redshift-utils-mcp

Redshift Utils MCP Server

Overview

This project implements a Model Context Protocol (MCP) server designed specifically to interact with Amazon Redshift databases.

It bridges the gap between Large Language Models (LLMs) or AI assistants (like those in Claude, Cursor, or custom applications) and your Redshift data warehouse, enabling secure, standardized data access and interaction. This allows users to query data, understand database structure, and monitoring/diagnostic operations using natural language or AI-driven prompts.

This server is for developers, data analysts, or teams looking to integrate LLM capabilities directly with their Amazon Redshift data environment in a structured and secure manner.

Table of Contents

• Redshift Utils MCP Server
  • Overview
  • Table of Contents
  • Features
  • Prerequisites
  • Configuration
  • Usage
    • Connecting with Claude Desktop / Anthropic Console:
    • Connecting with Cursor IDE:
    • Available MCP Resources
    • Available MCP Tools
  • TO DO
  • Contributing
  • License
  • References

Features

• ✨ Secure Redshift Connection (via Data API): Connects to your Amazon Redshift cluster using the AWS Redshift Data API via Boto3, leveraging AWS Secrets Manager for credentials managed securely via environment variables.
• 🔍 Schema Discovery: Exposes MCP resources for listing schemas and tables within a specified schema.
• 📊 Metadata & Statistics: Provides a tool (handle_inspect_table) to gather detailed table metadata, statistics (like size, row counts, skew, stats staleness), and maintenance status.
• 📝 Read-Only Query Execution: Offers a secure MCP tool (handle_execute_ad_hoc_query) to execute arbitrary SELECT queries against the Redshift database, enabling data retrieval based on LLM requests.
• 📈 Query Performance Analysis: Includes a tool (handle_diagnose_query_performance) to retrieve and analyze the execution plan, metrics, and historical data for a specific query ID.
• 🔍 Table Inspection: Provides a tool (handle_inspect_table) to perform a comprehensive inspection of a table, including design, storage, health, and usage.
• 🩺 Cluster Health Check: Offers a tool (handle_check_cluster_health) to perform a basic or full health assessment of the cluster using various diagnostic queries.
• 🔒 Lock Diagnosis: Provides a tool (handle_diagnose_locks) to identify and report on current lock contention and blocking sessions.
• 📊 Workload Monitoring: Includes a tool (handle_monitor_workload) to analyze cluster workload patterns over a time window, covering WLM, top queries, and resource usage.
• 📝 DDL Retrieval: Offers a tool (handle_get_table_definition) to retrieve the SHOW TABLE output (DDL) for a specified table.
• 🛡️ Input Sanitization: Utilizes parameterized queries via the Boto3 Redshift Data API client where applicable to mitigate SQL injection risks.
• 🧩 Standardized MCP Interface: Adheres to the Model Context Protocol specification for seamless integration with compatible clients (e.g., Claude Desktop, Cursor IDE, custom applications).

Prerequisites

Software:

• Python 3.8+
• uv (recommended package manager)
• Git (for cloning the repository)

Infrastructure & Access:

• Access to an Amazon Redshift cluster.
• An AWS account with permissions to use the Redshift Data API (redshift-data:*) and access the specified Secrets Manager secret (secretsmanager:GetSecretValue).
• A Redshift user account whose credentials are stored in AWS Secrets Manager. This user needs the necessary permissions within Redshift to perform the actions enabled by this server (e.g., CONNECT to the database, SELECT on target tables, SELECT on relevant system views like pg_class, pg_namespace, svv_all_schemas, svv_tables, `svv_table_info``). Using a role with the principle of least privilege is strongly recommended. See Security Considerations.

Credentials:

Your Redshift connection details are managed via AWS Secrets Manager, and the server connects using the Redshift Data API. You need:

• The Redshift cluster identifier.
• The database name within the cluster.
• The ARN of the AWS Secrets Manager secret containing the database credentials (username and password).
• The AWS region where the cluster and secret reside.
• Optionally, an AWS profile name if not using default credentials/region.

These details will be configured via environment variables as detailed in the Configuration section.

Configuration

Set Environment Variables: This server requires the following environment variables to connect to your Redshift cluster via the AWS Data API. You can set these directly in your shell, using a systemd service file, a Docker environment file, or by creating a .env file in the project's root directory (if using a tool like uv or python-dotenv that supports loading from .env).

Example using shell export:

Example .env file (see .env.example):

Required Variables Table:

Note: Ensure the AWS credentials used by Boto3 (via environment, profile, or IAM role) have permissions to access the specified REDSHIFT_SECRET_ARN and use the Redshift Data API (redshift-data:*).

Usage

Connecting with Claude Desktop / Anthropic Console:

Add the following configuration block to your mcp.json file. Adjust command, args, env, and workingDirectory based on your installation method and setup.

Connecting with Cursor IDE:

1. Start the MCP server locally using the instructions in the Usage / Quickstart section.
2. In Cursor, open the Command Palette (Cmd/Ctrl + Shift + P).
3. Type "Connect to MCP Server" or navigate to the MCP settings.
4. Add a new server connection.
5. Choose the stdio transport type.
6. Enter the command and arguments required to start your server (uvx run redshift_utils_mcp). Ensure any necessary environment variables are available to the command being run.
7. Cursor should detect the server and its available tools/resources.

Available MCP Resources

Replace {script_path} and {schema_name} with the actual values when making requests. Accessibility of schemas/tables depends on the permissions granted to the Redshift user configured via REDSHIFT_SECRET_ARN.

Available MCP Tools

TO DO

• Improve Prompt Options
• Add support for more credential methods
• Add Support for Redshift Serverless

Contributing

Contributions are welcome! Please follow these guidelines.

Find/Report Issues: Check the GitHub Issues page for existing bugs or feature requests. Feel free to open a new issue if needed.

Security is critical when providing database access via an MCP server. Please consider the following:

🔒 Credentials Management: This server uses AWS Secrets Manager via the Redshift Data API, which is a more secure approach than storing credentials directly in environment variables or configuration files. Ensure your AWS credentials used by Boto3 (via environment, profile, or IAM role) are managed securely and have the minimum necessary permissions. Never commit your AWS credentials or .env files containing secrets to version control.

🛡️ Principle of Least Privilege: Configure the Redshift user whose credentials are in AWS Secrets Manager with the minimum permissions required for the server's intended functionality. For example, if only read access is needed, grant only CONNECT and SELECT privileges on the necessary schemas/tables and SELECT on the required system views. Avoid using highly privileged users like admin or the cluster superuser.

For guidance on creating restricted Redshift users and managing permissions, refer to the official (https://docs.aws.amazon.com/redshift/latest/mgmt/security.html).

License

This project is licensed under the MIT License. See the (LICENSE) file for details.

References

• This project relies heavily on the Model Context Protocol specification.
• Built using the official MCP SDK provided by Model Context Protocol.
• Utilizes the AWS SDK for Python (Boto3) to interact with the Amazon Redshift Data API.
• Many of the diagnostic SQL scripts are adapted from the excellent awslabs/amazon-redshift-utils repository.