What authentication method does the server use?
It uses the Google OAuth 2.0 Desktop App flow. The server automatically stores and refreshes tokens after the first authorization.
@deciduus
基本情報
This project implements a Python-based MCP (Model Context Protocol) server that acts as an interface between Large Language Models (LLMs) and the Google Calendar API. It enables LLMs to perform calendar operations via natural language requests.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"calendar-mcp": {
"command": "python",
"args": [
"run_server.py"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A Python-based MCP (Model Context Protocol) server that acts as an interface between Large Language Models and the Google Calendar API. It enables LLMs to perform calendar operations via natural language requests. Secure OAuth 2.0 authentication is built in. For users who want to manage Google Calendar through AI assistants.
Requires Python 3.8+, Git, a Google Cloud project with the Calendar API enabled, and OAuth 2.0 Desktop app credentials. Set up a .env file with your Client ID, Client Secret, token file path, and optionally the callback port. Install dependencies with pip install -r requirements.txt. Run python run_server.py once for initial OAuth authentication; after that, the MCP client launches the server automatically. Configure your MCP client (e.g., Cursor/Claude Desktop) via an mcp.json entry that provides the full absolute path to run_server.py as the command argument.
It uses the Google OAuth 2.0 Desktop App flow. The server automatically stores and refreshes tokens after the first authorization.
After initial authentication, add a JSON entry to your client’s settings (e.g., `mcp.json`). Set `command` to the full path of your Python executable and `args` to the full absolute path of `run_server.py`. Credentials remain in the `.env` file, not in the client config.
Your Google Client ID and Client Secret are stored in the `.env` file in the project root. OAuth tokens are saved to the file specified by `TOKEN_FILE_PATH` (default `.gcp-saved-tokens.json`). Both files should be kept secure and are typically added to `.gitignore`.
By default, the server requests read/write access to the Calendar API (`https://www.googleapis.com/auth/calendar`). You can set `CALENDAR_SCOPES` to read-only if needed.
Yes. After the initial authentication, running `python run_server.py` starts a FastAPI server (e.g., on `http://localhost:8000`) that you can test with tools like `curl` or Postman. For routine use, the MCP client handles launching.
Find the AI tells in your prose. Deterministic, local, runs in CI. MCP server + CLI + Action.

Find wedding venues and suppliers, plan budgets and timelines, and manage wedding details, guests and events with your AI assistant. Public planning tools are free to use; private wedding tools use OAuth and changes requ
Local tools that let your AI use Mail, Calendar, Contacts, Teams, Slack, WhatsApp, OneDrive, Google Drive, Notion, Outlook and Office files on Mac and Windows. Runs on your computer.

Index your docs, help center, support tickets, wikis and code into one fast knowledge base. Connect Zendesk, Confluence, Notion, GitHub, Slack, Google Drive, Jira, Salesforce, websites, PDFs and 15+ more sources. Kapa sy

Multiplayer coding in the agentic era through an MCP server for real-time codebase sync between your agents.
コメント