How to Use the Supabase Vector MCP in Vercel AI SDK

Q: Can I query table rows using Supabase Vector within ai-sdk?

Yep. You use querytablerows to fetch data from any specific table name. The result streams back, letting you show the user exactly what records are being retrieved in sequence.

Q: What is the best way to maintain transactional integrity with Supabase Vector using ai-sdk?

For atomic operations, stick to functions like callpostgresfunction. This allows your agent to wrap multiple database actions—like an insert and a vector match—into one reliable transaction visible on the frontend.

Q: Does ai-sdk support Supabase Vector for complex embeddings?

Absolutely. You can pass embedding arrays to matchvectors via your agent call. The result shows how well those vectors match data stored in Supabase, which you then stream into the user's viewport.

Q: If I need to delete old vector records, how does ai-sdk handle it?

You use deletetablerows for irreversible deletions. Since this is a destructive action, your agent should confirm the intent before running the command through the MCP Server.

Stream Supabase Vector Results Directly into Your UI with 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 Supabase Vector MCP to Vercel AI SDK

Create your Vinkius account to connect Supabase 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 Supabase Vector with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Live Vector Similarity Search

You can run complex vector searches instantly using `match_vectors`. Your agent calls this function, and the top K results stream back to your component in real time. This lets you build dynamic UI elements that populate as data arrives.

Fetch Specific Records by ID

Need one piece of data right away? Use `get_table_row` to fetch a single record matching a column value. Since the result streams, you get immediate feedback in your UI rather than waiting for a full database query cycle.

Manage Structured Data Inserts

Building a form? Use `insert_table_rows` to send an array of JSON objects directly into the Supabase table. Your agent handles this data submission, and you can immediately update your client state with confirmation that the records were written.

Setup guide

Set up Supabase 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 Supabase 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 Supabase 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 Supabase 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 Supabase 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 Supabase Vector MCP in Vercel AI SDK

The ai-sdk is built for real-time data. When your agent executes `match_vectors`, you won't wait for a final response; instead, the top K vector results stream directly into your UI component as they are found.

Yep. You use `query_table_rows` to fetch data from any specific table name. The result streams back, letting you show the user exactly what records are being retrieved in sequence.

For atomic operations, stick to functions like `call_postgres_function`. This allows your agent to wrap multiple database actions—like an insert and a vector match—into one reliable transaction visible on the frontend.

Absolutely. You can pass embedding arrays to `match_vectors` via your agent call. The result shows how well those vectors match data stored in Supabase, which you then stream into the user's viewport.

You use `delete_table_rows` for irreversible deletions. Since this is a destructive action, your agent should confirm the intent before running the command through the MCP Server.

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