mcp-server-client-demo
Model Context Protocol (MCP)は、開発者が大規模言語モデル（LLM）を使用してAIアプリケーションを構築するためのフレームワークです。外部データソースやツールとの接続を標準化することで、LLMと機能を簡単に統合できます。このリポジトリには、MCPサーバーとクライアントのデモコードが含まれています。
GitHubスター
18
ユーザー評価
未評価
お気に入り
0
閲覧数
21
フォーク
4
イシュー
0
Model Context Protocol (MCP)
The Model Context Protocol (MCP) is a powerful framework that enables developers to build AI applications with large language models (LLMs) by providing a standardized way to connect models with external data sources and tools.
MCP is nothing but a protocol to connect LLMs with external data sources and tools (functions).
MCP Server
This repository contains the code for setting up a demo MCP server. It contains:
- A stateless MCP server with streamable HTTP transport for scalable production deployment.
- Auto tool registry with
@mcp_tooldecorator. - Docker file to containerize the server.
- Server can be run locally or in docker and deployed to any cloud provider.
Setup
- Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
- Install dependencies
uv sync
MCP Client
This repository contains the code for setting up a demo MCP client with OpenAI SDK. Refer to the client for more details.
Note: For ease of understanding, both server and client are in the same repository, you can easily keep them in separate repositories / projects.