How to Use the Redis Vector MCP in Vercel AI SDK

Q: How does Vercel AI SDK handle streaming responses from Redis Vector?

The SDK grabs the tool output from searchvectors and feeds it into streamText. This lets your UI render vector similarity results item-by-item rather than waiting for the entire database query to finish.

Run KNN searches on Redis Vector and stream raw vector matches straight to your user's screen with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Redis Vector MCP to Vercel AI SDK

Create your Vinkius account to connect Redis Vector to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Redis Vector with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Vector Search Streaming

Stop making users stare at loading spinners while your app runs similarity searches. Hook your Vercel AI SDK frontend directly to `search_vectors` to output KNN matches instantly. Your users watch raw vector data resolve into UI components as the model streams the response. Under the hood, the MCP client lets your agent query your Redis index and render the closest matches on the fly. The SDK handles the incoming float array stream without blocking the main edge thread.

Index Administration via Vercel AI SDK

Let your application build indexes on demand during runtime. By feeding `create_vector_index` directly into the Vercel AI SDK tool registry, your agent can spin up new Redis index spaces without manual backend deployments. The model reads index parameters from user input, executes the creation, and verifies the setup using `get_index_info`. It is completely hands-off database administration driven by chat prompts.

Immediate Embedding Writes and Deletes

Update your Redis database state in the middle of a chat session. Your agent can call `upsert_vector` to write fresh floats or `delete_vector` to clean up old documents based on user commands. Because this MCP server runs on Vinkius, your Vercel edge functions do not need to hold long-lived database connections. The client executes the write, updates the local UI state, and closes the connection cleanly.

Setup guide

Set up Redis Vector MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with 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 Redis Vector tools. Pass them directly to generateText() or streamText() — 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.

index.ts

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 Redis Vector transactions",
});

console.log(text);
await mcpClient.close();

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 Redis Vector. 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 Redis Vector 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 Redis Vector MCP in Vercel AI SDK

The SDK grabs the tool output from `search_vectors` and feeds it into streamText. This lets your UI render vector similarity results item-by-item rather than waiting for the entire database query to finish.

Yes. Vinkius hosts the server, so your edge runtime only needs to make a lightweight HTTP call. You do not need to bundle heavy Redis binary drivers into your Vercel deployment.

Always call mcpClient.close() inside your API route after generating text. This prevents connection leaks and ensures your Vinkius server allocation stays within limits.

Your model extracts the floats from the user conversation and passes them as a JSON array to `upsert_vector`. The SDK handles the serialization automatically before hitting the Redis database.

Your raw embeddings, float arrays, and Redis keys are fully isolated. Vinkius runs the server in an ephemeral, zero-trust V8 sandbox that never persists your vector payloads or database credentials.

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