MCP Server for Amazon Redshift

What is MCP Server for Amazon Redshift?

The MCP Server for Amazon Redshift is a Model Context Protocol (MCP) server that provides a standardized interface for AI models to interact with Amazon Redshift databases. It enables listing tables, retrieving schema information, and executing read-only SQL queries.

How to use MCP Server for Amazon Redshift?

Install Node.js 18+, clone the repository, run npm install and npm run build, then configure environment variables for Redshift connection and transport type. Run with npm start for production or npm run dev for development. The server exposes three tools: list_tables, get_tables_schema, and query.

Key features of MCP Server for Amazon Redshift

• List tables, views, and materialized views across multiple schemas
• Get detailed schema information for multiple tables in a single request
• Execute read-only SQL queries against Redshift
• Support for stdio and SSE (Server-Sent Events) transport
• Type-safe implementation in TypeScript

Use cases of MCP Server for Amazon Redshift

• AI‑powered data exploration without direct SQL access
• Schema discovery for analytics and reporting tools
• Read-only query execution for LLM‑driven data analysis
• Integrating Redshift data into MCP‑compatible assistants

FAQ from MCP Server for Amazon Redshift

What prerequisites are needed to run the server?

Node.js 18 or higher, access to a Redshift database, and properly configured environment variables for host, port, database, user, password, and schemas.

How are queries secured against accidental writes?

All queries are executed in read-only transactions, preventing any data modification.

What transports does the server support?

It supports both stdio (default) and SSE (Server-Sent Events). Set TRANSPORT_TYPE to sse and optionally configure a port.

Are there any known limitations?

The server is based on the PostgreSQL MCP server and may inherit its limitations. CORS is enabled for SSE transport and should be configured for production.

Where does the configuration data live?

Configuration is stored in a .env file in the root directory, which must contain Redshift connection details and server settings.