astro-airflow-mcp
OfficialRelated Servers
Alternatives to astro-airflow-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that wraps the Apache Airflow REST API, enabling clients to manage DAGs, monitor task instances, and handle workflows through a standardized interface. It provides comprehensive access to Airflow features including DAG runs, variables, connections, and XComs.MIT
- AlicenseAqualityAmaintenanceAn MCP server that enables AI coding assistants to interact with a local Airflow cluster via its REST API for triggering DAG runs, monitoring status, reading logs, and diagnosing errors.101MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server for controlling Apache Airflow 3 via its REST API, enabling operations like DAG management, task monitoring, and more through natural language.MIT
- AlicenseAqualityBmaintenanceMCP server exposing Apache Airflow REST API operations as tools — list DAGs, inspect runs and task instances, trigger DAG runs, and check failed DAGs and scheduler health72MIT
- FlicenseNot gradedqualityDmaintenanceEnables DAG management, monitoring, debugging, and connection testing for Apache Airflow through the MCP protocol.-
- AlicenseBqualityAmaintenanceMonitor and manage Apache Airflow clusters through natural language queries via MCP tools: DAG inspection, task monitoring, health checks, and cluster analytics without API complexity. * Guide: https://call518.medium.com/mcp-airflow-api-a-model-context-protocol-mcp-server-for-apache-airflow-5dfdfb25453MIT
TDQS
Scored across 31 tools
Each tool targets a distinct aspect of Airflow (DAGs, runs, tasks, instances, logs, pools, variables, etc.), with clear descriptions that prevent confusion. Even similar tools like 'explore_dag' and 'get_dag_details' serve different granularity levels.
Most tools follow a verb_noun pattern (list_dags, get_dag_details, trigger_dag), but a few deviate (diagnose_dag_run, explore_dag, trigger_dag_and_wait). Overall, the pattern is clear and predictable.
31 tools is high but appropriate for a comprehensive Airflow MCP server covering many subsystems. Each tool has a clear purpose, though some consolidation (e.g., get_dag_details and explore_dag) could reduce count slightly.
The tool set is strong for monitoring and troubleshooting (DAGs, runs, tasks, logs, system health) but misses write operations for variables, connections, and pools. This leaves agents without the ability to create or update these resources.