How to Use the R2R MCP in Mastra AI

Q: How do I search documents in R2R with Mastra AI?

You register the search tool to your Mastra agent. When the agent receives a prompt, it triggers a vector search and uses the output to continue the workflow.

Q: Can I use listcollections with R2R in Mastra AI?

You can. By calling listcollections, your agent can identify which data silos to search, making your workflows more dynamic and adaptable.

Build autonomous workflows in Mastra AI. Connect your R2R engine to handle complex document retrieval and multi-step agent logic.

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 Mastra AI

Create your Vinkius account to connect R2R to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute complex RAG with Mastra AI

Use `rag_query` inside your Mastra agents to pull context during a workflow. If the document isn't found, you can trigger a retry block immediately. This keeps your agents focused on the logic while the MCP Server handles the heavy lifting of vector retrieval. It's built for production-grade reliability.

Automated document management for Mastra AI

Call `list_documents` to audit your system state within a workflow branch. You can programmatically decide which collection to query based on previous step results. This removes the need for manual oversight. Your Mastra agents handle the entire lifecycle of document inspection and retrieval without human intervention.

Reliable health checks for R2R MCP Server

Integrate `get_health` as a prerequisite step in your Mastra workflow. If the server is down, the agent skips the RAG step and alerts your team instead of hanging. This ensures your agents are always talking to a responsive backend. It keeps your automation pipeline clean and predictable.

Setup guide

Set up R2R MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All R2R tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "r2r-mcp-client",
  servers: {
    "r2r-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "R2R Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to R2R tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent R2R transactions"
);
console.log(result.text);

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 Mastra AI

You register the `search` tool to your Mastra agent. When the agent receives a prompt, it triggers a vector search and uses the output to continue the workflow.

Security is handled at the transport layer. Your R2R data remains isolated, and only the specific document fragments needed for the agent task are accessed.

You can. By calling `list_collections`, your agent can identify which data silos to search, making your workflows more dynamic and adaptable.

Tool errors bubble up to your workflow catch blocks. You can define custom logic to handle failures from the R2R MCP Server, like logging the error or retrying.

Yes. You can require tool approval for the R2R MCP Server. This forces the agent to ask for permission before it reads a document or runs a query.

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