How to Use the R2R MCP in LangChain

Q: What is the fastest way to verify the connection before starting a chain?

Call gethealth at the start of your script. This returns the server status and prevents your chain from failing mid-run due to an unreachable database.

Give your LangChain agents direct access to your R2R engine to run deep vector searches and multi-step RAG chains.

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 LangChain

Create your Vinkius account to connect R2R to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step knowledge retrieval in LangChain

Feed your LangChain chains with live vector data. Your agent can now run `search` across your documents to find raw context, then pipe that output directly into another node in your graph. This removes the need to write custom vector store adapters. If the raw search isn't enough, the agent can trigger a full `rag_query` to get a synthesized answer before deciding on the next step. You track the latency and token usage of every single tool call inside LangSmith.

Dynamic document context management

Stop guessing which documents your LangChain agent is reading. The agent can use `list_documents` to inspect the available files and track down specific metadata using `get_document` when a user asks for verification. You can group your files into logical boundaries. By executing `list_collections`, your chain gains the ability to restrict its searches to specific enterprise divisions or project folders on the fly.

Setup the R2R MCP Server in your chains

Integration takes just a few lines of Python. We use an MCP adapter to map the tools, allowing you to instantiate the client and pass the toolset directly into your agent constructor to get started. Before running your main execution loop, you can verify the connection. A quick call to `get_health` ensures your document engine is online and responding before your agent starts executing expensive runs.

Setup guide

Set up R2R MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes R2R tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "r2r-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent R2R transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You register the tools with your agent constructor. The agent will automatically call `get_document` or `list_documents` based on the user's prompt using an MCP client.

Yes, every tool invocation is tracked over the MCP protocol. You can view the exact latency and returned payloads of `search` or `rag_query` directly in your LangSmith dashboard.

Your chain can query collections dynamically. The agent uses `list_collections` to discover available groups and then targets its search queries accordingly.

Call `get_health` at the start of your script. This returns the server status and prevents your chain from failing mid-run due to an unreachable database.

Your files and vector chunks remain in your private database. The MCP server acts as a local bridge, meaning your raw document text never passes through third-party logging systems.

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