calendar-mcp
MCP server that lets AI agents manage Google Calendar -- create events, check availability, and manage schedules.
README
calendar-mcp
MCP server that lets AI agents manage Google Calendar -- create events, check availability, and manage schedules.
Tools
| Tool | Description |
|---|---|
calendar_list_events |
List upcoming events from a calendar |
calendar_create_event |
Create a new event with attendees, reminders, location |
calendar_update_event |
Update an existing event |
calendar_delete_event |
Delete an event |
calendar_free_busy |
Check availability across multiple calendars |
calendar_find_slot |
Find the next available meeting slot |
Google Calendar API Setup
1. Create a Google Cloud project
- Go to Google Cloud Console
- Create a new project (or select an existing one)
- Enable the Google Calendar API:
- Navigate to APIs & Services > Library
- Search for "Google Calendar API" and click Enable
2. Create a Service Account
- Go to APIs & Services > Credentials
- Click Create Credentials > Service account
- Give it a name and click Done
- Click into the service account, go to the Keys tab
- Click Add Key > Create new key > JSON
- Save the downloaded JSON key file somewhere safe
3. Share your calendar with the service account
- Copy the service account email address (looks like
name@project.iam.gserviceaccount.com) - Open Google Calendar
- Go to Settings > Settings for my calendar > [Your Calendar]
- Under Share with specific people or groups, add the service account email
- Set the permission to Make changes to events (or See all event details for read-only)
4. Configure the environment
Set the path to your service account key file:
export GOOGLE_SERVICE_ACCOUNT_KEY=/path/to/your/service-account-key.json
Or create a .env file in the project root:
GOOGLE_SERVICE_ACCOUNT_KEY=/path/to/your/service-account-key.json
Installation
pip install -e .
Usage
As an MCP server
Add to your MCP client configuration:
{
"mcpServers": {
"calendar": {
"command": "calendar-mcp",
"env": {
"GOOGLE_SERVICE_ACCOUNT_KEY": "/path/to/key.json"
}
}
}
}
Run directly
calendar-mcp
Examples
List events for the next week:
"Show me my upcoming events for this week"
Create a meeting:
"Schedule a 1-hour meeting called 'Sprint Planning' tomorrow at 2pm with alice@example.com"
Find an open slot:
"Find a 30-minute slot for a meeting with Bob sometime this week during working hours"
Check availability:
"Is my calendar free next Tuesday afternoon?"
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。