How to Use the Supabase Vector MCP in Windsurf

Q: What if I need to delete rows using Supabase Vector?

The deletetablerows tool handles this, but be careful—it's irreversible. You specify a column value, and it deletes all matching rows from the table immediately.

Run vector searches and full CRUD operations in Windsurf.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search with Supabase Vector

The `match_vectors` tool performs vector similarity searches using Postgres RPC. You give it an embedding array, and it returns the most relevant rows from your database. This capability lets your agent find connections in unstructured data—think finding documents based on meaning, not just keywords. Windsurf runs this search autonomously; you only set the goal.

Managing Data with the Supabase Vector MCP Server

Need to modify records? The `insert_table_rows` tool lets you dump JSON arrays directly into your tables. It's fast, and it gives your agent full control over writing new data. We also have read and write controls like `get_table_row` and `query_table_rows`. You can list all available tables first using `list_tables`, which is perfect for setting up multi-step workflows.

Advanced Postgres Functionality

The server supports calling any custom function via the `call_postgres_function` tool. This means if you've built a complex backend process, your agent can trigger it directly. This level of access lets you manage data integrity or run specialized calculations that standard queries don't cover. It’s what makes this MCP Server powerful for pipelines.

Setup guide

Set up Supabase Vector MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Supabase Vector MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Supabase Vector payment history." If connected, Cascade will call the Supabase Vector tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Supabase Vector uses pgvector extensions to keep your embeddings and relational data in one place. When you run a query, it runs the vector similarity search first, narrowing down results before hitting standard row checks. This keeps everything fast.

Yes, because the entire MCP Server lives within your single Supabase stack, it treats vectors and relational fields as one source of truth. It's designed to handle those linked operations without needing separate services.

No. When you set a goal—say, 'Find all customer records related to X concept'—Windsurf figures out the steps. It autonomously calls `match_vectors` and then uses `query_table_rows` to pull the final data.

The `delete_table_rows` tool handles this, but be careful—it's irreversible. You specify a column value, and it deletes all matching rows from the table immediately.

It touches general row objects across your defined tables. Specifically, for vector operations, it manages high-dimensional embedding arrays within those structured rows.

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