awslabs.redshift-mcp-server

What it is and what it does

This package is an MCP server that bridges AI assistants to Amazon Redshift by exposing cluster discovery, metadata browsing, and query execution as standardized protocol tools. It works with both provisioned Redshift clusters and serverless workgroups, allowing assistants to enumerate databases, schemas, tables, and columns, then execute SQL queries in a read-only mode that rejects write statements.

The server integrates with boto3 and botocore to authenticate against AWS using standard credential chains (profiles, environment variables, or IAM roles). It depends on pydantic for configuration validation, loguru for logging, sqlglot for query parsing, and the mcp library for protocol compliance. Installation is straightforward via pip, though it requires Python 3.10+ and properly configured AWS credentials with appropriate Redshift permissions.

Use it for:

• Enable AI coding assistants (Cursor, VS Code) to explore Redshift schema and run exploratory queries without leaving the editor.
• Build chatbots that answer business questions by discovering relevant tables and executing aggregation queries on Redshift data.
• Automate metadata documentation by having an AI assistant traverse all clusters, databases, and schemas to generate data dictionaries.
• Create data governance tools that audit which tables and columns exist across multiple Redshift environments.
• Integrate Redshift query capabilities into multi-tool AI agent workflows for data analysis and reporting.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides a Model Context Protocol (MCP) server that enables AI assistants to discover, explore, and safely query Amazon Redshift clusters and serverless workgroups through a standardized interface.

Yes. The package is actively maintained, has no known vulnerabilities, installs with low friction, and solves a clear problem for developers who want AI assistants to interact safely with Redshift. The permissive Apache-2.0 license and broad Python version support (3.10–3.13) make it suitable for most environments. Install it if you use Redshift and want MCP-compatible AI tooling; skip it if you have no Redshift clusters or do not use MCP clients.

Install

awslabs-redshift-mcp-server on PyPI

pip install awslabs-redshift-mcp-server

uv add awslabs-redshift-mcp-server

poetry add awslabs-redshift-mcp-server

Installing awslabs.redshift-mcp-server

Before you install

Low friction installation via pure Python wheel. Active maintenance with recent release (4 days old) and high repository engagement (9599 stars). Requires Python 3.10 or newer and AWS credentials configured.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most deployment scenarios.

Quickstart

# Install via uv
uv pip install awslabs.redshift-mcp-server

# Configure in MCP client (e.g., ~/.kiro/settings/mcp.json)
# Set AWS_PROFILE, AWS_REGION, and FASTMCP_LOG_LEVEL environment variables
# Then use via MCP client to call list_clusters, list_databases, list_tables, execute_query

Requires Python 3.10 or newer, AWS credentials configured (via CLI, environment variables, or profile), and appropriate AWS IAM permissions for Redshift discovery and query execution.

Verify before relying

• Specific AWS IAM permissions required for full functionality beyond the general Redshift access mentioned.
• Performance characteristics and query timeout limits for large result sets.
• Whether read-only enforcement applies to all query contexts or only specific execution paths.

Package facts

Evidence: awslabs_redshift_mcp_server-0.0.34-py3-none-any.whl

Tags

More Database packages

Further reading