How to Use the Supabase Vector MCP in VS Code Copilot

Q: Can I verify schema details using Supabase Vector and VS Code Copilot?

Yes. Use listtables to see all available tables, then use gettablerow on a specific table name to check the column structure before writing code.

Q: What are the best practices for using Supabase Vector with VS Code Copilot?

For new features, write data first using inserttablerows. For testing, query existing data with querytablerows before committing to any deletions.

Standardize Supabase Vector operations across the team using VS Code Copilot Chat's integrated tools.

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 VS Code Copilot

Create your Vinkius account to connect Supabase Vector to VS Code Copilot — 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run production vector searches

The `match_vectors` tool performs a necessary semantic search via Postgres RPC. By committing this to your shared config, every developer on the team gets access to standardized vector searching. This means you don't have to remember complex connection strings; Copilot Chat handles calling the function with the required embedding array.

Inspect and query all data sources

`list_tables` shows everyone what tables are in the project, keeping team knowledge centralized. If you need to pull specific records, `get_table_row` lets developers grab a single row by matching a column value for immediate context. This consistency is huge when multiple people are working on data-driven features.

Manage data state reliably

`insert_table_rows` allows the team to write new records using JSON arrays, making feature rollout predictable. Conversely, `delete_table_rows` lets you remove rows based on a column value when required. Remember that Copilot Chat treats these actions as critical data writes against Supabase Vector.

Setup guide

Set up Supabase Vector MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Supabase Vector MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Supabase Vector tools listed. Try asking: "List my recent Supabase Vector transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

By committing the MCP configuration file, everyone gets automatic access to `match_vectors`. It ensures that every developer uses the same standardized function call.

Yes. Use `list_tables` to see all available tables, then use `get_table_row` on a specific table name to check the column structure before writing code.

For new features, write data first using `insert_table_rows`. For testing, query existing data with `query_table_rows` before committing to any deletions.

The server manages structured row objects and the underlying column values. Every tool, including vector functions, operates on these defined database types.

The risk is to the specific column values you use for matching. Since it’s irreversible, confirm your criteria before running this action.

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