Language: 日本語English

aws-data-analytics Plugin

Author
Amazon Web Services
Category
Development
Topics
Data Engineering & Analytics · Cloud, Deployment & CI/CD · Databases & Storage
First seen
2026-07-09
Last confirmed
2026-07-13
Explanation last updated
2026-07-12

The explanation below is AI-generated. Please verify it against the sources.

aws-data-analytics is a plugin within AWS's official 'agent-toolkit-for-aws' repository that equips AI coding agents (Claude Code, Codex, Cursor, and other MCP-compatible agents) with skills and MCP server configuration for data lake, analytics, and ETL work on AWS. According to the plugin README, it bundles eight agent skills covering data lake table creation, data ingestion, Athena querying, data catalog discovery, vector storage, external database connectivity, and Amazon OpenSearch Service tasks. It relies on the AWS MCP Server (aws-mcp) for AWS API access, documentation search, and SOP retrieval. Installation is via the Claude Code plugin marketplace, Cursor's team marketplace, Codex plugin marketplace, or by installing skills directly with npx skills add. Users must configure their own AWS credentials and IAM permissions for services such as Athena, Glue, S3, S3 Tables, and S3 Vectors.

Overview

aws-data-analytics is a plugin from AWS's Agent Toolkit for AWS repository. It packages AWS MCP Server configuration together with a set of agent skills so that AI coding agents can perform data lake, analytics, and ETL tasks using AWS services such as Amazon S3 Tables, AWS Glue, Amazon Athena, Amazon S3 Vectors, and Amazon OpenSearch Service.

What you can do with aws-data-analytics

  • Create managed Iceberg tables on Amazon S3 Tables with compaction, snapshot management, Glue catalog registration, and partitioning (creating-data-lake-table skill)
  • Ingest data from S3 files, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (ingesting-into-data-lake skill)
  • Run and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, Amazon Redshift), with workgroup selection and cost tracking (querying-data-lake skill)
  • Resolve fuzzy data references to concrete catalog entries by name, keyword, column, or S3 path (finding-data-lake-assets skill)
  • Inventory and audit the AWS Glue Data Catalog across S3 Tables, Redshift-federated, and remote Iceberg catalogs, flagging stale tables (exploring-data-catalog skill)
  • Store and query vector embeddings via Amazon S3 Vectors for semantic search and RAG workloads (storing-and-querying-vectors skill)
  • Create and troubleshoot AWS Glue connections to JDBC databases, Amazon Redshift, Snowflake, and BigQuery, including Secrets Manager/IAM DB auth and VPC networking (connecting-to-data-source skill)
  • Handle migration, provisioning, and vector/semantic/hybrid search or log/trace analytics for Amazon OpenSearch Service and Serverless (amazon-opensearch-service skill)

Sources

Original description (English)

Data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena.

History of aws-data-analytics

Back to list