How to Use the R2R MCP in Vercel AI SDK
Connect the Vercel AI SDK to your R2R engine. Stream document retrieval and RAG results directly into your React or Next.js interface.
Works with every AI agent you already use
…and any MCP-compatible client
Connect R2R MCP to Vercel AI SDK
Create your Vinkius account to connect R2R to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.
Key Capabilities
Real-time RAG streaming in AI SDK
Feed your front-end components live data using `rag_query`. Your users stop watching spinners and start seeing citations appear as the AI generates them. Connect the MCP Server to your Edge functions to keep latency low. You get precise answers without waiting for the full document context to load.
Manage vector data via AI SDK tools
Call `list_documents` or `get_document` to inspect your knowledge base state in real time. You can build UI dashboards that show exactly what the AI sees when it answers a question. This gives your application direct visibility into the R2R ingestion pipeline. No more guessing what data is available for your agent to process.
Verify connectivity with R2R MCP Server
Ping your backend using `get_health` before your app starts a generation cycle. This prevents runtime errors by checking the state of your vector store before dispatching user queries. Use this tool to gate your AI responses. If the R2R MCP Server isn't ready, your UI handles the state gracefully instead of failing mid-stream.
Set up R2R MCP in Vercel AI SDK
Prerequisites
- Node.js 18+ and a TypeScript project
-
ai+@modelcontextprotocol/sdkpackages - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Run
npm install ai @modelcontextprotocol/sdkplus your preferred model provider (e.g.@ai-sdk/openai). - 2
Create the Streamable HTTP transport
Use
StreamableHTTPClientTransportwith your Vinkius endpoint URL. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. - 3
Discover and use tools
Call
mcpClient.tools()to auto-discover all R2R tools. Pass them directly togenerateText()orstreamText()— no manual schema definitions needed. - 4
Works with any model provider
Swap
openai("gpt-4o")for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.
import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
const transport = new StreamableHTTPClientTransport(
new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);
const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();
const { text } = await generateText({
model: openai("gpt-4o"),
tools,
prompt: "List recent R2R transactions",
});
console.log(text);
await mcpClient.close();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.
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 Vercel AI SDK
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the R2R MCP today
We host it, we monitor it, we maintain it. You just paste one token.
