smithery-ai

Calendar MCP Server

Community smithery-ai
Updated

A Model Context Protocol server for Google Calendar integration

Calendar MCP Server

A Model Context Protocol (MCP) server for Google Calendar integration in Claude Desktop. This server enables AI assistants to manage Google Calendar events through natural language interactions.

smithery badgenpm versionLicense: ISC

Features

  • Create calendar events with title, time, description, and location
  • Retrieve event details by event ID
  • Update existing events (title, time, description, location)
  • Delete events
  • List events within a specified time range
  • Full integration with Google Calendar API
  • Secure OAuth2 authentication

Installation

Installing via Smithery

To install Google Calendar Integration for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gongrzhe/server-calendar-mcp --client claude

Manual Installation

npm install @gongrzhe/server-calendar-mcp

Setup

  1. Create a Google Cloud Project and obtain credentials:

    a. Create a Google Cloud Project:

    • Go to Google Cloud Console
    • Create a new project or select an existing one
    • Enable the Google Calendar API for your project

    b. Create OAuth 2.0 Credentials:

    • Go to "APIs & Services" > "Credentials"
    • Click "Create Credentials" > "OAuth client ID"
    • Choose "Desktop app" as application type
    • Give it a name and click "Create"
    • You will get your GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET

    c. Get Refresh Token:

    • Go to OAuth 2.0 Playground
    • Click the gear icon (Settings) in the top right
    • Check "Use your own OAuth credentials"
    • Enter your OAuth Client ID and Client Secret
    • In the left panel, find "Calendar API v3" and select "https://www.googleapis.com/auth/calendar"
    • Click "Authorize APIs" and complete the OAuth flow
    • Click "Exchange authorization code for tokens"
    • Copy the "Refresh token" - this is your GOOGLE_REFRESH_TOKEN
  2. Configure in Claude Desktop:

{
  "calendar": {
    "command": "npx",
    "args": [
      "@gongrzhe/server-calendar-mcp"
    ],
    "env": {
      "GOOGLE_CLIENT_ID": "your_client_id_here",
      "GOOGLE_CLIENT_SECRET": "your_client_secret_here",
      "GOOGLE_REFRESH_TOKEN": "your_refresh_token_here"
    }
  }
}

Usage Examples

The server provides several tools that can be used through the Claude Desktop:

Create Event

{
  "summary": "Team Meeting",
  "start": {
    "dateTime": "2024-01-20T10:00:00Z"
  },
  "end": {
    "dateTime": "2024-01-20T11:00:00Z"
  },
  "description": "Weekly team sync",
  "location": "Conference Room A"
}

List Events

{
  "timeMin": "2024-01-01T00:00:00Z",
  "timeMax": "2024-12-31T23:59:59Z",
  "maxResults": 10,
  "orderBy": "startTime"
}

Update Event

{
  "eventId": "event123",
  "summary": "Updated Meeting Title",
  "start": {
    "dateTime": "2024-01-20T11:00:00Z"
  },
  "end": {
    "dateTime": "2024-01-20T12:00:00Z"
  }
}

Delete Event

{
  "eventId": "event123"
}

Security Notes

  • Keep your Google API credentials secure
  • Regularly rotate your refresh tokens
  • Store sensitive information in Claude Desktop configuration
  • Never share or commit your credentials to version control
  • The refresh token gives access to your Google Calendar, treat it like a password

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the ISC License.

Author

gongrzhe

Support

If you encounter any issues or have questions, please file an issue on the GitHub repository.

MCP Server · Populars

MCP Server · New

    appwrite

    Appwrite MCP server

    Appwrite’s MCP server. Operating your backend has never been easier.

    Community appwrite
    pydantic

    Pydantic Validation

    Data validation using Python type hints

    Community pydantic
    arangodb

    Python-Arango

    The official ArangoDB Python driver.

    Community arangodb
    probelabs

    Probe

    Probe is an AI-friendly, fully local, semantic code search engine which which works with for large codebases. The final missing building block for next generation of AI coding tools.

    Community probelabs
    probelabs

    Docs MCP Server

    Turn any github repo to MCP server, and chat with code or docs

    Community probelabs