広告掲載
MCP.so
ログイン

MCP Python Starter

@SamMorrowDrums

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

SamMorrowDrums

MCP Python Starter について

A starter MCP server in Python.

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

MCP Python Starter 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 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

よくある質問

1

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.

2

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).

3

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.

4

What environment variables are needed?

Copy `.env.example` to `.env` and configure the required variables. No specific variables are detailed in the README.

5

What license does the project use?

The MCP Python Starter is released under the MIT License.

コメント

「開発者ツール」の他のコンテンツ

Final POS – Custom POS Builder

Final Commerce

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

1

LocalCan

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

82

JiCo for Jira & Confluence – PII-redacting MCP server with Human-in-the-Loop

drkv-com

JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval

広告掲載