広告掲載
MCP.so
ログイン

MCP Server POC

@TarcisioPhilips

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

TarcisioPhilips

MCP Server POC について

This project demonstrates how to create and use a Model Context Protocol (MCP) server that can provide custom tools and resources to AI assistants like Claude and others that support the MCP standard. The server includes: - Simple math operations (addition) - Dynamic greeting re

MCP Server POC の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-server-poc": {
      "command": "uv",
      "args": [
        "init"
      ]
    }
  }
}

MCP Server POC のツール

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。

概要

What is MCP Server POC?

A proof-of-concept implementation of a Model Context Protocol (MCP) server for AI assistant note-taking. It provides custom tools and resources to add, fetch, and summarize notes, and is designed for use with MCP-capable assistants like Claude and Cursor.

How to use MCP Server POC?

Install Python 3.11, clone the repo, set up a virtual environment, install dependencies, and run uv run mcp to start the server. For integration with Cursor, configure the absolute path to main.py in ~/.cursor/mcp.json.

Key features of MCP Server POC

  • add_note(note) tool: Appends a note to notes.txt
  • notes://latest resource: Retrieves the most recent note from the file
  • note_summary_prompt() prompt: Asks the AI to summarize all stored notes
  • All notes are persisted locally in a plain text file (notes.txt)
  • Uses stdio transport for communication with client applications

Use cases of MCP Server POC

  • Quickly capture and retrieve notes with an AI assistant
  • Prototype MCP server capabilities for note-management workflows
  • Experiment with custom tools, resources, and prompts in a local environment
  • Serve as a learning example for building MCP-based integrations

よくある質問

1

What tools and resources does the server provide?

It offers the `add_note` tool to append a note, the `notes://latest` resource to fetch the latest note, and the `note_summary_prompt` to request a summary of all notes.

2

Where are notes stored?

Notes are saved in a file named `notes.txt` in the project root directory. The file is created automatically if it does not exist.

3

What runtime environment is required?

Python 3.11 and the packages listed in `requirements.txt` (including the MCP SDK) are needed. Optionally, the `mcp[cli]` extras can be installed.

4

How do I integrate the server with Cursor IDE?

Create or edit `~/.cursor/mcp.json` (Windows: `C:\Users\<username>\.cursor\mcp.json`) with a JSON entry specifying the Python command and the absolute path to `main.py`, then restart Cursor.

5

What transport method does the server use?

The server uses stdio (standard input/output) as its transport mechanism, which means it communicates via command-line input/output streams.

コメント

「その他」の他のコンテンツ

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

FastMCP v2 🚀

jlowin

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

26.0K

Handl

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.

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

広告掲載