MCP-Airflow-API

MCPOpen SourceMIT57.5

by call518 • Uncategorized

An MCP server enabling natural language management of Apache Airflow workflows via REST API abstraction.

Example Use Cases

1
Manage and monitor Apache Airflow workflows using natural language commands.
2
Integrate Airflow cluster status and task execution data into AI-driven automation workflows.
3
Dynamic support for multiple Airflow API versions with secure remote access.

Description

MCP-Airflow-API transforms Apache Airflow REST API operations into intuitive natural language tools, allowing users to manage Airflow clusters without complex API calls. It supports both Airflow API v1 (2.x) and v2 (3.0+) dynamically, providing comprehensive coverage of Airflow functionalities including DAG management, task monitoring, and asset management. The server supports local and remote deployment modes with secure authentication options, and integrates seamlessly with AI agents via the Model Context Protocol (MCP).

Capabilities(57 total)

Tools (54)

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

section:anymode:any

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

limit:integeroffset:integerfetch_all:booleanid_contains:anyname_contains:any

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

dag_id:string*

get_dags_detailed_batch

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

limit:integeroffset:integerfetch_all:booleanid_contains:anyname_contains:anyis_active:anyis_paused:any

running_dags

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

Prompts (3)

airflow_cluster_monitoring

Comprehensive Airflow cluster monitoring assistant. Args: dag_name: Specific DAG to focus on (optional) time_range: Time range for analysis (default: "today")

dag_nametime_range

airflow_troubleshooting

Specialized Airflow troubleshooting assistant. Args: issue_type: Type of issue (failed_tasks, slow_dags, resource_issues, general) severity: Issue severity (low, medium, high, critical)

issue_typeseverity

airflow_dag_analysis

DAG analysis and optimization assistant. Args: analysis_type: Type of analysis (overview, performance, dependencies, configuration) dag_pattern: Pattern to filter DAGs (optional)

analysis_typedag_pattern

Quick Actions

View on GitHub

Security

Scanned 1 month(s) ago

Risk Level

LOW

Reads external data but no write or execute capability

Trust Score

C59/100

10/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities54 Tools / 3 Prompts / 0 Resources

Ownercall518

CategoryUncategorized

DependenciesStandalone

Set Your Username