MCP サーバー/クライアントサンプル

@ykitaza

About MCP サーバー/クライアントサンプル

No overview available yet

#mcp #server #client #example

Basic information

Category

Other

Runtime

node

Transports

stdio

Publisher

ykitaza

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-client-example": {
      "command": "bun",
      "args": [
        "run",
        "chat"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP サーバー/クライアントサンプル?

MCP サーバー/クライアントサンプル is a minimal sample project that implements a Model Context Protocol (MCP) server and client. It provides a numeric comparison tool, a chat interface powered by Google Gemini, and demonstrates how to build and test MCP servers independently of specific hosted clients.

How to use MCP サーバー/クライアントサンプル?

Set up the project with Bun (v1.0.0+), run bun install, copy .env.example to .env, and add your Gemini API key. Create a server-config.json file with the absolute path to the server script, then start the chat CLI with bun run chat.

Key features of MCP サーバー/クライアントサンプル

Numeric comparison tool (e.g., 9.11 vs 9.9)
MCP server with tool registration and execution
MCP client with bidirectional communication
Config-based connection management (server-config.json)
Chat CLI using Google Gemini API
Error handling and retry logic

Use cases of MCP サーバー/クライアントサンプル

Learning MCP fundamentals through a minimal implementation
Testing MCP tool integration without paid APIs (free Gemini tier)
Demonstrating how to build a custom MCP server
Solving common AI comparison errors with a dedicated tool

FAQ from MCP サーバー/クライアントサンプル

What runtime is required?

Bun v1.0.0 or higher.

Does this sample depend on a specific MCP client?

No. It includes its own MCP client and can also work with clients like Claude Desktop App, Cline, or Cursor via the server config.

What do I need to run the chat CLI?

A Gemini API key from Google Cloud Console, set in the .env file.

Where are server settings stored?

In server-config.json (command, args, timeout, etc.) and .env for the API key.

What transport does the MCP server use?

The server is launched as a child process using the command and arguments defined in server-config.json (local stdio-based communication).

Comments

More Other MCP servers

Production-ready MCP integrations for AI applications

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Awesome Mcp Servers

A collection of MCP servers.

Servers

modelcontextprotocol

Model Context Protocol Servers

Codelf

A search tool helps dev to solve the naming things problem.

FastMCP v2 🚀

🚀 The fast, Pythonic way to build MCP servers and clients.