🚀 duyet-mcp-server
この実験的な MCP (Model Context Protocol) サーバーは、AIアシスタントがduyetに関する情報に接続して取得できるようにするものです。このサーバーを通じて、主に https://duyet.net で利用可能な情報をAIアシスタントが直接利用できるようになります。

🚀 クイックスタート
AIアシスタントでのMCPサーバーの設定を更新します。
一般的な設定方法
{
"mcpServers": {
"duyet-mcp-server": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.duyet.net/sse"
]
}
}
}
Claude Codeを使用する場合
claude mcp add --transport http duyet https://mcp.duyet.net/mcp
エンドポイント
- https://mcp.duyet.net/sse
- https://mcp.duyet.net/mcp
スクリーンショット

✨ 主な機能
このプロジェクトは、MCPの機能を探索するための 研究、デモ、実験プロジェクト です。リモートMCPサーバーの構築を学ぶための演習として機能し、多くの部分がLLMによって作成されています。
目的: AIアシスタントが、手動でウェブを閲覧することなく、duyetの仕事、プロジェクト、コンテンツに関する情報にアクセスして取得できるようにすることです。
📦 インストール
Cloudflare Workersへのデプロイ

これにより、MCPサーバーが次のようなURLにデプロイされます: duyet-mcp-server.<your-account>.workers.dev/sse
コマンドラインを使用したデプロイ
git clone https://github.com/duyet/duyet-mcp-server
cd duyet-mcp-server
npm install
npm run deploy
💻 使用例
MCPサーバーのカスタマイズ
src/index.ts
の init()
メソッド内で this.server.tool(...)
を使用して、独自の ツール をMCPサーバーに追加できます。
Cloudflare AI Playgroundへの接続
- https://playground.ai.cloudflare.com/ にアクセスします。
- デプロイしたMCPサーバーのURL (
duyet-mcp-server.<your-account>.workers.dev/sse
または duyet-mcp-server.<your-account>.workers.dev/mcp
) を入力します。
- これで、Playgroundから直接duyetの情報ツールを使用できます!
Claude Desktopからの接続
Anthropic's Quickstart に従い、Settings > Developer > Edit Config を開き、次の設定を更新します。
{
"mcpServers": {
"duyet-info": {
"command": "npx",
"args": [
"mcp-remote",
"https://duyet-mcp-server.<your-account>.workers.dev/sse"
]
}
}
}
これで、duyet-mcpの情報ツールが利用可能になります。
Claude Chatの会話例
Duyetについて学ぶ
User: Who is Duyet and what does he do?
Claude: [Automatically accesses duyet://about resource]
Duyet is a Data Engineer with 8 years of experience. He is confident in his knowledge of Data Engineering concepts, best practices and state-of-the-art data and Cloud technologies. You can check out his blog at https://blog.duyet.net, his CV at https://duyet.net/cv, and his projects at https://github.com/duyet.
User: What has he been writing about lately?
Claude: [Automatically accesses duyet://blog/posts/3 resource]
His latest blog posts include topics on data engineering, cloud technologies, and distributed systems. Would you like me to show you more details about any specific post?
User: What's he working on currently?
Claude: [Automatically accesses duyet://github-activity resource]
Based on his recent GitHub activity, Duyet has been working on MCP server implementations, data pipeline projects, and contributing to open source tools for data engineering.
採用とコラボレーション
User: I'm looking to hire a data engineer. Can you help me contact Duyet?
Claude: I can help you send a message to Duyet using the send_message tool. What type of opportunity is this?
User: It's a full-time position at our startup working with Kafka and Spark
Claude: [Uses send_message tool]
What would you like to say in your message to Duyet? I'll make sure to include that this is about a full-time position with Kafka and Spark technologies.
User: Hi Duyet, we're a Series A startup building real-time data platforms. We'd love to discuss a Senior Data Engineer role working with Kafka, Spark, and cloud infrastructure. Remote-friendly position with competitive equity.
Claude: [Executes send_message tool with the message]
Your message has been sent successfully! Here's your reference ID: abc-123-def for follow-up. Duyet can be reached directly at me@duyet.net, LinkedIn: https://linkedin.com/in/duyet, or GitHub: https://github.com/duyet.
技術的な調査
User: I want to understand Duyet's technical background before our interview
Claude: [Automatically accesses duyet://cv/detailed resource]
Based on Duyet's detailed CV, he has 8 years of experience in data engineering with expertise in Apache Spark, Kafka, cloud platforms, and distributed systems. His experience includes building scalable data pipelines and working with modern data stack technologies.
User: Can you show me some of his recent technical work?
Claude: [Automatically accesses duyet://github-activity resource]
His recent GitHub activity shows contributions to data engineering projects, MCP server implementations, and open source tools. He's been actively working on distributed systems and cloud-native data solutions.
User: What kind of content does he write about?
Claude: [Automatically accesses duyet://blog/posts/5 resource]
His technical blog covers topics like building scalable data pipelines, modern data engineering best practices, cloud technologies, and distributed systems architecture.
📚 ドキュメント
利用可能なリソースとツール
このMCPサーバーは、リソース(URIを介した読み取り専用のデータアクセス)と ツール(パラメータを持つ対話型の機能)の両方を提供します。リソースはClaude Chatによって自動的に検出され、自然な会話フローを可能にします。一方、ツールはユーザー入力を必要とするアクションに使用されます。
リソース
リソースは、URIベースのリクエストを通じて情報への読み取り専用アクセスを提供します。これらはClaude Chatによって自動的に検出可能です。
duyet://about
- 動的に計算された経験年数を含むDuyetに関する基本情報
duyet://cv/{format}
- フォーマットパラメータ付きの履歴書:
duyet://cv/summary
- 簡単な履歴書の概要
duyet://cv/detailed
- 詳細な履歴書情報
duyet://cv/json
- 構造化された履歴書データ(利用可能な場合)
duyet://blog/posts/{limit}
- Duyetの技術ブログの最新のブログ記事:
duyet://blog/posts/1
- 最新のブログ記事
duyet://blog/posts/5
- 最新の5つのブログ記事(制限: 1-10)
duyet://github-activity
- 最近のGitHubの貢献とアクティビティ
ツール
ツールは、入力パラメータと副作用を持つ対話型の機能を提供します。
send_message
- コラボレーション、仕事の機会、コンサルティング、または一般的な問い合わせのためにDuyetにメッセージを送信します。メッセージはフォローアップのための参照IDとともに保存されます。
get_cv
- 異なるフォーマット(概要、詳細、またはJSON形式)でDuyetの履歴書を取得します。
get_github_activity
- コミット、イシュー、プルリクエスト、リリース、およびその他の公開イベントを含むDuyetの最近のGitHubアクティビティを取得します。最大20件の最近のアクティビティを、オプションで詳細情報とともに表示します。
hire_me
- フルタイム、契約社員、コンサルティング、またはパートタイムのさまざまな役割でDuyetを雇うための情報を取得します。専門知識、経験、および次のステップが含まれます。
say_hi
- オプションの個人的なメッセージを付けてDuyetに友好的な挨拶を送ります。連絡先情報と接続リンクを取得します。
contact_analytics
- 連絡先の提出に関する分析レポートを生成します。要約統計、目的の内訳、日々の傾向、および最近のアクティビティパターンが含まれます。
自然な発見パターン
このMCPサーバーの設計の主な利点は、Claude Chatがリソースを通じて自然に情報を発見して参照できるため、会話がより流れるようになることです。
- 情報に関する質問 → 自動的なリソースアクセス
- "Who is Duyet?" →
duyet://about
- "What's his experience?" →
duyet://cv/detailed
- "What's he writing about?" →
duyet://blog/posts/3
- "What's he working on?" →
duyet://github-activity
- アクション要求 → 対話型ツール
- "I want to contact him" →
send_message
ツール
- "Can you send him a greeting?" →
say_hi
ツール
- "Get his resume" →
get_cv
ツール
- 段階的な開示
- 一般的な質問から始めます。
- 特定の領域に深く掘り下げます。
- 準備ができたらアクションを実行します。
アーキテクチャ
- フレームワーク: Cloudflare Workers上で動作するHono.js
- データベース: Drizzle ORMを使用したCloudflare D1
- テスト: 包括的なテストカバレッジを持つJest
- リンティング: コード品質のためのBiome
- 型安全性: 厳格な設定のTypeScript
🔧 技術詳細
このMCPサーバーは、Cloudflare Workers上でHono.jsフレームワークを使用して構築されています。データベースにはCloudflare D1とDrizzle ORMが使用されており、テストにはJest、リンティングにはBiome、型安全性にはTypeScriptが使用されています。
📄 ライセンス
このプロジェクトはMITライセンスの下で公開されています。詳細は LICENSE
ファイルを参照してください。