Skip to main content
Glama
yangkyeongmo

MCP Server for Apache Airflow

by yangkyeongmo

get_dag_source

Retrieve DAG source code from Apache Airflow using a file token to access and review workflow definitions.

Instructions

Get a source code

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_tokenYes

Implementation Reference

  • The handler function for the 'get_dag_source' tool. It takes a file_token, calls the Airflow DAG API to retrieve the DAG source, converts the response to a dictionary string, and returns it as MCP TextContent.
    async def get_dag_source(file_token: str) -> List[Union[types.TextContent, types.ImageContent, types.EmbeddedResource]]:
        response = dag_api.get_dag_source(file_token=file_token)
        return [types.TextContent(type="text", text=str(response.to_dict()))]
  • Registers the 'get_dag_source' tool (4th entry) along with other DAG-related tools. This function is imported into src/main.py and its output used to add tools to the MCP server.
    def get_all_functions() -> list[tuple[Callable, str, str, bool]]:
        """Return list of (function, name, description, is_read_only) tuples for registration."""
        return [
            (get_dags, "fetch_dags", "Fetch all DAGs", True),
            (get_dag, "get_dag", "Get a DAG by ID", True),
            (get_dag_details, "get_dag_details", "Get a simplified representation of DAG", True),
            (get_dag_source, "get_dag_source", "Get a source code", True),
            (pause_dag, "pause_dag", "Pause a DAG by ID", False),
            (unpause_dag, "unpause_dag", "Unpause a DAG by ID", False),
            (get_dag_tasks, "get_dag_tasks", "Get tasks for DAG", True),
            (get_task, "get_task", "Get a task by ID", True),
            (get_tasks, "get_tasks", "Get tasks for DAG", True),
            (patch_dag, "patch_dag", "Update a DAG", False),
            (patch_dags, "patch_dags", "Update multiple DAGs", False),
            (delete_dag, "delete_dag", "Delete a DAG", False),
            (clear_task_instances, "clear_task_instances", "Clear a set of task instances", False),
            (set_task_instances_state, "set_task_instances_state", "Set a state of task instances", False),
            (reparse_dag_file, "reparse_dag_file", "Request re-parsing of a DAG file", False),
        ]
  • src/main.py:95-96 (registration)
    The loop in main() that adds all tools from module get_all_functions, including get_dag_source from dag.py, to the MCP app using Tool.from_function.
    for func, name, description, *_ in functions:
        app.add_tool(Tool.from_function(func, name=name, description=description))
  • src/main.py:8-8 (registration)
    Imports the get_all_functions from dag.py, which includes the get_dag_source registration.
    from src.airflow.dag import get_all_functions as get_dag_functions

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/yangkyeongmo/mcp-server-apache-airflow'

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