Supabase MCP Installation Guide

Installation and configuration guide for the Supabase MCP Server, providing a complete process description from environment preparation to client integration

Database Developer tools #Supabase #MCP service #Python tool #Database management

rating : 2 points

downloads : 12

update time : 2025-04-28

What is the Supabase MCP Server?

The Supabase MCP Server is a middleware service that allows AI development tools like Cursor to directly interact with the Supabase database through the Model Context Protocol (MCP). It simplifies the process for AI tools to access the database without the need for complex API development.

How to use the Supabase MCP Server?

After installation, configure your Supabase project information, and then add the server configuration in supported AI clients (such as Cursor) to start using it.

Use cases

Suitable for development scenarios where AI tools need to directly query or operate on the database, especially projects using Supabase as the backend.

Main features

Seamless Supabase integrationConnect directly to your Supabase project without additional API development

Multi - client supportCompatible with AI tools such as Cursor, Windsurf, Cline, and Claude Desktop

Simple configurationQuickly set up through environment variables or configuration files

Multi - region supportSupports Supabase projects deployed in multiple AWS regions globally

Advantages and limitations

Advantages

Simplify the process for AI tools to access the database

Support multiple popular AI development tools

Simple configuration and easy to deploy

Open - source project with community support

Limitations

Currently only supports the Supabase database

Requires Python 3.12 or higher

Some advanced features require Supabase administrator privileges

How to use

Install the Supabase MCP Server

Install the server package using pipx or uv

Configure project information

Set environment variables such as Supabase project reference, database password, and region

Add the server in the AI client

Add the MCP server configuration in the settings of clients such as Cursor

Verify the connection

Check if the server status indicator in the client is green

Usage examples

Query the databaseDirectly query the Supabase database table in Cursor

Data insertionAdd new records to the database through AI tools

Data updateModify existing database records

Frequently Asked Questions

How to find my Supabase project reference (Project Ref)?

Why does my server connection fail?

Which Supabase regions are supported?

How to view server logs?

Related resources

Official GitHub repository

Source code and latest version

Supabase official documentation

Supabase usage guide

Supabase community discussion

Get help and share experiences

Cursor official website

AI code editor

🚀 Supabase MCP Server

This guide will assist you in installing and configuring the Supabase MCP Server step by step.

🚀 Quick Start

Prerequisites

Before you begin, make sure you have the following:

Python 3.12 or a higher version installed.
- You can check your Python version by running python --version.
Compatible MCP clients:
- Cursor (recommended)
- Windsurf
- Cline
- Claude Desktop

Installation

Method 1: Using pipx (Recommended)

pipx install supabase-mcp-server

Method 2: Using uv

uv pip install supabase-mcp-server

Configuration

Required Environment Variables

Required:

SUPABASE_PROJECT_REF: Your Supabase project ID.
SUPABASE_DB_PASSWORD: Your database password.
SUPABASE_REGION: The AWS region where your project is hosted.

Optional:

SUPABASE_ACCESS_TOKEN: A personal access token for API management.
SUPABASE_SERVICE_ROLE_KEY: The service role key for the Auth Admin SDK.

Global Configuration on Windows

Create the configuration directory:

mkdir -Force "$env:APPDATA\supabase-mcp"

Create and edit the .env file:

notepad "$env:APPDATA\supabase-mcp\.env"

Add the following configuration:

SUPABASE_PROJECT_REF=Your project ID
SUPABASE_DB_PASSWORD=Your database password
SUPABASE_REGION=us-east-1
SUPABASE_ACCESS_TOKEN=Your access token
SUPABASE_SERVICE_ROLE_KEY=Your service role key

Where to Get Your Project Details

Project Reference:
- Visit your Supabase project URL: https://supabase.com/dashboard/project/<project-ref>
- project-ref is the identifier in the URL.
Database Password:
- Set when creating the project.
- Or find it in Project Settings → Database.
Access Token:
- Generate it at https://supabase.com/dashboard/account/tokens.
Service Role Key:
- Find it in Project Settings → API → Project API keys.

Integration with Cursor

Open Cursor.
Go to Settings → Features → MCP Servers.
Add a new server configuration as follows:

Name: supabase
Type: command
Command: C:\Users\<usuario>\.local\bin\supabase-mcp-server.exe

To find the exact path of the executable file:

where.exe supabase-mcp-server

Verification

Step 1: Verify Installation

Open a terminal and run:

supabase-mcp-server

If there are no error messages, the installation is successful.

Step 2: Verify Configuration

Check that all environment variables are set correctly and ensure the server is running.

Troubleshooting

If the server fails to start, check the log file for more information.
Ensure all environment variables are configured correctly.
Confirm that you have the necessary system permissions.

Resources

Support

If you encounter issues during the installation process:

Check the server logs.
Ensure all environment variables are set correctly.
Confirm that you have the necessary system permissions.
Consult the GitHub issues section.

Featured MCP Services

Markdownify MCP

Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.

TypeScript

1.7K

5 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.

A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.

UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.

554

5 points

Figma Context MCP

Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.

Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.

The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.

Python

745

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご