
Google Calendar MCP Server
Enables natural language queries to Google Calendar API for checking appointments, availability, and events. Supports flexible time ranges, timezone handling, and both service account and OAuth authentication methods.
README
Google Calendar MCP Server
An MCP (Model Context Protocol) server that connects to Google Calendar API to answer natural language questions about appointments and events.
Features
- Natural Language Queries: Ask questions like "What's on my schedule today?" or "Do I have any meetings tomorrow?"
- Flexible Time Ranges: Query events for specific dates, date ranges, or upcoming periods
- Availability Checking: Check if specific time slots are free or conflicted
- Timezone Support: Handle different timezones for accurate scheduling
- Structured Responses: Get formatted, easy-to-read calendar information
Setup
1. Google Calendar API Setup
Option A: Service Account (Recommended - No OAuth redirects needed)
- Go to the Google Cloud Console
- Create a new project or select existing one
- Enable the Google Calendar API
- Go to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "Service Account"
- Create the service account and download the JSON key file
- Important: Share your Google Calendar with the service account email address (found in the JSON file as
client_email
)
Option B: OAuth 2.0 (Traditional method)
- Go to the Google Cloud Console
- Create a new project or select existing one
- Enable the Google Calendar API
- Create credentials (OAuth 2.0 client ID) for a desktop application
- Download the credentials JSON file
2. Configuration
For Service Account:
- Copy the service account JSON file to
service-account-key.json
, OR - Set as environment variable:
export GOOGLE_SERVICE_ACCOUNT_KEY='{"type": "service_account", ...}'
For OAuth 2.0:
- Copy the downloaded credentials file to
credentials.json
, OR - Set as environment variable:
export GOOGLE_CREDENTIALS_JSON='{"installed": {...}}'
3. Installation
Install required dependencies:
pip install google-auth google-auth-oauthlib google-api-python-client mcp python-dateutil pytz
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。