Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AIRFLOW_API_URLYesThe base URL of your Airflow REST API endpoint
MCP_SERVER_PORTNoControls the transport mode selection. When NOT set: Uses stdio transport (traditional MCP mode). When set: Uses http transport (Docker mode)
AIRFLOW_LOG_LEVELNoControls logging verbosity. Values: DEBUG, INFO, WARNING, ERRORINFO
AIRFLOW_API_PASSWORDYesPassword for Airflow API authentication
AIRFLOW_API_USERNAMEYesUsername for Airflow API authentication

Tools

Functions exposed to the LLM to take actions

NameDescription
get_prompt_template

[Tool Role]: Provides comprehensive prompt template for LLM interactions with Airflow operations.

Args: section: Optional section name to get specific part of template mode: Optional mode (summary/detailed) to control response verbosity

Returns: Comprehensive template or specific section for optimal LLM guidance

list_dags

[Tool Role]: Lists all DAGs registered in the Airflow cluster with pagination support.

Args: limit: Maximum number of DAGs to return (default: 20) offset: Number of DAGs to skip for pagination (default: 0) fetch_all: If True, fetches all DAGs regardless of limit/offset id_contains: Filter DAGs by ID containing this string name_contains: Filter DAGs by display name containing this string

Returns: Dict containing dags list, pagination info, and total counts

get_dag

[Tool Role]: Retrieves detailed information for a specific DAG.

Args: dag_id: The DAG ID to get details for

Returns: Comprehensive DAG details

get_dags_detailed_batch

[Tool Role]: Retrieves detailed information for multiple DAGs in batch with latest run information.

running_dags

[Tool Role]: Lists all currently running DAG runs in the Airflow cluster.

failed_dags

[Tool Role]: Lists all recently failed DAG runs in the Airflow cluster.

trigger_dag

[Tool Role]: Triggers a new DAG run for a specified Airflow DAG.

pause_dag

[Tool Role]: Pauses the specified Airflow DAG (prevents scheduling new runs).

unpause_dag

[Tool Role]: Unpauses the specified Airflow DAG (allows scheduling new runs).

dag_graph

[Tool Role]: Retrieves task graph structure for the specified DAG.

list_tasks

[Tool Role]: Lists all tasks within the specified DAG.

dag_code

[Tool Role]: Retrieves the source code for the specified DAG.

list_event_logs

[Tool Role]: Lists event logs from Airflow.

get_event_log

[Tool Role]: Retrieves a specific event log entry.

all_dag_event_summary

[Tool Role]: Provides summary of event logs across all DAGs.

list_import_errors

[Tool Role]: Lists import errors in Airflow.

get_import_error

[Tool Role]: Retrieves a specific import error.

all_dag_import_summary

[Tool Role]: Provides summary of import errors across all DAGs.

dag_run_duration

[Tool Role]: Analyzes DAG run durations and performance metrics.

dag_task_duration

[Tool Role]: Analyzes task durations within a DAG run.

dag_calendar

[Tool Role]: Shows DAG schedule and execution calendar for a date range.

get_health

[Tool Role]: Checks Airflow cluster health status.

get_version

[Tool Role]: Gets Airflow version information.

get_config

[Tool Role]: Retrieves Airflow configuration.

list_config_sections

[Tool Role]: Lists all configuration sections with summary.

get_config_section

[Tool Role]: Gets all options within a specific configuration section.

search_config_options

[Tool Role]: Searches for configuration options matching a term.

list_pools

[Tool Role]: Lists all pools in Airflow.

get_pool

[Tool Role]: Gets details for a specific pool.

list_task_instances_all

[Tool Role]: Lists task instances with comprehensive filtering options.

get_task_instance_details

[Tool Role]: Gets detailed information for a specific task instance.

list_task_instances_batch

[Tool Role]: Lists task instances in batch with date and state filtering.

get_task_instance_extra_links

[Tool Role]: Gets extra links for a task instance.

get_task_instance_logs

[Tool Role]: Retrieves logs for a specific task instance.

list_variables

[Tool Role]: Lists all variables in Airflow.

get_variable

[Tool Role]: Gets the value of a specific variable.

list_xcom_entries

[Tool Role]: Lists XCom entries for a specific task instance.

get_xcom_entry

[Tool Role]: Gets a specific XCom entry.

list_connections

[Tool Role]: Lists all connections in Airflow.

get_connection

[Tool Role]: Gets details for a specific connection.

create_connection

[Tool Role]: Creates a new connection.

update_connection

[Tool Role]: Updates an existing connection.

delete_connection

[Tool Role]: Deletes a connection.

list_users

[Tool Role]: Lists all users in the Airflow system (v1 API only).

get_user

[Tool Role]: Gets details of a specific user (v1 API only).

list_permissions

[Tool Role]: Lists all permissions available in the Airflow system (v1 API only).

list_roles

[Tool Role]: Lists all roles in the Airflow system (v1 API only).

list_plugins

[Tool Role]: Lists all installed plugins in the Airflow system.

list_providers

[Tool Role]: Lists all provider packages installed in the Airflow system.

get_provider

[Tool Role]: Gets details of a specific provider package.

list_datasets

[Tool Role]: Lists all datasets in the Airflow system (v1 API only - v2 uses Assets).

get_dataset

[Tool Role]: Gets details of a specific dataset (v1 API only - v2 uses Assets).

list_dataset_events

[Tool Role]: Lists dataset events for data lineage tracking (v1 API only - v2 uses Assets).

get_dataset_events

[Tool Role]: Gets events for a specific dataset (v1 API only - v2 uses Assets).

Prompts

Interactive templates invoked by user choice

NameDescription
airflow_cluster_monitoringComprehensive Airflow cluster monitoring assistant. Args: dag_name: Specific DAG to focus on (optional) time_range: Time range for analysis (default: "today")
airflow_troubleshootingSpecialized Airflow troubleshooting assistant. Args: issue_type: Type of issue (failed_tasks, slow_dags, resource_issues, general) severity: Issue severity (low, medium, high, critical)
airflow_dag_analysisDAG analysis and optimization assistant. Args: analysis_type: Type of analysis (overview, performance, dependencies, configuration) dag_pattern: Pattern to filter DAGs (optional)

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/call518/MCP-Airflow-API'

If you have feedback or need assistance with the MCP directory API, please join our Discord server