Empower agents to manage and diagnose your Airflow data platform
Visit WebsiteFreemiumVisit Website
Tracked since2026
0 reviews trackedWhat is Astronomer MCP?
Astronomer's MCP server puts the Airflow REST API behind MCP tools so an assistant can read and act on the state of a data platform. It lists DAGs with their source code, statistics, warnings and import errors, walks task instances inside a run, and returns task logs directly. Variables, resource pools, assets, installed plugins, provider packages and Airflow configuration are all readable, with connection credentials excluded from what the agent sees.
Beyond mirroring endpoints one to one, it ships consolidated tools shaped for agent use: explore_dag gathers everything about a single DAG in one call, diagnose_dag_run assembles the failure context for a broken run, and get_system_health summarizes overall status. It can also trigger runs and pause or unpause DAGs, so an agent that has diagnosed a stuck pipeline can restart it in the same session rather than handing the work back.
The server points at any Airflow webserver URL, so it covers self-hosted Airflow as well as Astro deployments. Authentication supports bearer tokens, username and password with automatic OAuth2 exchange on Airflow 3, and basic auth on Airflow 2, with credentials passed as environment variables or CLI flags. Aimed at data engineers who want to debug a failed DAG run from their editor instead of clicking through the Airflow UI.
Key Features
Lists DAGs with source code, statistics, warnings and import errorsRetrieves task instances and full task logs for failure debuggingTriggers DAG runs and pauses or unpauses DAGsReads variables, resource pools, assets, plugins and provider packagesBundles agent-oriented tools: explore_dag, diagnose_dag_run and get_system_healthConnects to any Airflow webserver, self-hosted or on Astro, via bearer, basic or OAuth2 auth
Pricing
Freemium
Astronomer MCP offers a generous free tier with optional paid upgrades for advanced features.
Reviews
$99Free with your review
Write a reviewReview Astronomer MCP, get a free AI guide
Share your experience and we will send you Improve Your Thinking Patterns Using ChatGPT, free.
Best Astronomer MCP Alternatives
Top alternatives based on features, pricing, and user needs.
Still deciding?
Most buyers shortlist 2 or 3 tools before committing. Pull a side-by-side comparison or browse the full alternatives shortlist below.
Explore More
Astronomer MCP FAQ
How does Astronomer MCP help a data engineer debug a failed DAG run from their editor?
Astronomer MCP exposes the Airflow REST API through MCP tools, so an assistant can read and act on the state of a data platform directly from an editor. It includes a consolidated tool called diagnose_dag_run that assembles the failure context for a broken run, and it can also trigger runs or pause and unpause DAGs, allowing the engineer to restart a stuck pipeline in the same session without switching to the Airflow UI.
How does Astronomer MCP compare to Apache Airflow for managing data pipelines?
Astronomer MCP is not a replacement for Apache Airflow; it is an MCP server that puts the Airflow REST API behind MCP tools so an assistant can manage and diagnose an existing Airflow data platform. While Apache Airflow is the orchestration engine itself, Astronomer MCP adds agent-friendly consolidated tools like explore_dag and get_system_health that are shaped for agent use, making it easier to debug and control Airflow from an editor.
What are the main limitations or trade-offs of using Astronomer MCP?
Astronomer MCP excludes connection credentials from what the agent sees, so sensitive data is not exposed. It relies on the Airflow webserver URL and requires authentication credentials passed as environment variables or CLI flags, which means it does not work without a running Airflow instance and proper authentication setup.
Which teams benefit most from using Astronomer MCP?
Data engineering teams that use Apache Airflow for orchestration benefit most from Astronomer MCP, as it allows them to debug failed DAG runs and manage pipelines directly from their editor. It is especially useful for teams that want to reduce time spent clicking through the Airflow UI and instead use agent-driven workflows to diagnose and restart stuck pipelines.
How is Astronomer MCP priced?
Astronomer MCP is available on a free tier, with paid plans for more usage and features.
Can Astronomer MCP work with self-hosted Airflow deployments or only Astro?
Astronomer MCP can point at any Airflow webserver URL, so it covers both self-hosted Airflow deployments and Astro deployments. It supports authentication via bearer tokens, username and password with automatic OAuth2 exchange on Airflow 3, and basic auth on Airflow 2.
Does Astronomer MCP allow an agent to trigger a new DAG run after diagnosing a failure?
Yes, Astronomer MCP can trigger runs and pause or unpause DAGs, so an agent that has diagnosed a stuck pipeline can restart it in the same session rather than handing the work back. This is enabled by consolidated tools like diagnose_dag_run that assemble failure context and the ability to act on that context directly.
What specific information about a DAG can Astronomer MCP retrieve for an agent?
Astronomer MCP lists DAGs with their source code, statistics, warnings, and import errors. It also walks task instances inside a run, returns task logs, and provides a consolidated tool called explore_dag that gathers everything about a single DAG in one call.
Source: astronomer.io