🔍 GPT研究者MCPサーバー
👁 Webサイト
👁 ドキュメント
👁 Discord フォロー
GPT Researcher MCP を選ぶ理由
LLMアプリはMCPを使用してWeb検索ツールにアクセスできますが、 **GPT Researcher MCPは詳細な調査結果を提供します。**標準的な検索ツールは、手動でフィルタリングする必要がある生の検索結果を返すため、関連性のないソースが含まれることが多く、コンテキストウィンドウのスペースを無駄にしています。
GPT Researcherは、多数の情報源を自律的に探索・検証し、関連性が高く、信頼性が高く、最新の情報のみに焦点を当てます。標準的な検索よりも若干遅い(約30秒の待機時間)ものの、以下の機能を提供します。
✨ より質の高い情報
📊 コンテキストの使用を最適化
🔎 包括的な結果
🧠 LLMのためのより良い推論
Related MCP server: Crawl4AI+SearXNG MCP Server
💻 クロード デスクトップ デモ
https://github.com/user-attachments/assets/ef97eea5-a409-42b9-8f6d-b82ab16c52a8
リソース
research_resource: リサーチを通じて、特定のタスクに関連する Web リソースを取得します。
主なツール
deep_research: トピックに関するディープウェブリサーチを実行し、最も信頼性が高く関連性の高い情報を見つけます。quick_search:品質よりも速度を重視した高速ウェブ検索を実行し、スニペット付きの検索結果を返します。Tavily、Bing、Googleなど、GPTR対応のウェブリトリーバーをサポートしています。詳細はこちらをご覧ください。write_report: 調査結果に基づいてレポートを生成するget_research_sources: 研究で使用されたソースを取得するget_research_context: 研究の完全なコンテキストを取得する
プロンプト
research_query: リサーチクエリプロンプトを作成する
前提条件
MCP サーバーを実行する前に、次のものを用意してください。
Python 3.10以降がインストールされている
使用予定のサービスの API キー:
⚙️ インストール
GPT Researcher リポジトリをクローンします。
git clone https://github.com/assafelovic/gpt-researcher.git
cd gpt-researchergptr-mcp の依存関係をインストールします。
cd gptr-mcp
pip install -r requirements.txt環境変数を設定します。
.env.exampleファイルをコピーして、.env: GXP3 という名前の新しいファイルを作成します。.envファイルを編集し、APIキーを追加し、その他の設定を構成します: GXP4
GPT Researcher 構成に他の環境変数を追加することもできます。
🚀 MCP サーバーの実行
MCP サーバーは 2 つの方法で起動できます。
方法1: Pythonを直接使用する
python server.py方法 2: MCP CLI を使用する (インストールされている場合)
mcp run server.pyサーバーが実行される場合は、サーバーが接続を受け入れる準備ができていることを示す出力が表示されます。
クロードとの統合
以下の方法で MCP サーバーを Claude と統合できます。
Claude デスクトップ統合- Mac 上の Claude デスクトップ アプリケーションで使用する場合
詳細な手順については、上記のリンクを参照してください。
💻 クロード デスクトップ統合
ローカルで実行されている MCP サーバーを Claude for Mac と統合するには、次の操作を行う必要があります。
MCPサーバーがインストールされ、実行されていることを確認してください
Claude デスクトップを設定します。
~/Library/Application Support/Claude/claude_desktop_config.jsonで設定ファイルを探すか作成します。ローカルのGPT Researcher MCPサーバーを構成に追加する
設定を適用するにはClaudeを再起動してください
詳細な手順については、 Claude デスクトップ統合ガイドを参照してください。
📝 Claude の使用例
User: I'm considering investing in NVIDIA. Can you research the current state of the company, recent stock performance, latest product announcements, and analyst opinions?
Claude: I'll help you research NVIDIA for investment purposes. This will take a moment as I conduct comprehensive research to find the most up-to-date information about their stock performance, recent developments, and expert analysis.
[Claude uses conduct_research tool - this takes 30-40 seconds]
Claude: Based on my research, here's a comprehensive analysis of NVIDIA's current state:
## NVIDIA (NVDA) Current Status
### Recent Stock Performance
- Current price: $942.89 (as of my research)
- YTD performance: +90.4%
- 52-week range: $460.30 - $974.00
- Market cap: ~$2.32 trillion
### Recent Key Developments
1. **Blackwell AI Platform**: At GTC 2024, NVIDIA unveiled the Blackwell architecture, their next-generation AI chip platform promising 4x performance improvement over Hopper. Major cloud providers (AWS, Google, Microsoft) have already committed to integrating Blackwell.
2. **Q1 FY2025 Earnings (May 2024)**:
- Revenue: $26.0 billion (+262% YoY)
- Data Center revenue: $22.6 billion (+427% YoY)
- Gross margin: 78.4%
- Announced 10-for-1 stock split effective June 7, 2024
3. **Supply Chain Expansion**: Increased investments in manufacturing capacity with TSMC to address ongoing chip shortages for their high-demand AI GPUs.
### Analyst Consensus
- Strong Buy consensus with 37 analysts rating it "Buy," 5 "Hold," and 0 "Sell"
- Average price target: $1,042 (post-split adjusted: $104.20)
- Key bull thesis: Continued AI infrastructure spending and NVIDIA's dominant position in AI chips
- Key bear concerns: Valuation, potential competition from AMD, Intel, and custom silicon from tech giants
### Industry Position
- Dominant in AI GPU market with estimated 80-90% market share
- Expanding ecosystem through CUDA software platform and industry partnerships
- Diversifying beyond chips with DGX Cloud, AI software platforms, and automotive solutions🔧 トラブルシューティング
MCP サーバーの実行中に問題が発生した場合:
.envファイルにAPIキーが正しく設定されていることを確認してくださいPython 3.10以降を使用していることを確認してください
すべての依存関係が正しくインストールされていることを確認する
サーバーログでエラーメッセージを確認してください
👣 次のステップ
Claudeとの統合方法をより深く理解するために、 MCPプロトコルのドキュメントをご覧ください。
GPT Researcherのコア機能について学び、研究能力を高めましょう
詳細な設定オプションについては、高度な使用ガイドをご覧ください。
📄 ライセンス
このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細については LICENSE ファイルを参照してください。
📞 サポート / お問い合わせ
メールアドレス: assaf.elovic@gmail.com
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/assafelovic/gptr-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
