What language and libraries are used?
The server is written in C++ and uses an internal `mcp-server.hpp` library along with nlohmann/json for JSON handling (as seen in the source code).
@168iroha
基本情報
C++によるMCP Serversのサンプル
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A sample implementation of MCP (Model Context Protocol) servers written in C++. It demonstrates the basic protocol flow using standard I/O and is intended as an educational example based on a blog article. It is not production-ready and will be removed in a few months.
Build and run the executable. The server communicates over standard I/O (stdin/stdout) using the MCP protocol. It listens for initialization and tool calls, and logs diagnostic messages to stderr.
evaluate-scores for score evaluationThe server is written in C++ and uses an internal `mcp-server.hpp` library along with nlohmann/json for JSON handling (as seen in the source code).
It uses standard I/O (binary mode on Windows) for MCP messages. All diagnostic output goes to stderr.
A single tool named `evaluate-scores` that accepts a numeric score (minimum 0) and returns a formatted evaluation (beginner, intermediate, or advanced).
No. It is a sample for learning purposes, and the repository will be deleted after the source code is published on the author’s blog.
A C++ compiler supporting `<chrono>`, `<format>`, and the MCP library provided in the repository. Only stdio transport is confirmed to work.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Model Context Protocol Servers
Open-source MCP to use Blender with any LLM
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
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
コメント