calendar events. This server enables AI assistants to search through meeting documents, analyze transcripts, and access calendar information to provide intelligent meeting insights.
Features
šļø Google Drive Integration
- Search Meeting Transcripts: Full-text search across all meeting documents in a shared folder
- Get Meeting Content: Retrieve complete transcript content from Google Docs
- List Recent Meetings: Browse the most recently modified meeting documents
- Meeting Summaries: Generate basic summaries of meeting transcripts
š Google Calendar Integration
- Upcoming Meetings: View scheduled meetings with attendee counts and details
- Meeting Attendees: Get detailed attendee information for specific meetings
- Date Range Search: Find meetings within specific date ranges
- Historical Analysis: Access past meeting data for trend analysis
š Performance & Security
- Intelligent Caching: KV-based caching to minimize API calls and improve response times
- Read-Only Access: All operations use read-only Google API scopes for maximum security
- OAuth 2.0 Authentication: Secure authentication flow with Google OAuth
- Error Handling: Comprehensive error handling with user-friendly messages
Prerequisites
- Node.js 20 or higher
- Cloudflare Workers account
- Google Cloud Console project with API access
- Google Drive folder with meeting transcripts
- Google Calendar access
Setup
1. Clone the Repository
git clone https://github.com/your-username/google-services-mcp.git
cd google-services-mcp
npm install
2. Google Cloud Console Setup
- Go to Google Cloud Console
- Create a new project or select an existing one
- Enable the following APIs:
- Google Drive API
- Google Calendar API
- Google Docs API
- Create OAuth 2.0 credentials:
- Go to Credentials ā Create Credentials ā OAuth 2.0 Client ID
- Application type: Web application
- Authorized redirect URIs:
https://your-worker-domain.workers.dev/callback
3. Environment Configuration
Update wrangler.jsonc with your configuration:
{
"vars": {
"GOOGLE_CLIENT_ID": "your-google-client-id",
"GOOGLE_CLIENT_SECRET": "your-google-client-secret",
"COOKIE_ENCRYPTION_KEY": "your-32-byte-base64-key",
"GOOGLE_DRIVE_FOLDER_ID": "your-shared-folder-id",
"GOOGLE_CALENDAR_ID": "primary"
}
}
4. Get Your Google Drive Folder ID
- Open Google Drive in your browser
- Navigate to your shared meetings folder
- The folder ID is the last part of the URL:
https://drive.google.com/drive/folders/FOLDER_ID_HERE
5. Deploy to Cloudflare Workers
npm run deploy
Development
Local Development
npm run dev
The server will be available at http://localhost:8787
Type Checking
npm run type-check
Project Structure
src/
āāā index.ts # Main MCP server with all tools
āāā google-handler.ts # OAuth authentication handler
āāā utils.ts # Utility functions
āāā workers-oauth-utils.ts # OAuth helper functions
āāā services/
ā āāā google-drive.service.ts # Google Drive API wrapper
ā āāā google-calendar.service.ts # Google Calendar API wrapper
ā āāā cache.service.ts # KV caching utilities
āāā types/
āāā env.d.ts # Environment type definitions
Available MCP Tools
Drive Tools
search_meeting_transcripts
Search across all meeting documents in the configured folder.
Parameters:
query(string): Search query to find in meeting transcriptsfolderId(string, optional): Google Drive folder ID to search in
Example:
{
"query": "quarterly goals",
"folderId": "1A0n63cvNloB_h7c6SQpP0R8kzmZMOL9D"
}
get_meeting_transcript
Retrieve the full content of a specific meeting transcript.
Parameters:
fileId(string): Google Drive file ID of the meeting transcript
list_recent_meetings
List the most recently modified meeting documents.
Parameters:
folderId(string, optional): Google Drive folder IDlimit(number, optional): Number of recent meetings to return (default: 10)
Calendar Tools
get_upcoming_meetings
Get upcoming meetings with details and attendee counts.
Parameters:
daysAhead(number, optional): Number of days ahead to look for meetings (default: 7)calendarId(string, optional): Google Calendar ID
get_meeting_attendees
Get detailed attendee information for a specific meeting.
Parameters:
eventId(string): Google Calendar event IDcalendarId(string, optional): Google Calendar ID
search_meetings_by_date
Find meetings within a specific date range.
Parameters:
startDate(string): Start date (YYYY-MM-DD)endDate(string): End date (YYYY-MM-DD)calendarId(string, optional): Google Calendar ID
Usage with Claude Desktop
- Add the MCP server to your Claude Desktop configuration:
{
"mcpServers": {
"meetings": {
"command": "node",
"args": ["path/to/google-services-mcp"],
"env": {
"GOOGLE_CLIENT_ID": "your-client-id",
"GOOGLE_CLIENT_SECRET": "your-client-secret"
}
}
}
}
- Restart Claude Desktop
- The meeting tools will be available in your Claude conversations
API Rate Limits & Caching
The server implements intelligent caching to minimize API calls:
- File Lists: 5 minutes TTL
- File Content: 1 hour TTL
- Calendar Events: 5 minutes TTL
- File Metadata: 10 minutes TTL
Security Considerations
- All API operations use read-only scopes
- OAuth tokens are securely stored and encrypted
- No ability to modify documents or calendar events
- All API calls are logged for audit purposes
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
Deployment
Automatic Deployment
The project includes a GitHub Actions workflow that automatically deploys to Cloudflare Workers when you push to the main branch.
Required GitHub Secrets:
CLOUDFLARE_API_TOKEN: Your Cloudflare API tokenCLOUDFLARE_ACCOUNT_ID: Your Cloudflare account ID
Manual Deployment
npm run deploy
Troubleshooting
Common Issues
-
OAuth Redirect URI Mismatch
- Ensure your redirect URI in Google Cloud Console matches your worker domain
- Format:
https://your-worker.workers.dev/callback
-
Folder Not Found
- Verify your
GOOGLE_DRIVE_FOLDER_IDis correct - Ensure the service account has access to the folder
- Verify your
-
API Rate Limits
- The server implements caching to minimize API calls
- If you hit rate limits, increase cache TTL values
-
Authentication Issues
- Re-authenticate if you've changed OAuth scopes
- Check that all required APIs are enabled in Google Cloud Console
Debug Mode
For local development, you can enable debug logging by setting:
export DEBUG=google-services-mcp:*
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
For questions and support:
- Open an issue on GitHub
- Check the troubleshooting section
- Review the Google APIs documentation
Acknowledgments
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.