How to Use the Supabase Vector MCP in OpenAI Agents SDK

Q: How do I run a vector search with Supabase Vector and OpenAI Agents SDK?

Call the matchvectors tool. You'll provide the embedding array and specify the RPC function name. The agent handles the transaction, returning results validated for your production system.

Q: What happens if I use the Supabase Vector MCP Server with OpenAI Agents SDK?

The agents auto-discover all available tools, including querytablerows and deletetablerows. They'll execute based on your defined guardrails, making sure actions are safe before they hit the database.

Q: Can I delete rows using Supabase Vector and OpenAI Agents SDK?

Yes, the tool supports row deletion using deletetablerows. Remember this is irreversible, so always test it thoroughly in a non-production environment first.

Q: If data changes, how does Supabase Vector handle it with OpenAI Agents SDK?

You can use inserttablerows to update or create records. The agent manages this write flow, ensuring the database state matches your application's current logic.

Run structured vector search and database actions with your OpenAI Agents 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 OpenAI Agents SDK

Create your Vinkius account to connect Supabase Vector to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute semantic searches using `match_vectors`

The agent uses `match_vectors` to perform a similarity lookup across the Supabase Vector data. This means you don't just search keywords; you find records based on actual meaning. It handles embedding arrays and requires a valid RPC function name, keeping the process contained and auditable for your production system.

Manage table structure with `list_tables`

Need to know what data you're working with? Running `list_tables` lets the agent check every available schema in your Supabase project. This discovery step is key before any write operation. It’s a quick way to map out dependencies, ensuring that when your production agents run, they hit the right targets.

Insert and retrieve data with `insert_table_rows`

Use `insert_table_rows` to push new rows into a table using a JSON array. This is how you get fresh data—whether it's user feedback or newly generated embeddings. The agent can also pull specific records via `get_table_row`, letting your system confirm the exact row details before passing them downstream.

Setup guide

Set up Supabase Vector MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Supabase Vector tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Supabase Vector tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Supabase Vector tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Supabase Vector Agent",
            instructions="You have access to Supabase Vector tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Call the `match_vectors` tool. You'll provide the embedding array and specify the RPC function name. The agent handles the transaction, returning results validated for your production system.

The agents auto-discover all available tools, including `query_table_rows` and `delete_table_rows`. They'll execute based on your defined guardrails, making sure actions are safe before they hit the database.

Absolutely. The server supports standard relational operations and specialized vector search via `match_vectors`. This allows your agent to treat structured JSON data and high-dimensional vectors as one source of truth.

Yes, the tool supports row deletion using `delete_table_rows`. Remember this is irreversible, so always test it thoroughly in a non-production environment first.

You can use `insert_table_rows` to update or create records. The agent manages this write flow, ensuring the database state matches your application's current logic.

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