What runtime is required?
Bun v1.0.0 or higher.
@ykitaza
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-client-example": {
"command": "bun",
"args": [
"run",
"chat"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
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.
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.
Bun v1.0.0 or higher.
No. It includes its own MCP client and can also work with clients like Claude Desktop App, Cline, or Cursor via the server config.
A Gemini API key from Google Cloud Console, set in the `.env` file.
In `server-config.json` (command, args, timeout, etc.) and `.env` for the API key.
The server is launched as a child process using the command and arguments defined in `server-config.json` (local stdio-based communication).
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Hindsight: Agent Memory That Learns

Model Context Protocol Servers
Open-source MCP to use Blender with any LLM
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
评论