• GROUNDED
  • CONTEXTUAL
  • VERIFIED
  • CLEAN

How to run RAG queries with your AI client

Connect R2R to your AI client to turn your documents into a searchable knowledge base. Your agent uses this data to answer questions with real context.

Ask AI about this page

Short answer

How can I run RAG queries with my AI?

You use the rag_query tool to pull relevant text from your R2R data directly into your chat. Your agent then uses those snippets to answer your questions. You'll see how the retrieval works below.

The outcomes

What you get from RAG

RAG changes how your agent interacts with your data.

GROUNDED

Fact-based answers

The agent pulls specific text from your files. This keeps the response tied to your actual data.

CONTEXTUAL

Deep data awareness

Your agent understands the specifics of your documents. It treats your files as the primary source of truth.

VERIFIED

Human oversight

You can see the snippets the AI found. You decide if the answer is right based on the source text.

CLEAN

Focused context

The AI only grabs what it needs. This prevents the context window from getting cluttered with useless info.

The workflow

What your AI does when a query arrives.

The AI handles the search and synthesis steps automatically.

  1. Search data

    The agent looks through your R2R index to find information that matches your question.

    rag_query

  2. Retrieve context

    The tool pulls the most relevant text chunks from your uploaded documents.

    rag_query

  3. Synthesize answer

    Your AI client combines the retrieved text with your prompt to build a response.

    rag_query

  4. Deliver response

    The agent provides the final answer in your chat interface using the retrieved context.

    rag_query

Try it

Copy these to start.

Use these prompts to test the connection immediately.

Starting points

These are opening lines. Swap the bracketed text for your specific document names or topics.

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"
    }
  }
}
Copy into chat04

  • Using the R2R data, what does the [Project X] roadmap say about the Q3 release?

  • Summarize the main findings from the [User Feedback] documents.

  • Based on the [Technical Specs] in my files, how do I configure the API?

  • Find any mentions of [Budget Constraints] in the [Finance] folder.

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

Start here

Connect R2R once, then ask.

One link connects your data. Your login stays encrypted on our side, and you can start querying in any MCP-compatible client.

Connect R2R to your AI

FAQ

How RAG queries behave

  • 01

    Can the AI edit my files?

    No. The rag_query tool is for reading data only. It cannot change or delete your documents.

  • 02

    Does the AI read every file I have?

    No. It only retrieves the specific snippets needed to answer your current question.

  • 03

    Can I use this with Cursor or VS Code?

    Yes. Any MCP-compatible client works once you connect the R2R MCP through Vinkius.

  • 04

    What if the answer isn't in my data?

    The agent should tell you it can't find the info. It relies on the retrieved context to answer.

  • 05

    Can the AI delete my R2R index?

    No. This MCP does not have tools to delete or modify your data index.

  • More questions about R2R? See everything the R2R Connector can do

Connect R2R to Claude, Cursor, ChatGPT & more