Language:JapaneseEnglish

astronomer-data-agents Claude Code Plugin

Category
Development
Topics
Data Engineering & Analytics · Databases & Storage · Migration & Modernization
First cataloged
2026-07-09 (UTC)
Explanation last updated
2026-07-16 (UTC)
Source (GitHub) last updated
2026-08-05 (UTC) (22 days ago)

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

astronomer-data-agents is a Claude Code plugin that adds data-engineering tooling for Apache Airflow, combining an MCP server, a command-line tool, and a set of specialized skills, per its README. It helps with writing DAGs following best practices, diagnosing pipeline failures, tracing data lineage, profiling warehouse tables, and migrating DAGs from Airflow 2 to Airflow 3. It can operate against a self-hosted open-source Airflow REST API or against Astronomer's managed Astro platform. It also connects to data warehouses such as Snowflake, PostgreSQL, and BigQuery, plus other databases via SQLAlchemy drivers, for schema discovery and SQL-based analysis. The project is released under the Apache 2.0 license and also supports other agentic coding tools such as Cursor.

About the service

Astronomer is the company behind Astro, a managed service for running Apache Airflow. The plugin can connect either to a self-hosted Airflow instance's REST API or to an Astro deployment, and it also links to external data warehouses like Snowflake, PostgreSQL, and BigQuery to run queries and profile tables.

What you can do with astronomer-data-agents

  • Author and validate Airflow DAGs following recommended practices
  • Investigate pipeline failures with root-cause debugging
  • Trace upstream and downstream data lineage, including building custom OpenLineage extractors
  • Profile warehouse tables and check data freshness
  • Run ad-hoc SQL analysis through a background Jupyter kernel
  • Migrate DAGs from Airflow 2.x to Airflow 3.x
  • Set up and manage local or cloud Airflow environments, including Astro, Docker Compose, and Kubernetes deployments
  • Run dbt Core or dbt Fusion projects as Airflow DAGs via Cosmos
  • Compose DAGs from YAML templates using Blueprint
  • Interact with Airflow from the terminal via the af CLI or the MCP server

Sources

Back to list