Redshift MCP Server

🚀 Amazon Redshift MCP Server

The Amazon Redshift MCP Server is a Python implementation of the Model Context Protocol that enables AI assistants to interact with Amazon Redshift databases. It provides tools and resources for seamless interaction with Redshift, allowing AI assistants to perform various database operations.

🚀 Quick Start

The Redshift MCP Server is a Python implementation of the Model Context Protocol, offering tools and resources for interacting with Amazon Redshift databases. It allows AI assistants to perform the following operations:

• List schemas and tables in the database
• Obtain DDL (Data Definition Language) scripts for tables
• Retrieve table statistics
• Execute SQL queries
• Analyze tables to collect statistics
• Get the execution plan for SQL queries

📦 Installation

Prerequisites

• Python 3.13 or higher
• An Amazon Redshift cluster
• Redshift credentials (host, port, username, password, database)

Install from Source Code

# Clone the repository
git clone https://github.com/Moonlight-CL/redshift-mcp-server.git
cd redshift-mcp-server

# Install dependencies
uv sync

🛠️ Configuration

The server requires the following environment variables to connect to your Redshift cluster:

RS_HOST=your-redshift-cluster.region.redshift.amazonaws.com
RS_PORT=5439
RS_USER=your_username
RS_PASSWORD=your_password
RS_DATABASE=your_database
RS_SCHEMA=your_schema  # Optional, default is "public"

You can set these environment variables directly or use a .env file.

💻 Usage Examples

Start the Server

# Start the server
uv run --with mcp python-dotenv redshift-connector mcp
mcp run src/redshift_mcp_server/server.py

Integrate with an AI Assistant

To use this server with an MCP-compatible AI assistant, add the following configuration to your MCP settings:

{
  "mcpServers": {
    "redshift": {
      "command": "uv",
      "args": ["--directory", "src/redshift_mcp_server", "run", "server.py"],
      "env": {
        "RS_HOST": "your-redshift-cluster.region.redshift.amazonaws.com",
        "RS_PORT": "5439",
        "RS_USER": "your_username",
        "RS_PASSWORD": "your_password",
        "RS_DATABASE": "your_database",
        "RS_SCHEMA": "your_schema"
      }
    }
  }
}

Basic Usage

Here are some basic usage examples:

List Schemas

access_mcp_resource("redshift-mcp-server", "rs:///schemas")

List Tables in a Schema

access_mcp_resource("redshift-mcp-server", "rs:///public/tables")

Get Table DDL

access_mcp_resource("redshift-mcp-server", "rs:///public/users/ddl")

Execute SQL

use_mcp_tool("redshift-mcp-server", "execute_sql", {"sql": "SELECT * FROM public.users LIMIT 10"})

Analyze a Table

use_mcp_tool("redshift-mcp-server", "analyze_table", {"schema": "public", "table": "users"})

Get Execution Plan

use_mcp_tool("redshift-mcp-server", "get_execution_plan", {"sql": "SELECT * FROM public.users LIMIT 10"})

✨ Features

Resources

The server provides the following resources:

• rs:///schemas - List all schemas in the database
• rs:///{schema}/tables - List all tables in a specific schema
• rs:///{schema}/{table}/ddl - Get the DDL script for a specific table
• rs:///{schema}/{table}/statistic - Get statistics for a specific table

Tools

The server provides the following tools:

• execute_sql - Execute SQL queries on the Redshift cluster
• analyze_table - Analyze a table to collect statistics
• get_execution_plan - Get the execution plan and runtime statistics for an SQL query

🔧 Technical Details

Project Structure

.
├── src/
│   └── redshift_mcp_server/
│       ├── server.py
│       └── [Other modules]
└── [Other files]

Dependencies

• uv - Implementation of the MCP protocol
• python-dotenv - Load environment variables
• redshift-connector - Redshift connector