MCP For Claude Marketplace
R2R

R2R MCP Connector for Claude

A+

Equip your AI with direct access to your R2R engine — execute vector searches, run precise RAG queries, and manage your documents.

6 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your R2R (Rag to Riches) deployment to an AI agent, bringing your RAG infrastructure inside your chat interface. By linking this server, the AI can query its own constructed knowledge base on demand.

What you can do

  • Vector Search — Perform semantic similarity queries across your document database to retrieve contextually relevant chunks of information.
  • Execute RAG Queries — Use the 'rag_query' endpoint to have the R2R server directly summarize information based on vector data.
  • Knowledge Management — Call the API to list ingested documents, read metadata attributes, and filter logical collections.
  • Instance Health Monitoring — Quickly ping the connection using health checks to verify your system is responsive.

How it works

  1. Enable the server integration.
  2. Provide your active R2R Base URL and Auth Key (if applicable).
  3. Trigger RAG requests natively within your supported chat interfaces.

Who is this for?

  • AI & ML Engineers — Query your vector instances locally without needing Postman or external scripts.
  • Data Custodians — Quickly verify document ingestions and browse metadata directly inside the terminal.
  • Backend Developers — Audit engine responses and fine-tune semantic retrieval limits easily.
ragvector-searchdocument-ingestionknowledge-managementsemantic-retrieval

6 tools expose this connector's capabilities to your AI agent.

search

Performs a vector search across ingested documents

rag_query

Executes a RAG (Retrieval-Augmented Generation) query

list_documents

Lists all ingested documents in the R2R system

get_document

Retrieves details for a specific document

get_health

Checks the health status of the R2R server

list_collections

Lists all document collections

See how to talk to your AI agent using R2R.

Perform a vector search for 'Company Holiday Policy 2026'.

Using the R2R server, I found 3 highly relevant snippets. The top hit from document `doc_7712a` states: 'In 2026, employees are granted 21 flexible floating days, bypassing old blackout windows.'

Query the RAG engine to summarize known advanced RAG chunking strategies.

I requested the summary directly from R2R via `rag_query`. The engine replied: 'Advanced strategies focus on semantic segmentation rather than standard character limits, utilizing markdown structure, sentence boundaries, and logical overlaps to retain context.'

Verify the operational health of the R2R server.

I executed the `get_health` probe. The R2R server replied with `status: ok` and is primed to accept vector operations.

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.

Related Connectors

DataStax Astra DB Vector

DataStax Astra DB Vector MCP

7 tools Official

Manage Astra DB collections, documents, and perform vector similarity searches via DataStax directly from your AI agent.

A+ View details →
MongoDB Atlas Vector Search

MongoDB Atlas Vector Search MCP

6 tools Official

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

A+ View details →
Cognita (RAG Framework)

Cognita (RAG Framework) MCP

7 tools Official

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

A+ View details →
Appwrite

Appwrite MCP

9 tools Official

Open-source backend-as-a-service — manage databases, storage, and users via AI.

A+ View details →