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.

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.

What is the difference between RAG and Search?

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

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.

R2R MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: R2R
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect R2R through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="R2R Assistant",
            instructions=(
                "You help users interact with R2R. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from R2R"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About R2R MCP Server

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.

The OpenAI Agents SDK auto-discovers all 6 tools from R2R through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries R2R, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

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.

The R2R MCP Server exposes 6 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect R2R to OpenAI Agents SDK via MCP

Follow these steps to integrate the R2R MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from R2R

Why Use OpenAI Agents SDK with the R2R MCP Server

OpenAI Agents SDK provides unique advantages when paired with R2R through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

R2R + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the R2R MCP Server delivers measurable value.

Automated workflows: build agents that query R2R, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries R2R, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through R2R tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query R2R to resolve tickets, look up records, and update statuses without human intervention

R2R MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect R2R to OpenAI Agents SDK via MCP:

get_document

Retrieves details for a specific document

get_health

Checks the health status of the R2R server

list_collections

Lists all document collections

list_documents

Lists all ingested documents in the R2R system

rag_query

Executes a RAG (Retrieval-Augmented Generation) query

search

Performs a vector search across ingested documents

Example Prompts for R2R in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with R2R immediately.

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

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

"Verify the operational health of the R2R server."

Troubleshooting R2R MCP Server with OpenAI Agents SDK

Common issues when connecting R2R to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

R2R + OpenAI Agents SDK FAQ

Common questions about integrating R2R MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.