Accelerating SQL analytics with Amazon Redshift MCP server

As information analysts and engineers, we frequently discover ourselves switching between a number of instruments to discover database schemas, perceive desk constructions, and execute queries throughout completely different Amazon Redshift information warehouses. Utilizing pure language to discover metadata and information can simplify this course of, however an AI agent typically wants the extra context of your Redshift cluster configurations and schemas to efficiently uncover and construct the very best execution path.

That is the place the Mannequin Context Protocol (MCP) can act as a bridge between the AI agent and your Redshift clusters to offer the mandatory data to higher assist pure language interfaces to your information. MCP is an open normal that permits AI purposes to securely hook up with exterior information sources and instruments, offering them with wealthy, real-time context about your particular atmosphere. In contrast to static instruments, MCP permits AI brokers to dynamically uncover database constructions, perceive desk relationships, and execute queries with full consciousness of your Amazon Redshift setup.

To deal with these challenges and unlock the total potential of conversational information evaluation, Amazon Internet Providers (AWS) launched the Amazon Redshift MCP server, an open supply resolution that innovates the way you work together with Amazon Redshift information warehouses. The Amazon Redshift MCP server integrates seamlessly with Amazon Q Developer command line interface (CLI), Claude Desktop, Kiro, and different MCP-compatible instruments. It might allow uncover, discover, and analyze your Amazon Redshift metadata and information by pure language conversations with an AI assistant that actually understands your database atmosphere.

On this submit, we stroll by organising the Amazon Redshift MCP server and show how an information analyst can effectively discover Redshift information warehouses and carry out information evaluation utilizing pure language queries.

What’s the Amazon Redshift MCP Server?

The Amazon Redshift MCP server is a MCP implementation that gives AI brokers with protected, structured entry to Amazon Redshift assets. It permits:

• Cluster discovery – Robotically uncover each provisioned Redshift clusters and serverless workgroups
• Metadata exploration – Browse databases, schemas, tables, and columns by pure language
• Protected question execution – Execute SQL queries in READ ONLY mode with built-in security protections
• Multi-cluster assist – Work with a number of clusters and workgroups concurrently for information reconciliation duties

The MCP server acts as a bridge between Amazon Q CLI and your Amazon Redshift infrastructure, translating pure language requests into applicable API calls and SQL queries. The next diagram illustrates the high-level structure.

The next video demonstrates the answer outlined on this submit.

Conditions

Earlier than you start, guarantee you might have the next:

System necessities

• Python 3.10 or newer
• uv package deal supervisor (set up information)
• Amazon Q CLI or different instruments resembling Claude Desktop put in and configured

AWS necessities

Required IAM permissions

The person identification wants the next IAM permissions in your entry insurance policies:

{
  "Model": "2012-10-17",
  "Assertion": [
    {
      "Effect": "Allow",
      "Action": [
        "redshift:DescribeClusters",
        "redshift-serverless:ListWorkgroups",
        "redshift-serverless:GetWorkgroup",
        "redshift-data:ExecuteStatement",
        "redshift-data:BatchExecuteStatement",
        "redshift-data:DescribeStatement",
        "redshift-data:GetStatementResult"
      ],
      "Useful resource": "*"
    }
  ]
}

Set up and configuration

The next part covers the steps required to put in and configure Amazon Redshift MCP server.

Set up required dependencies

Full the next steps to put in required dependencies:

1. Set up the uv package deal supervisor should you haven’t already:

# macOS/Linux
curl -LsSf https://astral.sh/uv/set up.sh | sh

# Home windows
powershell -c "irm https://astral.sh/uv/set up.ps1 | iex"

2. Set up Python 3.10 or newer:

uv python set up 3.10

Configure the MCP server

The MCP server could be configured utilizing a number of MCP supported shoppers. On this submit we focus on the steps utilizing Amazon Q Developer CLI and Claude Desktop.Full the next directions to arrange Amazon Q Developer CLI in your host machine and entry the Amazon Redshift MCP Server:

1. Set up the Amazon Q Developer CLI.
2. Configure the Amazon Redshift MCP server in your Amazon Q CLI configuration. Edit the MCP configuration file at ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "awslabs.redshift-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.redshift-mcp-server@latest"],
      "env": {
        "AWS_PROFILE": "default",
        "AWS_REGION": "us-east-1",
        "FASTMCP_LOG_LEVEL": "INFO"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

For additional particulars on set up, consult with the Set up part within the Amazon Redshift MCP server README.md.

3. Begin Amazon Q CLI to confirm the MCP server is correctly configured:

You need to discover the Amazon Redshift MCP server initialize efficiently within the startup logs.To arrange Amazon Q Developer CLI in your host machine and entry the Amazon Redshift MCP Server utilizing Claude Desktop, full the next steps:

4. Obtain and set up Claude Desktop in your working system
5. Open Claude Desktop and within the backside left, select the gear icon to navigate to Settings
6. Select the Developer tab and configure your MCP server by including the identical configuration as step 3 within the Amazon Q CLI setup
7. Restart Claude Desktop to activate the MCP server connection
8. Take a look at the combination by beginning a brand new dialog and asking: Present me all out there Redshift clusters

Use case: Buyer buy evaluation

Think about a sensible situation the place an information analyst must discover buyer buy information throughout a number of Redshift clusters. The next walkthrough demonstrates how the MCP server simplifies this workflow.As an information analyst at an ecommerce firm, you want to:

1. Uncover out there Redshift clusters
2. Discover the database construction to search out buyer and gross sales information
3. Analyze buyer buy patterns
4. Generate insights for the enterprise crew

To perform these duties, you observe these steps:

5. Ask Amazon Q to indicate you out there Amazon Redshift assets:

Present me all out there Redshift clusters

Amazon Q will use the MCP server to find your clusters and supply particulars resembling cluster identifiers and kinds (provisioned or serverless), present standing and availability, connection endpoints and configuration, and node varieties and capability data.

6. Discover the database construction to know your information group:

What databases and tables can be found within the analytics-cluster?

Amazon Q will use the MCP server to systematically discover the objects within the cluster:

7. Earlier than analyzing information, perceive the desk schemas:

Present me the construction of the purchasers and orders tables in analytics-cluster

Amazon Q will use the MCP server to will look at the desk columns and supply detailed schema data.

8. Analyze buyer buy patterns utilizing pure language queries:

Analyze buyer buy sample from analytics cluster. Present me the highest 10 clients by whole buy quantity and their shopping for frequency

Amazon Q will use the MCP server to run the suitable SQL queries and supply insights.

9. The MCP server helps analyzing information throughout a number of clusters:

Examine buyer acquisition prices between the analytics-cluster and marketing-cluster information.

Amazon Q will use the MCP server to run the suitable SQL queries evaluate the info throughout analytics-cluster and marketing-cluster.

Greatest Practices

The MCP server comes geared up with a number of important security protections designed to safeguard your information and system efficiency. The READ ONLY mode serves as a important safeguard towards unintended information modifications, and we advocate enabling this function when relevant to your use case. To additional improve safety, the server implements question validation mechanisms that scrutinize operations for potential dangerous impacts, with user-in-loop validation being really helpful for optimum security. For useful resource administration, the server enforces useful resource limits to forestall performance-impacting runaway queries, once more benefiting from user-in-loop validation for finest outcomes. By way of accessibility, the MCP functionality maintains broad availability throughout all AWS Areas the place Amazon Redshift Information API is supported, with throttling limits aligned to present Amazon Redshift Information API service quotas to make sure constant efficiency and reliability.For finest outcomes, observe these suggestions:

1. Begin with discovery – Start by exploring cluster and database construction and tables
2. Use pure language – Describe what you wish to analyze somewhat than writing SQL immediately
3. Iterate steadily – Construct advanced analyses step-by-step
4. Confirm outcomes – Cross-check essential findings with enterprise stakeholders
5. Doc insights – Save essential queries and outcomes for future reference

Conclusion

The Amazon Redshift MCP server transforms how information analysts work together with Redshift clusters by enabling pure language information exploration and evaluation by agentic tooling like Kiro and Amazon Q CLI. By eliminating the necessity to manually write SQL queries and navigate advanced database constructions, analysts can concentrate on producing insights somewhat than wrestling with syntax and schema discovery.Whether or not you’re performing a one-time evaluation, producing common experiences, or exploring new datasets, the Amazon Redshift MCP server offers a strong, intuitive interface in your information evaluation workflows.Able to get began? Right here’s what to do subsequent:

1. Set up the MCP server following the configuration steps on this submit
2. Discover your Amazon Redshift atmosphere utilizing pure language queries
3. Begin with easy analyses and steadily construct complexity
4. Share insights along with your crew utilizing the pure language summaries
5. Present suggestions to assist enhance the MCP server capabilities

Take a look at these weblog posts that can assist you navigate utilizing pure language along with your use instances:

Concerning the authors