MCP Server Redshift

🚀 MCP Server for Redshift

An implementation of the Model Context Protocol (MCP) server for Amazon Redshift, providing a standard interface for interacting with Redshift databases through AI models.

🚀 Quick Start

This is an MCP server implementation for Amazon Redshift, which offers a standard interface to interact with Redshift databases via AI models.

✨ Features

• List tables, views, and materialized views across multiple schemas.
• Retrieve detailed schema information for multiple tables.
• Execute read - only SQL queries against Redshift.
• Support stdio and SSE (Server - Sent Events) transports.
• Type - safe TypeScript implementation.

📦 Installation

Prerequisites

• Node.js 18 or higher.
• Access to a Redshift database.
• Environment variables configured (see the Configuration section).

Steps

1. Clone the repository:

   git clone https://github.com/yourusername/mcp-server-redshift.git
   cd mcp-server-redshift
   

2. Install dependencies:

   npm install
   

3. Build the project:

   npm run build
   

📚 Documentation

Configuration

Create a .env file in the root directory with the following variables:

# Redshift connection configuration
REDSHIFT_HOST=your-redshift-host
REDSHIFT_PORT=5439
REDSHIFT_DATABASE=your-database
REDSHIFT_USER=your-username
REDSHIFT_PASSWORD=your-password
REDSHIFT_SCHEMAS=public,schema1,schema2  # Comma-separated list of schemas

# Server configuration
TRANSPORT_TYPE=stdio  # or 'sse' to use Server-Sent Events
PORT=3000  # Only used when TRANSPORT_TYPE=sse

Usage

Run the server

# Development environment
npm run dev

# Production environment
npm run build
npm start

Available tools

1. List tables (list_tables)
   • List all tables, views, and materialized views in the specified schemas.
   • The optional schemas parameter is used to filter by specific schemas.

   {
     "schemas": ["public", "analytics"]
   }
   

2. Get table schemas (get_tables_schema)
   • Retrieve schema information for tables across multiple different schemas.

   {
     "tables": [
       { "schema": "public", "table": "users" },
       { "schema": "analytics", "table": "events" }
     ]
   }
   

3. Query (query)
   • Execute a read - only SQL query against the database.

   {
     "sql": "SELECT * FROM public.users LIMIT 5"
   }
   

Testing

Run the test suite:

npm test

Architecture

The project is organized as follows:

src/
├── config/         # Configuration and database settings
├── tools/          # Implementations of individual tools
├── server/         # Server settings and transport configuration
└── index.ts        # Entry file

Security Considerations

• All queries are executed within read - only transactions.
• Environment variables should be properly protected.
• CORS is enabled for SSE transport (needs to be configured in a production environment).
• Database credentials should be securely managed.

Contribution Guidelines

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add some feature').
4. Push to the branch (git push origin feature/amazing-feature).
5. Open a pull request.

📄 License

This project is released under the MIT License.

🙏 Acknowledgments

This project is based on the PostgreSQL MCP server. Thanks to the original authors.