Haystack Deepset CloudをChatGPTとClaudeに接続

• 01 / 03インデックスの監査方法
• 02 / 03ワークスペースの管理方法
• 03 / 03RAGの精度をテストする方法

最速日

694ms

最遅日

1270ms

14日間の傾向

遅延傾向+54%

deepset Cloud Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_Tf2g8zLZroyDlliFU39whBZWkEDykSKQVz38t3zr/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — deepset Cloud capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "haystack-deepset-cloud-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Tf2g8zLZroyDlliFU39whBZWkEDykSKQVz38t3zr/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ deepset CloudをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  AI/ML チーム

  パイプライン構成の迅速な監査や、検索結果のテストを効率化できます。

• 02

  RAG 開発者

  エンタープライズの知識ベースをAIエージェントに統合し、文脈に沿った回答を実現します。

• 03

  プロダクトマネージャー

  検索パフォーマンスの監視や、ドキュメントのインデックス状態の確認が行えます。

• 01

  How do I connect this MCP to my deepset Cloud account?

  You just need to provide your deepset Cloud API URL and your API Key during the setup process on Vinkius.

• 02

  Which AI clients can I use with this MCP?

  You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

• 03

  Can I run actual searches through my AI agent?

  Yes, you can trigger both dense and sparse vector searches and run specific Haystack pipelines using natural language.

• 04

  Does this MCP host the data?

  No, this MCP connects to your existing deepset Cloud account where your data and pipelines are hosted.

• 05

  Can I manage multiple workspaces?

  Yes, the MCP includes capabilities to list and manage your isolated workspaces.

• 06

  Can I test my RAG pipelines directly via my AI agent?

  Yes. Use the run_pipeline capability to dispatch a query to any registered pipeline in your workspace. Your agent will return the response from the NLP topology, allowing you to verify retriever performance and LLM grounding without leaving your workspace.

• 07

  How can I audit my document indexing status?

  Ask your agent to list files in your workspace. You can then get specific metadata for any file to ensure embeddings and attributes are correctly attached. This is essential for debugging retrieval issues in production environments.

• 08

  Is it possible to manage multiple deepset Cloud workspaces?

  Absolutely. The agent provides high-level workspace listing, allowing you to navigate across tenant boundaries and isolation zones easily. You just need to provide the workspace name to any pipeline or search command.

• 

  Elastic Enterprise Search AIコネクタ

  Manage enterprise search via Elastic — search engines and documents, handle indexing, and monitor search analy

  表示
• 

  Cognita (RAG Framework) AIコネクタ

  Manage modular RAG via Cognita — list collections, ingest data sources, and perform AI-driven Q&A directly fro

  表示
• 

  Jina AI (Search Foundation & LLM Grounding) AIコネクタ

  Power your RAG and search via Jina AI — generate embeddings, rerank documents, read URLs, and perform semantic

  表示
• 

  LlamaIndex (AI Data Framework & RAG) AIコネクタ

  Query and manage RAG pipelines via LlamaIndex — execute natural language searches, audit indexed files, and mo

  表示

おすすめ

• 

  Mistral AI (Frontier LLMs & Embeddings) AIコネクタ

  Manage AI inference via Mistral — execute chat completions, generate RAG embeddings, and audit frontier models

  表示
• 

  Linkup (AI Search & RAG) AIコネクタ

  Power your AI agents with real-time web search via Linkup — execute semantic queries and extract RAG-ready con

  表示
• 

  Writer (AI Enterprise LLM) AIコネクタ

  Access Writer's enterprise-grade LLMs and Knowledge Graph capabilities to generate content, manage files, and

  表示
• 

  Azure AI Search AIコネクタ

  Execute RAG queries against Azure AI Search natively — search vectors, full-text documents, and audit cloud in

  表示