How to Use the Supabase Vector MCP in Claude

Q: How do I perform advanced searches using Supabase Vector in Claude Desktop?

You invoke matchvectors. The server needs an RPC function name and your embedding array. Your agent handles the Postgres call, returning top-K results based on vector similarity.

Q: Can I check for data integrity when using Supabase Vector with Claude Desktop?

Yes. You can use gettablerow to pull specific records and then cross-reference that data against the search results from your vector queries, ensuring consistency before acting.

Q: Does this MCP Server help manage Supabase Vector embeddings in Claude Desktop?

Absolutely. The matchvectors tool is specifically designed to execute those semantic searches using pgvector's capabilities, making it easy for your AI client to interact with the vector data.

Run live Supabase Vector queries and manage data directly from your Claude Desktop session.

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 Claude Desktop

Create your Vinkius account to connect Supabase Vector to Claude Desktop — 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Perform semantic vector searches

Use `match_vectors` to run a similarity search across your database using pgvector. You just feed it an embedding array, and the server returns relevant results via a Postgres RPC call. It's perfect for when you need to find related data quickly without knowing exact keywords. This MCP Server makes running those vector searches simple, letting your AI client access that deep layer of semantic context.

Manage database structure

Need to know what tables exist? Call `list_tables` to get a full list of every table in the Supabase project. This gives your agent enough information to figure out where it needs to look next. Beyond just listing, you can use `get_table_row` if you already have a specific column value and need to pull a single record for review.

Read or write data records

`query_table_rows` lets your AI client read any row from a specified table, giving you control over which columns it selects. If you're done reading and need to update something, `insert_table_rows` handles dumping new JSON objects into the target table. Be careful with data modification though; remember that running `delete_table_rows` is irreversible. It takes a column value and wipes out the records matching it.

Setup guide

Set up Supabase Vector MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Supabase Vector MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Supabase Vector MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under supabase-vector-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 Claude Desktop

You invoke `match_vectors`. The server needs an RPC function name and your embedding array. Your agent handles the Postgres call, returning top-K results based on vector similarity.

Yes. You can use `get_table_row` to pull specific records and then cross-reference that data against the search results from your vector queries, ensuring consistency before acting.

Absolutely. The `match_vectors` tool is specifically designed to execute those semantic searches using pgvector's capabilities, making it easy for your AI client to interact with the vector data.

The server interacts with structured row data and associated text/numeric values within defined tables. It doesn't manage raw files, but it reads and writes specific column data types.

It's irreversible. Use this tool only after confirming exactly which records you want gone, as it deletes rows based on a column value without undo.

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