Google Calendar MCP Server
Enables natural language interaction with Google Calendar via the Model Context Protocol, allowing LLMs like Claude to read and manage calendar events through the Google Calendar v3 API.
README
🗓️ Google Calendar MCP Server
This project integrates the Google Calendar v3 APIs with a custom MCP (Model Context Protocol) Server, enabling natural language interaction with your calendar via tools like Claude Desktop.
It acts as a bridge between your calendar data and an LLM using MCP-compatible HTTP streaming.
🧠 Overview
This project contains two core servers:
1. 🔐 Google OAuth Server
- Handles OAuth 2.0 flow
- Stores and refreshes access tokens in a local session file
2. 🤖 MCP Server
- Implements the Model Context Protocol (MCP)
- Exposes an HTTP streaming interface
- Uses saved credentials to interact with Google Calendar API v3
🚀 Getting Started
Step 1: 🔧 Set Up Google API Credentials
- Go to the Google Cloud Console
- Create or select a project
- Enable the Google Calendar API
- Go to Credentials → Create OAuth 2.0 Client ID
- Choose Desktop App
- Set branding and add test user emails in audience
- Download the OAuth credentials as
client_secret.json - Place this file in the root directory of the project
Step 2: 📦 Install Dependencies
poetry install
Step 3: 🚪 Start the OAuth Server
poetry run uvicorn src.main:app --host 0.0.0.0 --port 8000
- This should automatically open a browser for OAuth authentication.
- If not, visit http://0.0.0.0:8000/google_oauth/
- Upon successful authentication, you'll see a success page.
- A
session.jsonfile will be created with your access/refresh tokens.

Step 4: 🧩 Run the MCP Server
poetry run python src/server.py
This launches a streamable MCP-compatible HTTP server at
http://localhost:8080/mcp
Step 5: 🧠 Connect MCP Client (Claude Desktop)
Update the config file at:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the following entry:
{
"mcpServers": {
"google-calendar-mcp": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8080/mcp"
]
}
}
}
Step 6: ✅ Verify Integration
- Open Claude Desktop settings.
- If the MCP server was added correctly, it will appear under Settings -> integrations

🧠 Demo
https://github.com/user-attachments/assets/27a8e5ee-8f2f-40c7-bdfc-1caa93767efb
🧱 Project Structure
project-root/
├── client_secret.json # Google OAuth credentials
├── session.json # Access/refresh token storage
├── pyproject.toml # Poetry project config
├── README.md
└── src/
├── main.py # FastAPI app for OAuth server
├── server.py # MCP-compatible server
├── settings.py # App settings and constants
├── api/
│ └── oauth_callback.py # OAuth endpoint logic
├── core/
│ ├── calendar_client.py # Google Calendar API wrapper
│ ├── mcp_tools.py # Tools exposed to MCP clients
│ ├── oauth_manager.py # OAuth initiation and flow
│ └── session_manager.py # Token handling
└── gcalendar_types/ # Typed definitions for Calendar v3 API
🧩 Dependencies
- FastAPI
- Uvicorn
- Google Auth Libraries
- Poetry for dependency management
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。