Language: 日本語English

data-engineering Plugin

Topics
Data Engineering & Analytics · AI Agents & AI App Development · 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.

This is the astronomer/agents GitHub repository, described as "AI agent tooling for data engineering workflows." It provides an MCP server for Airflow (astro-airflow-mcp), a terminal CLI tool called af, and a set of skills that extend AI coding agents (Claude Code, Cursor, and other tools) with capabilities for working with Airflow and data warehouses. It is built by Astronomer, licensed under Apache 2.0, and stated to be compatible with open-source Apache Airflow as well as Astronomer's managed Astro platform. The plugin is installed as astronomer-data via Claude Code's plugin marketplace or via the skills.sh npx installer for other agents.

Overview

According to the README, this is not itself a hosted SaaS but an open-source plugin/toolkit (astronomer-data) combining an MCP server, a CLI (af), and modular "skills" for AI coding agents. It integrates with Apache Airflow (self-hosted or Astronomer's managed Astro platform) and with data warehouses such as Snowflake, PostgreSQL, BigQuery, and other SQLAlchemy-supported databases.

What you can do with data-engineering

  • Install the astronomer-data plugin in Claude Code, or add skills to Cursor and 25+ other AI coding agents
  • Use the Airflow MCP server for DAG management, triggering runs, viewing task logs, and checking system health
  • Run the af CLI (e.g. af health, af dags list, af runs trigger ) to interact with Airflow from the terminal
  • Use Data Discovery & Analysis skills such as warehouse-init, analyzing-data, checking-freshness, and profiling-tables
  • Use Data Lineage skills such as tracing-downstream-lineage, tracing-upstream-lineage, annotating-task-lineage, and creating-openlineage-extractors
  • Use DAG Development skills such as authoring-dags, testing-dags, debugging-dags, deploying-airflow, and airflow-hitl
  • Use dbt Integration skills (cosmos-dbt-core, cosmos-dbt-fusion) to run dbt projects as Airflow DAGs via Astronomer Cosmos
  • Use the migrating-airflow-2-to-3 skill to migrate DAGs from Airflow 2.x to 3.x
  • Configure warehouse connections (Snowflake, PostgreSQL, BigQuery, or any SQLAlchemy-supported database) via ~/.astro/agents/warehouse.yml

Sources

Original description (English)

Data engineering plugin - warehouse exploration, pipeline authoring, Airflow integration

History of data-engineering

Back to list