MCP-Airflow-API

Instructions

Implementation Reference

• src/mcp_airflow_api/tools/common_tools.py:563-580 (handler)

  The main handler function for the 'get_health' tool. It checks the Airflow cluster health by making an HTTP request to the appropriate health endpoint (/health for v1, /monitor/health for v2) using the shared airflow_request function.

  @mcp.tool()
  async def get_health() -> Dict[str, Any]:
      """[Tool Role]: Checks Airflow cluster health status."""
      # Import here to avoid circular imports
      from ..functions import get_api_version
      
      api_version = get_api_version()
      
      if api_version == "v2":
          # v2 API: Use /monitor/health endpoint (Airflow 3.x)
          resp = await airflow_request("GET", "/monitor/health")
      else:
          # v1 API: Use /health endpoint (Airflow 2.x)
          resp = await airflow_request("GET", "/health")
      
      resp.raise_for_status()
      return resp.json()

• src/mcp_airflow_api/tools/v1_tools.py:13-28 (registration)

  Registration entry point for v1 tools. Sets the v1-specific airflow_request function and calls register_common_tools(mcp), which defines and registers the get_health handler among others.

  def register_tools(mcp):
      """Register v1 tools by importing common tools with v1 request function."""
      
      logger.info("Initializing MCP server for Airflow API v1")
      logger.info("Loading Airflow API v1 tools (Airflow 2.x)")
      
      # Set the global request function to v1
      common_tools.airflow_request = airflow_request_v1
      
      # Register all 56 common tools (includes management tools)
      common_tools.register_common_tools(mcp)
      
      # V1 has no exclusive tools - all tools are shared with v2
      
      logger.info("Registered all Airflow API v1 tools (56 tools: 43 core + 13 management tools)")

• src/mcp_airflow_api/tools/v2_tools.py:14-104 (registration)

  Registration entry point for v2 tools. Sets the v2-specific airflow_request function and calls register_common_tools(mcp), which defines and registers the get_health handler among others.

  def register_tools(mcp):
      """Register v2 tools: common tools + v2-exclusive asset tools."""
      
      logger.info("Initializing MCP server for Airflow API v2")
      logger.info("Loading Airflow API v2 tools (Airflow 3.0+)")
      
      # Set the global request function to v2
      common_tools.airflow_request = airflow_request_v2
      
      # Register all 43 common tools
      common_tools.register_common_tools(mcp)
      
      # Add V2-exclusive tools (2 tools)
      @mcp.tool()
      async def list_assets(limit: int = 20, offset: int = 0,
                           uri_pattern: Optional[str] = None) -> Dict[str, Any]:
          """
          [V2 New] List all assets in the system for data-aware scheduling.
          
          Assets are a key feature in Airflow 3.0 for data-aware scheduling.
          They enable workflows to be triggered by data changes rather than time schedules.
          
          Args:
              limit: Maximum number of assets to return (default: 20)
              offset: Number of assets to skip for pagination (default: 0)
              uri_pattern: Filter assets by URI pattern (optional)
              
          Returns:
              Dict containing assets list, pagination info, and metadata
          """
          params = {'limit': limit, 'offset': offset}
          if uri_pattern:
              params['uri_pattern'] = uri_pattern
              
          query_string = "&".join([f"{k}={v}" for k, v in params.items()])
          
          resp = await airflow_request_v2("GET", f"/assets?{query_string}")
          resp.raise_for_status()
          data = resp.json()
          
          return {
              "assets": data.get("assets", []),
              "total_entries": data.get("total_entries", 0),
              "limit": limit,
              "offset": offset,
              "api_version": "v2",
              "feature": "assets"
          }
  
      @mcp.tool()
      async def list_asset_events(limit: int = 20, offset: int = 0,
                                 asset_uri: Optional[str] = None,
                                 source_dag_id: Optional[str] = None) -> Dict[str, Any]:
          """
          [V2 New] List asset events for data lineage tracking.
          
          Asset events track when assets are created or updated by DAGs.
          This enables data lineage tracking and data-aware scheduling in Airflow 3.0.
          
          Args:
              limit: Maximum number of events to return (default: 20)
              offset: Number of events to skip for pagination (default: 0)
              asset_uri: Filter events by specific asset URI (optional)
              source_dag_id: Filter events by source DAG that produced the event (optional)
              
          Returns:
              Dict containing asset events list, pagination info, and metadata
          """
          params = {'limit': limit, 'offset': offset}
          if asset_uri:
              params['asset_uri'] = asset_uri
          if source_dag_id:
              params['source_dag_id'] = source_dag_id
              
          query_string = "&".join([f"{k}={v}" for k, v in params.items()])
          
          resp = await airflow_request_v2("GET", f"/assets/events?{query_string}")
          resp.raise_for_status()
          data = resp.json()
          
          return {
              "asset_events": data.get("asset_events", []),
              "total_entries": data.get("total_entries", 0),
              "limit": limit,
              "offset": offset,
              "api_version": "v2",
              "feature": "asset_events"
          }
  
      logger.info("Registered all Airflow API v2 tools (43 common + 2 assets + 4 management = 49 tools)")