Opensearch VectorをChatGPT、Claude、Geminiに接続

• 01 / 03ベクトル検索を実行する
• 02 / 03k-NNインデックスの管理方法
• 03 / 03更新と削除の方法

最速日

751ms

最遅日

1525ms

14日間の傾向

遅延傾向+80%

OpenSearch 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_6R4dQ885yexHhsyH4M5e8fLiT1BjuMlzaUlJMumQ/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 — OpenSearch capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "opensearch-vector-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_6R4dQ885yexHhsyH4M5e8fLiT1BjuMlzaUlJMumQ/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？ OpenSearch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

  MLエンジニア

  Curlコマンドなどを記述することなく、本番環境の埋め込みデータに対して類似度クエリをテストできます。

• 02

  RAG開発者

  検索拡張生成（RAG）パイプラインのためのコンテキストドキュメントのインデックス作成と取得を効率化できます。

• 03

  データチーム

  Kibanaダッシュボードを使わずに、対話を通じてインデックスの状態やドキュメント数、ベクトル構成を確認できます。

• 01

  What is this MCP used for?

  This MCP allows your AI client to perform k-NN vector searches, manage k-NN indexes, and handle document upserts within an OpenSearch cluster.

• 02

  Which AI clients can I use with this?

  You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

• 03

  Can I create indexes with specific dimensions?

  Yes, you can instruct your agent to create new k-NN indexes with configurable dimensions such as 384, 768, or 1536.

• 04

  Does this work with existing OpenSearch clusters?

  Yes, you simply provide your existing host credentials to connect the MCP to your cluster.

• 05

  How do I perform similarity searches?

  You can ask your agent to execute a k-NN search by providing the index name and a dense float vector.

• 06

  What vector dimensions does it support?

  Any dimension supported by OpenSearch k-NN. Common values: 384 (MiniLM), 768 (BERT/all-mpnet), 1536 (OpenAI text-embedding-ada-002), 3072 (text-embedding-3-large). When creating an index, specify the exact dimension and the agent provisions the mapping automatically.

• 07

  Can I delete an entire index or just individual documents?

  Currently, the agent supports deleting individual documents by ID from an index. Full index deletion is not exposed through this integration to prevent accidental data loss. If you need to drop an index, use the OpenSearch Dashboards or direct API calls.

• 08

  Does this work with Amazon OpenSearch Service (managed)?

  Yes. Provide the Amazon OpenSearch Service endpoint as the host (e.g., https://search-xxx.us-east-1.es.amazonaws.com) along with the master username and password. The integration uses standard REST APIs that work identically on managed and self-hosted clusters.

• 

  Marqo AI (Vector Search & Embeddings) AIコネクタ

  Manage semantic search via Marqo — execute tensor queries, index JSON documents, and audit vector indices.

  表示
• 

  Typesense Vector Search AIコネクタ

  Automate vector similarity searches via Typesense — index documents, manage collections, and execute semantic

  表示
• 

  Elasticsearch Vector AIコネクタ

  Empower vector search via Elasticsearch — perform dense vector kNN searches, handle index mappings, and index

  表示
• 

  pgvector (Vector Database) AIコネクタ

  Run vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines — all direct

  表示

おすすめ

• 

  MyScale (SQL Vector Database API) AIコネクタ

  Manage MyScale vector databases via SQL — execute queries, perform vector searches, and manage indices directl

  表示
• 

  Redis Vector AIコネクタ

  Equip your AI to autonomously manage embeddings, run KNN similarity searches, and administrate vector indexes

  表示
• 

  Oracle Vector DB AIコネクタ

  Run vector similarity searches on Oracle 23ai — execute VECTOR_DISTANCE queries, inspect schemas, list vector

  表示
• 

  MongoDB Atlas Vector Search AIコネクタ

  Manage vector storage via MongoDB Atlas — perform similarity searches, query MQL documents, and audit collecti

  表示