Google Calendar MCP Server
Enables interaction with Google Calendar services through the Model Context Protocol using a Service Account. It allows MCP-compatible clients to manage calendar events and integrate calendar data via the Google Calendar API.
README
MCP server for Google Calendar
Credentials
The credentials.json file is needed to authenticate againts the Google services.
To generate the file, the following steps must be performed:
- Visit the Google Cloud Platform website
- Crete a new project (or use an existant one)
- Into the APIs & Services section, enable the Google Calendar API service
- Go to Credentials and generate a new credential as Service Account
- Copy the service account's email generated. It will be needed to share the calendar with it
- After the credential is created, a JSON file will be able to download. Place it into the root of this project and name it as
credentials.json
Calendar sharing
To interact with a calendar, it needs to be shared with the service account previously created to access it following these steps:
- Visit the Google Calendar website
- Into the sidebar, place on the target calendar, click the three dots (...) and then go to Settings and sharing
- Go the Shared with and add the email address for the service account copied previously when the credential was created
- Go to Integrate calendar and copy the Calendar ID value
Inspector
While developing, you can use the inspector to debug the server. To do this:
npm run inspector
Build MCP Server
Before adding the MCP server to the configuration file, you need to build it. The build process will create a Docker image that can be run in WSL.
npm run build
docker build -t mcpserver-googlecalendar .
Add MCP Server
To add the MCP server, add to the configuration file and paste the Calendar ID copied previously:
{
"mcpServers": {
"google-calendar": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOOGLE_CALENDAR_ID",
"mcpserver-googlecalendar"
],
"env": {
"GOOGLE_CALENDAR_ID": "[CALENDAR_ID_HERE]"
}
}
}
}
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。