Airflow MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AIRFLOW_BASE_URL | Yes | Base URL of the Airflow instance (e.g., http://localhost:8080) | |
| AIRFLOW_PASSWORD | Yes | Password for Airflow authentication | |
| AIRFLOW_USERNAME | Yes | Username for Airflow authentication | |
| AIRFLOW_AUTH_MODE | No | Authentication mode (default: basic) | basic |
| AIRFLOW_LOG_MAX_LINES | No | Maximum number of log lines to return (optional) | 100 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_dagsA | List Airflow DAGs, optionally filtered by tag or active state. |
| get_dagC | Get metadata for a single Airflow DAG. |
| list_dag_runsC | List DAG run history for a given DAG. |
| get_dag_runC | Get details for a single DAG run, including its trigger conf. |
| list_task_instancesB | List task instances and their state for a given DAG run. |
| get_task_logsB | Get logs for a task instance, truncated to AIRFLOW_LOG_MAX_LINES. |
| trigger_dag_runB | Trigger a new DAG run. Sensitive: creates a new, irreversible execution. |
| pause_dagA | Pause a DAG. Reversible, but affects the shared scheduler. |
| unpause_dagB | Resume a paused DAG. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct entity or action: DAG metadata, DAG run details, task logs, listing operations, and state changes (pause, unpause, trigger). No overlapping purposes.
All names follow a consistent verb_noun pattern with underscores (e.g., get_dag, list_dags, trigger_dag_run). Verbs are clear and nouns precisely identify the resource.
9 tools is appropriate for an Airflow MCP server, covering core operations without redundancy. The count is well-scoped for the domain.
Covers essential DAG, DAG run, and task instance operations. Minor gaps like clearing task instances or updating DAG configuration are missing but not critical for typical monitoring and triggering workflows.