Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use R2R with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Equip your AI with direct access to your R2R engine. execute vector searches, run precise RAG queries, and manage your documents.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 6 capabilities

The complete R2R capability set.

These are the exact actions your AI can choose when you ask it to work with R2R.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through R2R.

  1. 01

    List collections

    Lists all document collections

  2. 02

    Rag query

    Executes a RAG (Retrieval-Augmented Generation) query

  3. 03

    Get document

    Retrieves details for a specific document

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through R2R.

  1. 04

    Get health

    Checks the health status of the R2R server

  2. 05

    List documents

    Lists all ingested documents in the R2R system

  3. 06

    Search

    Performs a vector search across ingested documents

Observed, not estimated

911ms average. Fast in production.

R2R is checked daily against the live service.

Daily averagePeak 1146ms
Aug 20Today
Fastest day
696ms
Slowest day
1146ms
14-day trend
Improving-10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of R2R, so you can see the experience inside your AI.

It does not authenticate your account with R2R. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

R2R Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_Psy9XiP4IhGY7SchHirciLtxL89aKlE6LAoJStd2/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  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.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "r2r-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Psy9XiP4IhGY7SchHirciLtxL89aKlE6LAoJStd2/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions R2R owners ask.

  • 01

    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.

  • 02

    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.

  • 03

    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.

  • 04

    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.

Explore

More in Friends

Suggestions