Supabase MCP Server

by ninad7007
MIT License

Integrations

  • Uses .env files for securely managing Supabase credentials and configuration settings for the MCP server.

  • Supports containerized deployment with Docker and Docker Compose, allowing for easy setup, management and troubleshooting of the MCP server environment.

  • Utilizes Pydantic for type-safe request/response handling, ensuring data validation and consistent interactions with the Supabase database.

Supabase MCP Server

A Model Context Protocol (MCP) server that enables AI tools to interact with Supabase databases. This server provides tools for reading, creating, updating, and deleting records in Supabase tables.

Features

  • Read rows from any Supabase table with filtering and column selection
  • Create single or multiple records in tables
  • Update records based on filter conditions
  • Delete records based on filter conditions
  • Comprehensive tool descriptions for AI model understanding
  • Type-safe request/response handling with Pydantic
  • Docker support for easy deployment

Prerequisites

  • Python 3.9+
  • Docker and Docker Compose
  • Supabase project with service role key
  • FastMCP-compatible AI IDE

Installation

  1. Clone the repository:
git clone https://github.com/yourusername/supabase-mcp.git cd supabase-mcp
  1. Create a .env file with your Supabase credentials:
cp .env.example .env # Edit .env with your Supabase credentials: # SUPABASE_URL=your-project-url # SUPABASE_KEY=your-service-role-key
  1. Build and start the container:
# Build and start in detached mode docker-compose up --build -d # To view logs docker-compose logs -f # To stop the container docker-compose down

The server will be available at http://localhost:8000.

Docker Management Commands

# Start the container docker-compose up # Start in detached mode (background) docker-compose up -d # Stop the container docker-compose down # View logs docker-compose logs -f # Rebuild the container docker-compose up --build # Check container status docker-compose ps # Restart the container docker-compose restart

Troubleshooting Docker Issues

  1. If the container fails to start:
    # Check logs docker-compose logs -f # Check container status docker-compose ps # Remove and rebuild docker-compose down docker-compose up --build
  2. If you get port conflicts:
    # Stop any existing containers using port 8000 docker-compose down # Or modify the port in docker-compose.yml # ports: # - "8000:8000" # Change the first number to an available port
  3. If environment variables aren't loading:
    # Verify .env file exists and has correct values cat .env # Check environment variables in container docker-compose exec mcp-server env

Configuring MCP in Your AI IDE

General Configuration Steps

  1. Open your AI IDE's settings/preferences
  2. Navigate to the MCP or AI settings section
  3. Add a new MCP server with the following configuration:
{ "name": "Supabase MCP", "command": "docker-compose", "args": ["up"], "cwd": "/path/to/supabase-mcp" }

IDE-Specific Instructions

Cursor
  1. Open Settings (⌘, or Ctrl+,)
  2. Go to "AI" section
  3. Under "MCP Servers", click "Add Server"
  4. Use the configuration above
  5. Restart Cursor to apply changes
VS Code with AI Extensions
  1. Open Command Palette (⌘⇧P or Ctrl+Shift+P)
  2. Search for "MCP" or "AI Settings"
  3. Add new MCP server configuration
  4. Use the configuration above
  5. Reload VS Code window
JetBrains IDEs with AI Plugins
  1. Open Settings (⌘, or Ctrl+Alt+S)
  2. Navigate to "Tools" → "AI" → "MCP Servers"
  3. Click "+" to add new server
  4. Use the configuration above
  5. Restart IDE to apply changes

Verifying MCP Connection

  1. Check your IDE's status bar for MCP server status
  2. Look for a green indicator or "MCP Connected" message
  3. Try using AI features that require database access
  4. Check Docker logs for any connection issues:
    docker-compose logs -f

Usage

  1. Start the MCP server:
docker-compose up
  1. Configure your AI tool to use the MCP server:
{ "mcpServers": { "supabase": { "command": "docker-compose", "args": ["up"] } } }

Available Tools

read_rows

Read rows from a Supabase table with optional filtering and column selection.

Example usage:

{ "table_name": "users", "columns": ["id", "name"], "filters": { "age": { "gt": 18 } }, "limit": 10 }

create_records

Create one or more records in a Supabase table.

Example usage:

{ "table_name": "users", "records": [ { "name": "John", "age": 30 }, { "name": "Jane", "age": 25 } ] }

update_records

Update records in a Supabase table based on filter conditions.

Example usage:

{ "table_name": "users", "filters": { "status": "inactive" }, "updates": { "status": "active" } }

delete_records

Delete records from a Supabase table based on filter conditions.

Example usage:

{ "table_name": "users", "filters": { "id": 1 } }

Security Considerations

  • Always use the service role key in a secure environment
  • Never expose the service role key in client-side code
  • Use appropriate row-level security policies in Supabase
  • Consider implementing rate limiting for production use

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Commit your changes
  4. Push to the branch
  5. Create a Pull Request

License

MIT

-
security - not tested
A
license - permissive license
-
quality - not tested

A Model Context Protocol server that enables AI tools to interact with Supabase databases, providing tools for reading, creating, updating, and deleting records in Supabase tables.

  1. Features
    1. Prerequisites
      1. Installation
        1. Docker Management Commands
        2. Troubleshooting Docker Issues
      2. Configuring MCP in Your AI IDE
        1. General Configuration Steps
        2. IDE-Specific Instructions
        3. Verifying MCP Connection
      3. Usage
        1. Available Tools
          1. read_rows
          2. create_records
          3. update_records
          4. delete_records
        2. Security Considerations
          1. Contributing
            1. License

              Related MCP Servers

              • A
                security
                F
                license
                A
                quality
                A Model Context Protocol (MCP) server that provides programmatic access to the Supabase Management API. This server allows AI models and other clients to manage Supabase projects and organizations through a standardized interface.
                Last updated -
                8
                84
                27
                JavaScript
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server optimized for integrating Supabase with the Windsurf Editor, providing database interactions through natural language with enhanced error handling and response formatting.
                Last updated -
                2
                TypeScript
                MIT License
              • -
                security
                F
                license
                -
                quality
                A Model Context Protocol server that enables querying feature suggestions from a Supabase database, allowing AI tools like Cursor and Claude to access and display feature request data.
                Last updated -
                TypeScript
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that enables Claude and other LLMs to perform database operations and invoke Edge Functions within Supabase through natural language.
                Last updated -
                TypeScript
                MIT License

              View all related MCP servers

              ID: 909joay3vo