Skip to main content
Glama
nikhil-ganage

MCP Server Airflow Token

get_xcom_entry

Retrieve cross-communication data between Airflow tasks by specifying DAG, run, task, and XCom key parameters.

Instructions

Get an XCom entry

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dag_idYes
dag_run_idYes
task_idYes
xcom_keyYes
map_indexNo
deserializeNo
stringifyNo

Implementation Reference

  • The async handler function that implements the logic for the 'get_xcom_entry' tool by calling the Airflow XCom API and formatting the response as MCP TextContent.
    async def get_xcom_entry(
        dag_id: str,
        dag_run_id: str,
        task_id: str,
        xcom_key: str,
        map_index: Optional[int] = None,
        deserialize: Optional[bool] = None,
        stringify: Optional[bool] = None,
    ) -> List[Union[types.TextContent, types.ImageContent, types.EmbeddedResource]]:
        # Build parameters dictionary
        kwargs: Dict[str, Any] = {}
        if map_index is not None:
            kwargs["map_index"] = map_index
        if deserialize is not None:
            kwargs["deserialize"] = deserialize
        if stringify is not None:
            kwargs["stringify"] = stringify
    
        response = xcom_api.get_xcom_entry(
            dag_id=dag_id, dag_run_id=dag_run_id, task_id=task_id, xcom_key=xcom_key, **kwargs
        )
        return [types.TextContent(type="text", text=str(response.to_dict()))]
  • The registration function that provides the tuple for the 'get_xcom_entry' tool, including its name, description, and read-only flag, which is imported and used in main.py to register the tool via app.add_tool.
    def get_all_functions() -> list[tuple[Callable, str, str, bool]]:
        """Return list of (function, name, description, is_read_only) tuples for registration."""
        return [
            (get_xcom_entries, "get_xcom_entries", "Get all XCom entries", True),
            (get_xcom_entry, "get_xcom_entry", "Get an XCom entry", True),
        ]

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/nikhil-ganage/mcp-server-airflow-token'

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