google-calendar-mcp
A Model Context Protocol (MCP) server for Google Calendar integration with Claude Desktop. Create, update, delete, and manage calendar events with batch operations and enterprise-grade retry mechanisms.
README
Google Calendar MCP Server
A Model Context Protocol (MCP) server for Google Calendar integration with Claude Desktop. Create, update, delete, and manage calendar events with batch operations and enterprise-grade retry mechanisms.
🚀 Quick Start
1. Install
npm install -g github:wanthigh/google-calendar-mcp-server
2. Set up Google Calendar API
- Go to Google Cloud Console
- Create a new project or select existing one
- Enable Google Calendar API
- Create credentials:
- Go to "Credentials" → "Create Credentials" → "OAuth 2.0 Client IDs"
- Choose "Desktop application"
- Download the JSON file
3. Configure
Create a folder for your config files and save your credentials:
mkdir ~/.google-calendar-mcp
# Save your downloaded credentials.json to ~/.google-calendar-mcp/credentials.json
4. Add to Claude Desktop or Claude Code
For Claude Desktop
Edit your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"google-calendar": {
"command": "google-calendar-mcp",
"args": ["--credentials", "/Users/YOUR_USERNAME/.google-calendar-mcp/credentials.json"]
}
}
}
For Claude Code
Edit your Claude Code global config file:
All platforms: ~/.claude.json
{
"mcpServers": {
"google-calendar": {
"command": "google-calendar-mcp",
"args": ["--credentials", "/Users/YOUR_USERNAME/.google-calendar-mcp/credentials.json"]
}
}
}
Note: On Windows, replace /Users/YOUR_USERNAME/ with C:\Users\YOUR_USERNAME\
5. First Run
Restart Claude Desktop. The first time you use a calendar function, you'll be prompted to authorize access through your browser.
Note: If you need to manually authorize (rare), you can run:
google-calendar-mcp --credentials /Users/YOUR_USERNAME/.google-calendar-mcp/credentials.json
✨ Features
- Single Operations: Create, update, delete, list, and search events
- Batch Operations: Process multiple events efficiently
- Smart Retry: Automatic retry with exponential backoff for API failures
- Rate Limiting: Built-in protection against quota exhaustion
- Authentication: OAuth2 and Service Account support
🛠️ Available Tools
Basic Operations
create_event- Create a new calendar eventupdate_event- Update an existing eventdelete_event- Delete an eventlist_events- List events in a time rangesearch_events- Search events by keyword
Batch Operations
batch_create_events- Create multiple eventsbatch_update_events- Update multiple eventsbatch_delete_events- Delete multiple events
🔧 Example Usage in Claude
"Create a meeting tomorrow at 2pm called 'Team Sync'"
"List all my events for next week"
"Delete the event with ID abc123"
"Create 5 training sessions every Monday at 10am for the next month"
🐛 Troubleshooting
"Authentication failed"
- Check your credentials.json file path
- Complete the OAuth authorization in your browser
"Calendar not found"
- Make sure you're using the correct calendar ID
- For service accounts, share your calendar with the service account email
"Rate limit exceeded"
- The server has built-in retry mechanisms
- Reduce batch sizes if needed
📞 Support
📄 License
MIT License
Version: 1.0.1 | Author: @wanthigh
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。