Build and run data lakes on AWS with your agent: AWS's skills for S3 Tables, Glue, Athena, Redshift, OpenSearch, MSK, Flink and Airflow.
by Amazon· Data & analyticsUnclaimed · Yours? Claim it
4 images
About
AWS Data Analytics is Amazon Web Services' plugin for data engineering on AWS, part of the Agent Toolkit for AWS. Its skills guide your coding agent through the data lifecycle across AWS analytics services, and it includes the AWS MCP Server for the AWS APIs and current AWS documentation. What its skills cover - Data lakes: creating managed Iceberg tables on Amazon S3 Tables, loading data from S3, JDBC databases, Snowflake, BigQuery, DynamoDB or AWS Glue tables, and querying across catalogs with Athena - Finding data: inventorying the AWS Glue Data Catalog and tracking down a table by name, keyword, column or S3 path - Connecting sources: creating and troubleshooting AWS Glue connections to Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora, Redshift, Snowflake and BigQuery - Vectors: storing and querying embeddings in Amazon S3 Vectors for semantic search and RAG - Search: Amazon OpenSearch Service and Serverless, including moving from Solr or Elasticsearch, vector and hybrid search, and log and trace analytics - Warehousing: Amazon Redshift SQL, COPY and UNLOAD, system views and the Data API - Orchestration: writing, testing, debugging and upgrading Apache Airflow workflows on Amazon MWAA and MWAA Serverless - Streaming: running Amazon MSK clusters, moving from self-managed Kafka to MSK Express, and building Apache Flink applications - Governance: curating business metadata in Amazon SageMaker Catalog or the Glue Data Catalog, and requesting, approving and revoking access to data assets How to install it In Claude Code, run /plugin install aws-data-analytics@claude-plugins-official. It's also in Codex and Cursor through the aws/agent-toolkit-for-aws marketplace, and in Devin with devin plugins install aws/agent-toolkit-for-aws#plugins/aws-data-analytics. How it connects - The AWS MCP Server runs through the MCP Proxy for AWS with uvx, so you need uv installed. - You need an AWS account and AWS credentials on your machine (from aws configure, aws sso login or environment variables), with a default Region set. - Your IAM role needs permissions for the services the skills use, such as Glue, Athena, S3, S3 Tables, S3 Vectors and MWAA. AWS recommends scoping them to the resources your workload uses. Good to know - The skills are open source, so a team can fork them to match its own naming, data formats and standards.
Once it’s added
“Create an Iceberg table for our order events with daily partitioning.”
“Import our PostgreSQL sales data into the data lake.”
“Query the top 10 customers by revenue from our analytics table.”
“What data do we have in our account?”
“Find the table that has customer_id.”
“Set up an AWS Glue connection to Snowflake.”
Before you add it
Reads only
Your AWS Glue Data Catalog, S3 Tables and Redshift metadata · Query results from Athena and Redshift · Current AWS documentation
Makes changes · your agent can ask first
Creates tables, AWS Glue connections and data loads in your AWS account · Writes and deploys Airflow workflows and Flink applications · Can grant and revoke access to catalog assets, within your IAM permissions
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
No reviews yet. Used AWS Data Analytics? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add aws/agent-toolkit-for-aws /plugin install aws-data-analytics@agent-toolkit-for-aws
Scanned and passed · checked 7 h ago
Nobody has shared how they use AWS Data Analytics yet.
Plugins people install alongside AWS Data Analytics.
Scanned on every change, and again when our rules improve.
Claude CodeSupported
OpenClawSupportedTell us and a person on the trust team will look at it. Or email [email protected].
Plugins people install alongside AWS Data Analytics.
Lets your agent search, query and chart the data in your own Metabase, and build questions and dashboards with your permissions.
Equips your coding agent with a data engineer, pipeline commands and skills for Airflow, dbt, Spark and data quality.
Lets your agent query your PostHog analytics, triage errors, and create feature flags and experiments from plain-language asks.
Data analytics skills for product managers: SQL from plain English, cohort retention analysis and A/B test reads with a ship-or-stop call.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.
