How to Use the Supabase Vector MCP in Cline

Q: How does Supabase Vector work with Cline for semantic search?

It uses the matchvectors tool via RPCs. You supply the necessary embedding array, and the MCP Server runs a vector similarity query against your Postgres database. Cline then shows you those results right in VS Code.

Q: Can I delete rows using Supabase Vector with Cline?

Yes, the deletetablerows action is available for this MCP Server. Just remember that deleting rows is irreversible; always check your data before running it through Cline.

Q: Does Supabase Vector support batch inserts when using Cline?

Absolutely. You use inserttablerows. This tool takes an entire JSON array of row objects and pushes them to your target table in one go, which is way faster than doing it record by record.

Q: How do I check the available tables with Supabase Vector using Cline?

You just call listtables. It's a basic command that tells you every table in your Supabase project. This is always the best first step before running any complex queries or inserts.

Execute Supabase Vector searches and database writes directly inside VS Code.

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 Cline

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Semantic Searches in Cline

Need to find related data? Use `match_vectors` to run vector similarity search via Postgres RPC. Just pass the function name and your embedding array, and it spits out the most relevant results. Cline handles this entire process right inside your editor. You don't have to copy-paste anything; just set up the call, and the agent fetches the top K matching records for you.

Manage Data Records in Cline

Writing data is simple. Use `insert_table_rows` when you've got a JSON array of new row objects ready to go. The MCP Server handles the batch insertion into your specified Supabase table. For single-record work, `get_table_row` lets you pull one specific record by matching a column value. It’s quick and direct.

View Database Structure with Cline

Start by knowing what tables you're dealing with. Run `list_tables` to get an immediate list of every table in your Supabase project. This gives you the context needed before writing any queries. Need more detail? Use `query_table_rows`, passing only the desired table name and optionally a select statement or limit count. It pulls clean data back into your VS Code workspace.

Setup guide

Set up Supabase Vector MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type supabase-vector-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest Supabase Vector refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "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 Cline

It uses the `match_vectors` tool via RPCs. You supply the necessary embedding array, and the MCP Server runs a vector similarity query against your Postgres database. Cline then shows you those results right in VS Code.

Yes, the `delete_table_rows` action is available for this MCP Server. Just remember that deleting rows is irreversible; always check your data before running it through Cline.

This server primarily manages structured relational and vector embeddings stored in standard database columns. The `delete_table_rows` action specifically touches the row data itself, based on a column value.

Absolutely. You use `insert_table_rows`. This tool takes an entire JSON array of row objects and pushes them to your target table in one go, which is way faster than doing it record by record.

You just call `list_tables`. It's a basic command that tells you every table in your Supabase project. This is always the best first step before running any complex queries or inserts.

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