MWAA MCP Server

Instructions

Implementation Reference

• awslabs/mwaa_mcp_server/tools.py:312-318 (handler)

  The actual implementation of the get_dag_run tool logic, which interacts with the Airflow API.

  async def get_dag_run(
      self, environment_name: str, dag_id: str, dag_run_id: str
  ) -> Dict[str, Any]:
      """Get DAG run details via Airflow API."""
      return self._invoke_airflow_api(
          environment_name, "GET", f"/dags/{dag_id}/dagRuns/{dag_run_id}"
      )

• awslabs/mwaa_mcp_server/server.py:335-351 (registration)

  The registration of the get_dag_run MCP tool, which acts as a wrapper calling the implementation in tools.py.

  @mcp.tool(name="get_dag_run")
  async def get_dag_run(
      environment_name: str,
      dag_id: str,
      dag_run_id: str,
  ) -> Dict[str, Any]:
      """Get details about a specific DAG run.
  
      Args:
          environment_name: Name of the MWAA environment
          dag_id: The DAG ID
          dag_run_id: The DAG run ID
  
      Returns:
          Dictionary containing DAG run details including state and timing
      """
      return await tools.get_dag_run(environment_name, dag_id, dag_run_id)