MCP Server
Provides tools for retrieving today's meetings and event information from Google Calendar.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Server
A TypeScript implementation of a Model Context Protocol (MCP) server, designed to evaluate MCP capabilities over/with RAG (Retrieval-Augmented Generation) approaches for Nutrimate and other AI applications.
Overview
This project explores the Model Context Protocol as an alternative to RAG systems, providing a standardized way for AI applications to access external data sources and tools. The server is built with TypeScript, Node.js and the MCP TypeScript SDK.
Related MCP server: calendar-mcp
Features
TypeScript-first: Built with full TypeScript support for better developer experience
MCP Protocol: Implements the Model Context Protocol via Anthropic's TypeScript SDK
Prerequisites
Node.js (v18 or higher)
npm or yarn
TypeScript knowledge (recommended)
Getting Started
Clone the repository:
git clone https://github.com/samrasugu/mcp-server.git cd mcp-serverInstall dependencies:
npm installDevelopment mode:
npm run devBuild the project:
npm run buildStart the production server:
npm run start
Environment Variables
Set the following environment variables (or configure them in your MCP file):
GOOGLE_PUBLIC_API_KEY: Your Google API keyGOOGLE_CALENDAR_ID: Your Google Calendar ID (e.g., your Gmail address)
You can set these in a .env file:
GOOGLE_PUBLIC_API_KEY=your-google-api-key
GOOGLE_CALENDAR_ID=your-calendar-idUsage
Get Today's Meetings
To print today's meetings directly in your terminal:
node src/index.js todayIntegrating with Cursor MCP & Chat Interaction
This project supports integration with Cursor MCP, enabling you to interact with your server via chat and automate workflows.
1. Configure MCP Server in Cursor
Open Cursor and go to the MCP panel.
Add a new MCP server with the following settings (example):
Name: [your name]'s Calendar
Command:
nodeArgs:
src/index.tsHost:
localhostPort:
3000Environment Variables: Set
GOOGLE_PUBLIC_API_KEYandGOOGLE_CALENDAR_IDas needed.
You can also create a .cursor/mcp.json file for quick setup.
The content of the .cursor/mcp.json file should be like this:
{
"servers": [
{
"name": "[your name]'s Calendar",
"command": "node",
"args": ["src/index.ts"],
"host": "localhost",
"port": 3000,
"env": {
"GOOGLE_PUBLIC_API_KEY": "your-google-api-key",
"GOOGLE_CALENDAR_ID": "your-calendar-id"
}
}
]
}2. Start the MCP Server
Run the server locally:
node src/index.tsOr use the MCP panel's built-in controls to start/stop the server.
3. Interact via Chat
Open the chat panel in Cursor.
Select your MCP server (e.g., "Sam's Calendar") from the chat source dropdown.
Ask questions like:
Do I have any meetings today?What is my next event?List all meetings for this week.
The server will respond with information from your Google Calendar.
4. Customization
You can extend the server to support more commands or integrate with other tools. Update src/index.ts and restart the server to apply changes.
Project Structure
mcp-server/
├── src/
│ └── index.ts # Main server implementation
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This fileDevelopment
This project is actively being developed as part of an evaluation comparing MCP to RAG systems. The implementation may evolve as the evaluation progresses.
Available Scripts
npm run dev- Start development server with hot reloadnpm run build- Build the TypeScript projectnpm run start- Start the production servernpm test- Run tests (to be implemented)
MCP vs RAG Evaluation
This server is being developed to evaluate the effectiveness of the Model Context Protocol compared to traditional RAG approaches for AI applications, particularly focusing on:
Performance: Response times and resource usage
Flexibility: Ease of adding new data sources and tools
Maintainability: Code organization and extensibility
Integration: How well it works with existing AI workflows
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted Google Calendar MCP server for AI agents. No self-hosting or Google Cloud setup.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
A MCP server that works with Google Calendar to manage event listing, reading, and updates.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseAqualityDmaintenanceA TypeScript MCP server that allows querying documents using LLMs with context from locally stored repositories and text files through a RAG (Retrieval-Augmented Generation) system.417MIT
- AlicenseAqualityBmaintenanceThis 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.2352 PyPI27AGPL 3.0
- AlicenseAqualityDmaintenanceA TypeScript-based MCP server that integrates with Swagger/OpenAPI specifications to expose API endpoints as tools for Large Language Models (LLMs), enabling natural language interaction with any OpenAPI-compliant API.49MIT
- AlicenseNot gradedqualityDmaintenanceA production-ready MCP server that lets AI assistants interact with your personal Google Calendar using the Google Calendar API and OAuth 2.0.79 npmMIT