Skip to main content
Glama
santosh07401

Redshift MCP Server

by santosh07401

redshift_query

Execute SQL queries on Amazon Redshift databases to retrieve data as JSON results for analysis and reporting.

Instructions

Execute a SQL query on Redshift and return results as JSON.

Args:
    sql: The SQL query to execute

Returns:
    JSON string of the query results or error message

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYes

Implementation Reference

  • The core handler function for the 'redshift_query' MCP tool, decorated with @mcp.tool(). Executes the provided SQL query on a Redshift (or local Postgres) database using pandas.read_sql_query via a connection from get_connection(), converts results to JSON with orient='records', and returns it. Catches exceptions and returns an error message.
    @mcp.tool()
    def redshift_query(sql: str) -> str:
        """
        Execute a SQL query on Redshift and return results as JSON.
        
        Args:
            sql: The SQL query to execute
        
        Returns:
            JSON string of the query results or error message
        """
        try:
            with get_connection() as conn:
                df = pd.read_sql(sql, conn)
                return df.to_json(orient="records", indent=2)
        except Exception as e:
            return f"Error executing query: {str(e)}"
  • Helper function 'get_connection()' used by redshift_query and other tools to establish a connection to Redshift using redshift_connector or psycopg2 for local testing.
    def get_connection():
        """Create a connection to Redshift or local Postgres."""
        try:
            # If host is localhost and port is 5432, assume local Postgres for testing
            if REDSHIFT_HOST == "localhost" and REDSHIFT_PORT == 5432:
                import psycopg2
                return psycopg2.connect(
                    host=REDSHIFT_HOST,
                    port=REDSHIFT_PORT,
                    database=REDSHIFT_DATABASE,
                    user=REDSHIFT_USER,
                    password=REDSHIFT_PASSWORD
                )
            else:
                return redshift_connector.connect(
                    host=REDSHIFT_HOST,
                    port=REDSHIFT_PORT,
                    database=REDSHIFT_DATABASE,
                    user=REDSHIFT_USER,
                    password=REDSHIFT_PASSWORD
                )
        except Exception as e:
            logger.error(f"Connection error: {e}")
            raise

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/santosh07401/redshift-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server