What are the prerequisites to run the server?
Node.js 18 or higher, a Google account, and OAuth 2.0 credentials (client ID, client secret, and a refresh token) from the Google Cloud Console.
@ymello
Basic information
No overview available yet
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
It is an implementation of the Model Context Protocol (MCP) for Google Calendar that enables interaction with calendar events via CLI or Server-Sent Events (SSE). It is designed for developers and users who want to programmatically manage Google Calendar events through MCP-compatible clients.
Prerequisites: Node.js 18+, a Google account with Calendar API access, and OAuth 2.0 credentials from Google Cloud Console. Configure environment variables (GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_REFRESH_TOKEN, etc.) in a .env file, install dependencies (npm install), and build (npm run build). Run as an HTTP/SSE server (npm run start:http) or as a CLI stdio server (npm run start:stdio). Integrate with MCP clients like Claude Desktop by adding the server configuration to the client's config file.
Node.js 18 or higher, a Google account, and OAuth 2.0 credentials (client ID, client secret, and a refresh token) from the Google Cloud Console.
The README provides a JavaScript script (`getToken.js`) that starts a local HTTP server, generates an OAuth authorization URL, and after user consent prints the refresh token to the console.
Five tools: `list_events`, `create_event`, `update_event`, `delete_event`, and `find_free_time`. Each expects a JSON object with specific parameters (e.g., time range, event details).
Add a JSON entry to Claude's `claude_desktop_config.json` specifying the absolute path to the built `index.js`, the command `node`, and the required environment variables.
Two modes: HTTP/SSE (server listens on a port, default 3334) and CLI stdio (interactive command-line mode). The SSE endpoint is at `GET /sse` and message endpoint at `POST /messages`.

Fetch the full transcript of any YouTube video as clean text — no API key, no signup, no quota wall. Pass a YouTube URL (watch, youtu.be, shorts, embed) or a bare video ID and get the transcript back with title and metad

Spark Inventory’s MCP server lets Claude, ChatGPT and other AI agents work with your inventory. They can check stock, read Demand ESP forecasts (a model per SKU picked by backtest, with stockout correction and seasonalit

Run your dumpster rental business from AI: orders, dispatch, invoices and customers. You confirm every change.
WhatsMCP — WhatsApp for AI agents. Put an AI agent on a real WhatsApp number. Expose regular WhatsApp accounts to your LLM agents over JSON-RPC. A complete Model Context Protocol server that turns phone numbers into addr

Publish beautiful Markdown docs instantly from any AI agent. Zero-config remote MCP server — your LLM pastes Markdown, gets back a shareable page. Free, no signup needed.
Comments