How to Use the Supabase Vector MCP in Mastra AI

Q: How does mastra-ai ensure Supabase Vector searches are reliable?

Mastra-ai handles reliability by wrapping the matchvectors call in a resilient step. If Postgres throws an error, it doesn't stop; it retries until success or hits max attempts.

Q: Can I use Supabase Vector for data validation within mastra-ai?

Yes. You can set up a conditional branch that calls gettablerow using the vector results to validate user input against existing records in your database.

Q: If I use Supabase Vector for deletions, how does mastra-ai guarantee safety?

You must wrap any destructive action like deletetablerows in a required tool approval step. Mastra-ai forces human oversight before executing irreversible commands.

Build Reliable, Self-Correcting Workflows with Supabase Vector and mastra-ai

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 Mastra AI

Create your Vinkius account to connect Supabase Vector to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Reliable Semantic Search Steps

The workflow can include a dedicated step for vector lookup using `match_vectors`. If the initial search fails, mastra-ai's built-in retry logic automatically re-runs the RPC call with exponential backoff. This keeps your entire process running smoothly.

Automate Data Record Retrieval

Need to validate data before proceeding? Use `get_table_row` within a conditional branch. If the row isn't found, the workflow can trigger an alternative path—say, notifying an admin instead of failing outright.

Manage Data Inserts in Multi-Step Flows

When multiple steps complete successfully, you use `insert_table_rows` to commit the final results. Mastra-ai ensures that this writing step only runs if all preceding logic and checks passed.

Setup guide

Set up Supabase Vector MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Supabase Vector tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "supabase-vector-mcp-client",
  servers: {
    "supabase-vector-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Supabase Vector Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Supabase Vector tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Supabase Vector transactions"
);
console.log(result.text);

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 Mastra AI

Mastra-ai handles reliability by wrapping the `match_vectors` call in a resilient step. If Postgres throws an error, it doesn't stop; it retries until success or hits max attempts.

Yes. You can set up a conditional branch that calls `get_table_row` using the vector results to validate user input against existing records in your database.

The framework automatically handles failure. Instead of failing the whole process, it can execute a dedicated 'failure' path—like logging the error or sending an alert email.

Since it manages state, yes. If you need to re-run a vector search on updated data, mastra-ai can manage the sequence of `match_vectors` calls and ensure idempotency.

You must wrap any destructive action like `delete_table_rows` in a required tool approval step. Mastra-ai forces human oversight before executing irreversible commands.

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