Supabase MCP Server R4b

🚀 Supabase MCP Server

A Model Context Protocol (MCP) server that enables AI assistants to interact with Supabase databases through standardized tools.

✨ Features

• Read rows from tables with filtering and column selection.
• Create single or multiple records.
• Update records using flexible filtering conditions.
• Securely delete records that meet specific criteria.
• Environment based on configuration.
• Support for standardized I/O transport.

📦 Installation

1. Clone the repository:

git clone <repository-url>
cd mcp

2. Create a virtual environment and install dependencies:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt

3. Set up environment variables: Create a .env file in the project root directory with the following content:

SUPABASE_URL=your_project_url
SUPABASE_SERVICE_KEY=your_service_role_key

💻 Usage Examples

Basic Usage

Run the MCP server:

python -m supabase_mcp.server

Advanced Usage

The following are the available tools and their usage examples:

read_rows

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

{
    "table": "users",
    "columns": ["id", "name", "email"],  # Optional
    "filters": {"is_active": true},      # Optional
    "limit": 10                          # Optional
}

create_records

Insert one or more records into a table.

{
    "table": "users",
    "records": {
        "name": "John Doe",
        "email": "john@example.com"
    }
    # Or multiple records:
    # "records": [
    #     {"name": "John", "email": "john@example.com"},
    #     {"name": "Jane", "email": "jane@example.com"}
    # ]
}

update_records

Update records that meet specific filtering conditions.

{
    "table": "users",
    "filters": {"id": 123},
    "data": {"status": "active"}
}

delete_records

Delete records that meet specific filtering conditions.

{
    "table": "users",
    # [Original code continues here]
}