How to Use the R2R MCP in LlamaIndex

Q: Can LlamaIndex query specific R2R collections?

Yes, your agent can run listcollections to see what is available. It then filters its vector searches to target only the relevant collection IDs.

Q: How do I run a RAG pipeline using R2R and LlamaIndex?

Your agent uses the ragquery tool to get synthesized answers. This MCP tool bypasses manual chunking and lets the engine handle the heavy lifting.

Q: How do I handle document metadata lookups?

The agent calls getdocument with a specific ID. This returns the complete metadata schema, which your index can use for precise filtering.

Index your R2R search results directly into LlamaIndex vector stores to build memory-enriched RAG pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect R2R MCP to LlamaIndex

Create your Vinkius account to connect R2R to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup R2R with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build indexed knowledge bases with LlamaIndex

Turn API outputs into searchable data structures. When your LlamaIndex agent calls `search` using the MCP server, the raw vector results are immediately indexed back into your local memory store. This prevents hallucinations by grounding the agent in actual document context. You can also execute a `rag_query` to fetch pre-synthesized answers from your documents. This lets you combine live database retrievals with your agent's historical conversational context.

Document and collection discovery

Give your agent the ability to map out your entire knowledge base. This MCP capability lets your agent call `list_documents` to scan the active files and decide which ones require deeper analysis. Segmenting your data is straightforward. The agent can use `list_collections` to find specific data silos, then fetch detailed metadata for a single file using `get_document`.

Connection health checks

Avoid unexpected runtime failures in your indexing pipelines. Your pipeline can execute `get_health` to verify that the target vector database is fully operational before initiating any document ingest. This check runs in milliseconds. It ensures your agent doesn't waste LLM tokens attempting to query a disconnected or offline vector storage engine.

Setup guide

Set up R2R MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all R2R MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to R2R tools.",
)
response = await agent.run("List recent R2R data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by R2R. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect R2R now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about R2R MCP in LlamaIndex

You map the tools to an agent using the MCP tool spec. The agent calls `search` and writes the returned payloads directly into your local index.

Yes, your agent can run `list_collections` to see what is available. It then filters its vector searches to target only the relevant collection IDs.

Your agent uses the `rag_query` tool to get synthesized answers. This MCP tool bypasses manual chunking and lets the engine handle the heavy lifting.

The agent calls `get_document` with a specific ID. This returns the complete metadata schema, which your index can use for precise filtering.

Yes, all metadata and document indices are stored within your isolated environment. The MCP server uses point-to-point communication, ensuring no configuration details leak to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript