Vinkius
Supabase Vector logo
Vinkius
Vinkius runs on Claude Code

How to Use the Supabase Vector MCP in Claude Code

Execute Supabase Vector searches and database management from the terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Supabase Vector MCP on Cursor AI Code Editor MCP Client Supabase Vector MCP on Claude Desktop App MCP Integration Supabase Vector MCP on OpenAI Agents SDK MCP Compatible Supabase Vector MCP on Visual Studio Code MCP Extension Client Supabase Vector MCP on GitHub Copilot AI Agent MCP Integration Supabase Vector MCP on Google Gemini AI MCP Integration Supabase Vector MCP on Lovable AI Development MCP Client Supabase Vector MCP on Mistral AI Agents MCP Compatible Supabase Vector MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on Claude Code

Connect Supabase Vector MCP to Claude Code

Create your Vinkius account to connect Supabase Vector to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Key Capabilities

Perform Semantic Searches via MCP Server

Need to find related data? Use `match_vectors` to run vector similarity search via Postgres RPC. You pass the required function name and your embedding array, and it outputs the top K matching records. This is perfect for CI/CD pipelines or cron jobs because you just pipe the output directly into other scripts. The MCP Server handles all the heavy lifting.

Manage Table Data in Claude Code

Getting data from a specific table? Use `query_table_rows`, giving it the table name and any select/limit parameters you need. It returns clean, actionable JSON output that your shell script can parse. Want to write new records? `insert_table_rows` accepts a JSON array of row objects, letting you push batches of data from your terminal commands.

Audit and Structure Data with Claude Code

Before making changes, list everything. Run `list_tables` to get an immediate manifest of all tables in the Supabase project. Know your scope first. If you need a single record for verification, use `get_table_row`, passing the table name and column value. It's fast and keeps your shell scripting tight.

Setup guide

Set up Supabase Vector MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see supabase-vector-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Supabase Vector transactions." It will automatically discover and invoke the available Supabase Vector tools.

Terminal
claude mcp add --transport http supabase-vector-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 Code

Run `match_vectors` from your terminal command line. You must provide the RPC function name and an embedding array as arguments. The output is machine-readable, making it perfect for automation.
It manages structured relational and vector embeddings stored in standard database columns. Any write action touches the row data; `delete_table_rows` is irreversible, so double-check your commands.
Start by calling `list_tables`. This tool instantly lists all available tables in the entire Supabase project. It's a critical step before any deployment or data manipulation.
Yes, use `insert_table_rows`. You feed it a JSON array of row objects, and the MCP Server handles the bulk insertion into your designated table. This is highly efficient for DevOps scripting.
The server touches structured relational and vector embeddings in standard columns. The specific data type affected by row deletion or retrieval is the column value, which must be provided for `get_table_row` and `delete_table_rows`.

Start using the Supabase Vector MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 7 tools

We've already built the connector for Supabase Vector. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 7 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.