Redshift

Provides a Python-based MCP server to query Redshift with natural language, exposing SQL tools and resource data.

python

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "deeparajareddy-redshift_mcp_server": {
      "command": "py",
      "args": [
        "redshift_mcp_server.py"
      ],
      "env": {
        "REDSHIFT_HOST": "localhost",
        "REDSHIFT_PORT": "5432",
        "REDSHIFT_USER": "postgres",
        "REDSHIFT_DATABASE": "postgres",
        "REDSHIFT_PASSWORD": "password"
      }
    }
  }
}

This MCP server lets you interact with Amazon Redshift using natural language through your MCP client. It exposes SQL tools to run queries, inspect schemas, and sample data, along with status and resource visibility to help you build AI-assisted data workflows.

How to use

You install and run the Redshift MCP Server locally, then connect your MCP client (such as Antigravity, Claude Code, or VS Code) to it. The server exposes SQL tools that your agent can call in natural language, for example to execute queries, list tables, describe schemas, and fetch sample data. You can also query the connection status and retrieve a list of available tables.

How to install

Prerequisites you need before starting are Python and a working network connection to your Redshift cluster. You should also have access to install Python packages.

Install dependencies using the following command:

pip install mcp redshift-connector pandas python-dotenv psycopg2-binary sqlalchemy

Configuration to run the MCP server locally

Use the following MCP client configuration to run the server locally and connect to your Redshift instance. This config runs the server as a Python process and provides the necessary environment variables to point to your Redshift database.

"redshift-mcp": {
  "command": "py",
  "args": ["redshift_mcp_server.py"],
  "cwd": "c:/Users/deepa/OneDrive/Desktop/workspace/redis connection",
  "env": {
    "REDSHIFT_HOST": "localhost",
    "REDSHIFT_PORT": "5432",
    "REDSHIFT_DATABASE": "postgres",
    "REDSHIFT_USER": "postgres",
    "REDSHIFT_PASSWORD": "password"
  }
}

Additional setup you may perform

Optionally seed sample data and run tests to verify the setup.

Seed sample data command (as shown in the example flow):

python seed_redshift.py

Test the local setup to ensure the MCP server can communicate with Redshift and return expected results.

python test_redshift_local.py

Available tools

execute_sql

Execute a SQL query against Redshift and return results.

list_tables

Return a list of tables available in the current Redshift database.

describe_schema

Describe the schema of a selected table, including column names and types.

sample_data

Fetch a sample of data from a specified table to inspect structure and contents.

connection_status

Check and report the status of the Redshift connection and credentials.

Built by

VeilStrat

AI signals for GTM teams