Data & Analysis apache-airflowmcp-serverdata-warehousesql-analysisdag-developmentdbtdata-lineage

Astronomer Agents: AI Agent Toolkit for Airflow Data Engineering

AI agent tooling for data engineering workflows—unifying Airflow orchestration, warehouse analytics, and DAG development in one package.

FollowAgents review · FARS-2.1
Not recommended
46/ 100 5-point scale 2.3 / 5
1 2 3 4 5 6
1Trust8 / 29 · 1.4/5

Evidence: SECURITY.md provides vulnerability disclosure process; README mentions anonymous telemetry with opt-out; configuration uses environment variables and file permissions, but least privilege principle not explicit. Deductions: no explicit least privilege, user confirmation, data flow transparency, sensitive data handling details, dependency security audit, external effects control, rollback mechanism, source attribution.

2Reliability6 / 14 · 2.1/5

Evidence: README and CI config consistent; tests disable telemetry; CI matrix covers Python and Airflow versions. Deductions: dependency availability not explicit, failure messages not detailed.

3Adaptability12 / 18 · 3.3/5

Evidence: README clearly identifies target users (data engineers) and scenarios (data discovery, DAG development); skill descriptions clear; supports multiple clients and environments. Deductions: capability boundaries not fully explicit, trigger precision relies on skill descriptions, environment fit not comprehensive.

4Convention10 / 18 · 2.8/5

Evidence: README well-structured; installation instructions detailed; examples and FAQ provided; Apache-2.0 license complete. Deductions: naming stability not explicit, known limitations not fully documented, versioning/changelog missing, maintenance responsibility not explicit.

5Effectiveness7 / 13 · 2.7/5

Evidence: Output usability high (generates warehouse.md etc.); marginal value clear (automates data engineering workflows). Deductions: cost-benefit not quantified, relies on external services.

6Verifiability3 / 8 · 1.9/5

Evidence: README and CI config traceable, but no independent verification. Deductions: claim traceability limited, cross-source corroboration insufficient, fact-inference separation not explicit.

Evidence confidence: Low Reviewed Sep 07, 2026 Reviewed revision dbd9bb79c4f7
Safety controls not found in source: rollback or recovery path
Before you use it
  • Repository includes telemetry; verify data collection scope.
  • Relies on external services (PyPI, GitHub); ensure supply chain security.
  • No changelog provided; assess upgrade risks.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this agent do, and when should you use it?

Astronomer Agents is an Apache-2.0 licensed open-source project by Astronomer that equips AI coding agents with specialized capabilities for data engineering. The repository delivers three interlocking pieces: an MCP server (`astro-airflow-mcp`) exposing Airflow's REST API as Model Context Protocol tools for DAG management, triggering, and log retrieval; a CLI utility named `af` for terminal-based Airflow interaction; and over a dozen Skills—reusable prompt/instruction modules—that extend agents like Claude Code and Cursor with domain knowledge for warehouse discovery, lineage tracing, DAG authoring, testing, deployment, dbt integration, and Airflow upgrades. Installation is client-driven: a Claude Code plugin, a Cursor one-click MCP setup, or a generic `npx skills add` command for 25+ agents. The MCP server is compatible with any Airflow 2.x/3.x REST API endpoint, making it viable for both Astro and self-hosted deployments.

Concretely, the agent performs these operations: The Airflow MCP server (launched via uvx astro-airflow-mcp --transport stdio) converts Airflow REST API interactions into MCP tools, letting AI assistants list DAGs, trigger runs, fetch task logs, and check system health. The af CLI (invoked with uvx --from astro-airflow-mcp af) enables commands such as af health, af dags list, and af runs trigger <dag_id>. Skills extend agents with workflows: warehouse-init profiles configured databases (Snowflake, PostgreSQL, BigQuery, SQLAlchemy-compatible) to generate .astro/warehouse.md schema docs; analyzing-data runs SQL on a background Jupyter kernel to answer business questions; profiling-tables computes table statistics; lineage skills (tracing-downstream-lineage, tracing-upstream-lineage) analyze data flow; DAG skills (authoring-dags, testing-dags, debugging-dags) support code creation and validation; cosmos-dbt-core guides dbt Core integration; and migrating-airflow-2-to-3 assists version upgrades. Configuration lives in ~/.astro/agents/warehouse.yml and .env for warehouse credentials, with Airflow connection via environment variables or auto-discovery from a local dags/ folder.

  1. A data engineer using Claude Code inside an Airflow project wants to write a new DAG; they call the authoring-dags skill for best-practice suggestions and run testing-dags to validate locally.
  2. An analyst who needs to understand warehouse schemas runs warehouse-init to generate .astro/warehouse.md, then uses analyzing-data to query customer tables via natural language.
  3. A platform team debugging a failed DAG uses the debugging-dags skill for deep root-cause analysis and the af CLI to inspect task logs.
  4. A data governance engineer traces the impact of a schema change using tracing-downstream-lineage and tracing-upstream-lineage skills.
  5. A team porting dbt Core projects into Airflow employs the cosmos-dbt-core skill to integrate with Astronomer Cosmos.
  6. An organization upgrading from Airflow 2.x to 3.x follows the migrating-airflow-2-to-3 skill to refactor DAGs safely.

What are this agent's strengths and limitations?

Pros
  • Deep Airflow integration: MCP server and af CLI cover DAG listing, triggering, and log retrieval, reducing context switching.
  • Extensive Skills library spans the entire data engineering lifecycle—warehouse discovery, lineage, authoring, testing, debugging, deployment, dbt, and migration—and auto-triggers from natural language.
  • Client-agnostic distribution: works with Claude Code via plugin, Cursor via MCP, and any MCP-compatible client; Skills installable to 25+ agents via npx.
  • Open-source friendly: compatible with self-hosted Apache Airflow 2.x/3.x, not locked to Astronomer's managed platform.
Limitations
  • Warehouse connectors are built-in for only Snowflake, PostgreSQL, and BigQuery; other databases require SQLAlchemy configuration and manual driver installation.
  • Runtime dependencies: requires uvx (Python) and npx (Node.js) availability, plus a network connection for package fetching and remote API calls.
  • The af CLI collects anonymous telemetry unless disabled, which may raise data-governance concerns.
  • Advanced features like human-in-the-loop (HITL) to airflow-hitl skill require Airflow 3.1+ and may not apply to older deployments.

How do you install or deploy this agent?

Prerequisites: Python with uv (or pip), Node.js for npx, and appropriate client. Installation options: 1. Claude Code: run claude plugin marketplace add astronomer/agents then claude plugin install astronomer-data@astronomer. 2. Cursor: use the one-click install button or manually add to ~/.cursor/mcp.json: {"mcpServers":{"airflow":{"command":"uvx","args":["astro-airflow-mcp","--transport","stdio"]}}}. 3. Generic MCP clients: execute uvx astro-airflow-mcp --transport stdio (optionally set AIRFLOW_API_URL, AIRFLOW_USERNAME, AIRFLOW_PASSWORD). 4. Skills: run npx skills add astronomer/agents --skill '*' (omit --skill to select individually). Configure warehouse connections in ~/.astro/agents/warehouse.yml and credentials in ~/.astro/agents/.env.

How do you use this agent?

  1. Trigger warehouse initialization: invoke /astronomer-data:warehouse-init in the agent to generate .astro/warehouse.md. 2. Ask natural-language queries like "Show me revenue trends by product" or "Create a DAG that loads data from S3 to Snowflake daily"; the agent auto-invokes relevant skills. 3. Use the af CLI for direct terminal operations: alias af='uvx --from astro-airflow-mcp af', then af health, af dags list, af runs trigger <dag_id>. 4. For remote Airflow, set AIRFLOW_API_URL, AIRFLOW_USERNAME, AIRFLOW_PASSWORD, or AIRFLOW_AUTH_TOKEN environment variables. Run from a directory containing airflow.cfg or dags/ to enable auto-discovery.

FAQ

Is this only for Astronomer's Astro platform?
No. While Astro is supported, the core components are designed for open-source Apache Airflow. The MCP server works with any Airflow 2.x/3.x REST API by setting AIRFLOW_API_URL to your self-hosted instance. Skills are tool-agnostic and work with any Airflow deployment.
What credentials and permissions do I need?
For Airflow, you need API access credentials (username/password or auth token). For data warehouses, you must provide connection details in warehouse.yml and secrets in .env. Schema discovery via warehouse-init only scans databases listed in the config; querying can access any database your user has permissions for.
How are SQL queries executed? Do they modify production data?
The analyzing-data skill runs queries on a background Jupyter kernel using your warehouse connection. Queries are typically read-only SELECTs, but you should avoid issuing writes unless intended. The MCP server's Airflow operations (like triggering DAGs) require appropriate Airflow runtime permissions.
Can I use this with VS Code or other agents?
Yes. The MCP server is compatible with any MCP client (e.g., Claude Desktop, VS Code, Cursor). Skills are supported by major agents like Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, Cline, and others—see the compatibility list in the README.

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents