mcp-server-and-client

xakoul/mcp-server-and-client

3.1

If you are the rightful owner of mcp-server-and-client and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This repository provides a Model Context Protocol (MCP) server and client implementation for managing user data and interacting with AI-powered tools and prompts.

MCP Server and Client

This repository provides a Model Context Protocol (MCP) server and client implementation for managing user data and interacting with AI-powered tools and prompts. The server exposes resources and tools for user management, while the client enables interactive querying and tool usage via a command-line interface. The project integrates with Google's Gemini API for generative AI capabilities.

Features

  • MCP server with user management (CRUD operations)
  • MCP client with interactive CLI for tools, resources, and prompts
  • Integration with Gemini AI for text generation and tool augmentation
  • Extensible resource and tool definitions

Getting Started

Prerequisites

  • Node.js (v18+ recommended)
  • npm

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/mcp-server-and-client.git
cd mcp-server-and-client

  2. Install dependencies:

    npm install

Gemini API Key Setup

  1. Visit Google AI Studio and sign in with your Google account.
  2. Generate a Gemini API key.
  3. Create a .env file in the root of the repository and add your API key: 
    GEMINI_API_KEY=your-gemini-api-key-here

Running the MCP Server

To build and start the MCP server:

npm run server:build
npm run server:dev

Running the MCP Client

To start the MCP client:

npm run client:dev

Development

  • The server code is in .
  • The client code is in .
  • User data is stored in .

Notes

  • The .env file contains sensitive information. Do not commit it to version control.

License

ISC