Apache Airflow MCP Server
未认领Independent incident-response MCP server for Apache Airflow: diagnose failed DAGs from UI links with bounded logs, multi-instance routing, and opt-in recovery.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'apache-airflow-mcp-server' -- 'uvx' '--from' 'apache-airflow-mcp-server' '--with' 'apache-airflow-client==3.3.0' 'airflow-mcp' '--transport' 'stdio'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
14 个工具中显示 14 个
文档中列出的工具 (14)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
airflow_clear_dag_run
Clear a whole run (dryrun=true by default)
airflow_clear_task_instances
Clear task instances across runs (dryrun=true by default)
airflow_dataset_events
Dataset (Airflow 2) / asset (Airflow 3) events
airflow_describe_instance
Host, API version, auth type (secrets redacted)
airflow_get_dag
DAG details
airflow_get_dag_run
Single run details
airflow_get_task_instance
Task metadata, retries, timings, optional rendered template fields
airflow_get_task_instance_logs
Logs with level filtering, tailing, context lines, and byte caps
airflow_list_dag_runs
Runs with state filters and ordering (latest first by default)
airflow_list_dags
DAGs with pause state and UI links
airflow_list_instances
List configured instance keys and the default
airflow_list_task_instances
Task attempts for a run; filter by state / taskids server-side
airflow_resolve_url
Parse an Airflow UI URL into instance + dag/run/task identifiers
airflow_trigger_dag
Trigger a run with optional conf/logical date/note