How to Use the Supabase Vector MCP in Cursor

Q: How can I integrate Supabase Vector searches into my Cursor workflow?

Just let the agent call matchvectors. You pass it the embedding array, and the live JSON result populates your code block. It's immediate context without leaving your editor.

Q: Does this MCP Server help manage Supabase Vector data structures in Cursor?

Yes. By using listtables and then gettablerow, you can let the agent map out the entire schema, making sure your code uses the correct table names for vector operations.

Q: If I need to validate data before writing code, what tools should I use with Supabase Vector in Cursor?

Run querytablerows first. This lets you review exactly what data the server returns for a given table name, giving your agent confidence before committing any code changes.

Inject live Supabase Vector data and run queries directly into your Cursor code with guaranteed accuracy.

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 Cursor

Create your Vinkius account to connect Supabase Vector to Cursor — 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute vector similarity searches

The `match_vectors` tool runs a semantic search via Postgres RPC. You give it an embedding array, and the live API response feeds back into your code context with relevant results. This means when your AI agent writes code, it's using real-world data derived from Supabase Vector searches—no mock stubs required.

Build dynamic database queries

`query_table_rows` lets the AI client pull specific rows from any table you name, and that data gets injected right into your file. You can also use `list_tables` to let the agent figure out which tables it needs to reference. This capability is key for building code that reacts instantly to live database content.

Insert or delete structured records

Need to write data back? Use `insert_table_rows` by providing a JSON array of objects, and the agent writes it directly into your codebase. Conversely, if you need clean-up, `delete_table_rows` removes rows based on column values. Be mindful: Both modifying tools execute actions against Supabase Vector.

Setup guide

Set up Supabase Vector MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Supabase Vector MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Supabase Vector transactions." If the MCP tools are loaded correctly, Cursor will call the Supabase Vector tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "supabase-vector-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Just let the agent call `match_vectors`. You pass it the embedding array, and the live JSON result populates your code block. It's immediate context without leaving your editor.

Yes. By using `list_tables` and then `get_table_row`, you can let the agent map out the entire schema, making sure your code uses the correct table names for vector operations.

Run `query_table_rows` first. This lets you review exactly what data the server returns for a given table name, giving your agent confidence before committing any code changes.

The server handles structured row objects and column values. When you run searches or inserts, the specific data types from those tables are accessed by your agent client.

It's dangerous because it’s irreversible. Never run this unless you've confirmed the exact column value and know for sure those rows need to be deleted from your project.

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