MCP Python Starter

Name: MCP Python Starter
Author: SamMorrowDrums

@SamMorrowDrums

リポジトリ

MCP Python Starter について

A starter MCP server in Python.

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

SamMorrowDrums

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-python-starter": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 Python Starter?

A feature-complete Model Context Protocol (MCP) server template written in Python using FastMCP. It demonstrates all major MCP features—tools, resources, templates, and prompts—with clean, Pythonic code, serving as a jumpstart for developers building their own MCP servers.

How to use MCP Python Starter?

Install prerequisites: Python 3.11+ and uv (recommended) or pip. Clone the repository, run uv sync (or pip install -e .), then start the server with uv run mcp-python-starter --stdio for local development or uv run mcp-python-starter --http --port 3000 for HTTP transport. VS Code integration via .vscode/mcp.json and DevContainers are included for seamless development.

Key features of MCP Python Starter

Tools with annotations and structured data
Dynamic tool loading at runtime
Resource templates for personalized responses
Progress updates for long-running tasks
LLM sampling via tool invocation
Code review prompt template with focus areas

Use cases of MCP Python Starter

Quickly prototyping and testing an MCP server locally
Learning how to implement tools, resources, and prompts with FastMCP
Building a custom MCP server for an AI‑powered IDE or chat client
Debugging server behavior using the MCP Inspector tool

FAQ from MCP Python Starter

What are the prerequisites for using MCP Python Starter?

You need Python 3.11 or later and either uv or pip installed on your system.

How do I run the server?

Use uv run mcp-python-starter --stdio for stdio transport (local development) or uv run mcp-python-starter --http --port 3000 for HTTP transport (remote/web deployment).

How can I debug the server?

Launch the MCP Inspector with npx @modelcontextprotocol/inspector -- uv run mcp-python-starter to test tools, resources, prompts, and view JSON‑RPC logs.