R2RをChatGPT、Claude、Geminiに接続

• 01 / 03コレクションの監査方法
• 02 / 03RAGの検索デバッグ方法
• 03 / 03RAGクエリを実行する

最速日

693ms

最遅日

1133ms

14日間の傾向

遅延傾向+28%

R2R 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_Psy9XiP4IhGY7SchHirciLtxL89aKlE6LAoJStd2/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 — R2R capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "r2r-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Psy9XiP4IhGY7SchHirciLtxL89aKlE6LAoJStd2/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？ R2R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エンジニア

  Postmanや外部スクリプトを使わずに、ローカルからベクトルインスタンスへのクエリを実行できます。

• 02

  データ管理者

  ドキュメントの取り込み状況を迅速に確認し、ターミナル内で直接メタデータを閲覧できます。

• 03

  バックエンド開発者

  エンジンの応答を監査し、意味的な検索制限の微調整を容易に行えます。

• 01

  What do I need to connect this MCP?

  You need your R2R Base URL and an Auth Key if your deployment requires authentication.

• 02

  Which AI clients can I use with this?

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

• 03

  How does the agent access my documents?

  The agent uses the search and rag_query capabilities to interact with your R2R vector database.

• 04

  Can I see what documents are in my system?

  Yes, you can use the list_documents capability to see all ingested files or get_document to see specific details.

• 05

  Is my data hosted by Vinkius?

  Vinkius hosts the MCP connection and manages the credentials, but the data remains in your R2R deployment.

• 06

  What URL should I use for the R2R API URL?

  If you are running R2R locally via Docker, it's typically http://localhost:7272. If you are using SciPhi Cloud or have it deployed on your own infrastructure, provide the exact public or private endpoint.

• 07

  Do I need an R2R API Key?

  It depends on your deployment. Open deployments for local testing may not require a key. Production deployments or SciPhi Cloud environments require you to provide the generated key.

• 08

  What is the difference between RAG and Search?

  The search capability issues a standard vector similarity match—it returns relevant raw snippets from your database. The rag_query capability asks the R2R server to perform the search and compute an intelligent answer wrapping those snippets using an LLM.

• 09

  Are document ingestions possible via chat?

  No. This integration is designed for observational toolsets (listing documents, inspecting states, querying the index). Heavy ingestions of PDFs or websites should be handled through scripts or the dashboard.

• 

  Typesense Vector Search AIコネクタ

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

  表示
• 

  Lucidworks Fusion (AI Search & Discovery) AIコネクタ

  Manage AI-powered search via Lucidworks Fusion — execute semantic queries, index documents, and monitor ML tra

  表示
• 

  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
• 

  Verba AIコネクタ

  Connect your Verba RAG platform to your AI agent. Search your documents, retrieve semantic answers, and manage

  表示

おすすめ

• 

  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
• 

  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
• 

  LlamaCloud (Managed RAG & Parsing) AIコネクタ

  Manage RAG pipelines and document parsing via LlamaCloud — orchestrate LlamaParse jobs and audit data ingestio

  表示
• 

  Mem AI (Knowledge Workspace) AIコネクタ

  Manage your knowledge base via Mem.ai — create notes, run AI semantic search, and organize collections.

  表示