airflow-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AIRFLOW_MCP_TIMEOUT | No | Timeout in seconds for API requests. | 30 |
| AIRFLOW_MCP_BASE_URL | Yes | Base URL of the Airflow instance (e.g. http://localhost:8080, no /api suffix). Required. | |
| AIRFLOW_MCP_PASSWORD | No | Password for basic auth. Used with AIRFLOW_MCP_USERNAME. | |
| AIRFLOW_MCP_USERNAME | No | Username for basic auth. Used with AIRFLOW_MCP_PASSWORD. | |
| AIRFLOW_MCP_API_TOKEN | No | Bearer token for authentication. Wins over basic auth if both are provided. | |
| AIRFLOW_MCP_READ_ONLY | No | Set to 'true' to disable all write tools. | false |
| AIRFLOW_MCP_VERIFY_SSL | No | Whether to verify SSL certificates. | true |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_dag_runsB | List runs of a DAG, most recent first. |
| get_dag_runA | Get a single DAG run by dag_id and dag_run_id. |
| list_dagsA | List DAGs with their pause state, schedule, owners, and tags. |
| get_dagB | Get a single DAG's details by dag_id. |
| list_import_errorsA | List DAG import errors (parse failures), with filename and stack trace. The quickest way to find why a DAG is missing from the list or broken. |
| get_task_logsA | Read the log for one task attempt. Task logs can be large, so by default only the trailing portion is returned (where the error and traceback usually are). |
| get_airflow_versionA | Return the Airflow version reported by the API. Handy for confirming connectivity and which Airflow major version is in use. |
| get_airflow_healthA | Return Airflow component health: metadatabase, scheduler, triggerer, dag-processor. |
| list_poolsA | List worker pools with their slot usage (occupied/running/queued/open). |
| list_task_instancesA | List task instances in a DAG run, with their states and timings. |
| get_task_instanceB | Get a single task instance by dag_id, dag_run_id, and task_id. |
| trigger_dag_runB | Trigger a new run of a DAG. |
| set_dag_pausedA | Pause or unpause a DAG. |
| clear_task_instancesA | Clear task instances so they re-run (retry). Clearing resets task state and the scheduler re-runs them, so it is
destructive - it can re-execute work. Use |
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 14 tools
Each tool has a clearly distinct purpose. For example, 'get_dag' retrieves a single DAG, while 'list_dags' lists multiple; 'clear_task_instances' resets tasks, distinct from 'trigger_dag_run'. No overlapping functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., 'get_dag', 'list_pools', 'set_dag_paused'). Verbs like 'get' for single entities, 'list' for collections, 'clear', 'set', and 'trigger' are used uniformly.
14 tools is well-scoped for an Airflow MCP server. Core operations for DAGs, runs, task instances, pools, health, and version are covered without bloat or excessive specialization.
The toolset covers the main lifecycle for DAGs (list, get, pause, trigger), runs, and task instances (list, get, clear, logs). However, it lacks management operations for pools (only list), DAG run deletion, and advanced task retry options, leaving minor gaps for some workflows.