How to Use the Oracle Vector DB MCP in Vercel AI SDK

Q: Can I stream Oracle Vector DB search results through Vercel AI SDK streamText?

Yes, you can pass the vectorsearch tool directly into the tools parameter of streamText. The agent invokes the Oracle 23ai distance calculations and streams the resulting records to your React UI in real-time.

Q: What is the fastest way to verify Oracle Vector DB index types using Vercel AI SDK?

Run the listvectorindexes tool within your agent's system prompt to identify HNSW or IVF indexes. This lets the Vercel AI SDK structure its SQL queries to target the fastest index path.

Q: What is the best way to load MCP tools into my edge route?

Always call mcpClient.close() at the end of your Vercel edge execution block to release MCP Server connections. This clean closure prevents lingering SSE or HTTP connections between your serverless runtime and the gateway.

Stream native Oracle 23ai vector search results directly to your React components using the 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 Oracle Vector DB MCP to Vercel AI SDK

Create your Vinkius account to connect Oracle Vector DB 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 Oracle Vector DB with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time vector streams in Next.js

The `vector_search` tool executes native Oracle 23ai similarity searches and streams the raw Euclidean or cosine distance scores directly to your Vercel AI SDK frontend. Your Next.js app renders these database hits as they stream, bypassing the typical loading spinner. You configure this by passing the MCP client tools directly into `streamText`. This setup pulls matching high-dimensional data straight from your Oracle instance and feeds it to your UI components without intermediate API buffering.

Inspect Oracle schemas via Vercel AI SDK

The `describe_table` tool checks columns and explicit VECTOR data types directly from Edge Functions using this lightweight MCP Server. Your TypeScript client instantly knows the exact vector dimensions and column types without maintaining a massive local ORM schema. By coupling this tool with `list_tables` and `get_database_version`, your edge-deployed agents can dynamically discover database layouts. The Vercel AI SDK maps these database structures to UI forms, letting users query Oracle tables on the fly.

Safe query execution with row limits

The `execute_sql_query` tool runs raw SQL statements against your Oracle runtime via ORDS while protecting your edge runtime from payload overflows. Because Vercel AI SDK environments have strict memory limits, this tool forces a `FETCH FIRST 100 ROWS ONLY` constraint on every ad-hoc search. You track execution costs and row counts by running `table_stats` right before executing heavy queries. This sequence keeps your database connection pool stable and prevents large payloads from crashing your serverless edge functions.

Setup guide

Set up Oracle Vector DB 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 Oracle Vector DB 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 Oracle Vector DB 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 Oracle Database. 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 Oracle Vector DB 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 Oracle Vector DB MCP in Vercel AI SDK

You do not manage the Oracle pool in your Next.js code. The Vinkius MCP Server handles the database connection lifecycle, so your edge functions only need a single HTTP transport client to execute `vector_search` queries.

Yes, you can pass the `vector_search` tool directly into the tools parameter of `streamText`. The agent invokes the Oracle 23ai distance calculations and streams the resulting records to your React UI in real-time.

Run the `list_vector_indexes` tool within your agent's system prompt to identify HNSW or IVF indexes. This lets the Vercel AI SDK structure its SQL queries to target the fastest index path.

Always call `mcpClient.close()` at the end of your Vercel edge execution block to release MCP Server connections. This clean closure prevents lingering SSE or HTTP connections between your serverless runtime and the gateway.

Vinkius runs this server inside an isolated, ephemeral V8 sandbox. Your SQL queries, vector search inputs, and database schemas never persist on the host and transit solely over TLS-encrypted tunnels.

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