:class:`FluidsLeafMCP`
======================


.. py:class:: ansys.cfx.mcp.common.base.FluidsLeafMCP(*, backends: dict[str, ansys.cfx.mcp.common.backend.Backend], expose_tools: Iterable[str] = ALL_TOOLS, hide_connection_tools: bool = False, conversation_store: Optional[ansys.cfx.mcp.common.conversation.ConversationStore] = None, codegen_pipeline: Optional[ansys.cfx.mcp.common.codegen.CodegenPipeline] = None, name: Optional[str] = None, **fastmcp_kwargs: Any)

   Bases: :py:obj:`ansys.common.mcp.server.PyAnsysBaseMCP`


   
   Base server class for a single shared MCP leaf.
















   ..
       !! processed by numpydoc !!


.. py:currentmodule:: FluidsLeafMCP

Overview
--------

.. tab-set::



   .. tab-item:: Methods

      .. list-table::
          :header-rows: 0
          :widths: auto

          * - :py:attr:`~run`
            - Run the MCP server event loop for the configured transport.
          * - :py:attr:`~product_startup`
            - Run product-specific startup hooks before serving MCP requests.
          * - :py:attr:`~product_cleanup`
            - Run product-specific cleanup hooks before shutdown.
          * - :py:attr:`~build_toolsets`
            - Build toolset metadata for the tools exposed by this leaf server.
          * - :py:attr:`~register_run_code_observer`
            - Register a callback that observes successful run-code executions.


   .. tab-item:: Properties

      .. list-table::
          :header-rows: 0
          :widths: auto

          * - :py:attr:`~backend`
            - Return the currently active backend instance.


   .. tab-item:: Attributes

      .. list-table::
          :header-rows: 0
          :widths: auto

          * - :py:attr:`~leaf_name`
            - 
          * - :py:attr:`~default_backend_kind`
            - 
          * - :py:attr:`~cache_ttl_seconds`
            - 
          * - :py:attr:`~connect_on_startup`
            - 
          * - :py:attr:`~component_label`
            - 
          * - :py:attr:`~error_remediation_description`
            - 






Import detail
-------------

.. code-block:: python

    from ansys.cfx.mcp.common.base import FluidsLeafMCP

Property detail
---------------

.. py:property:: backend
   :type: ansys.cfx.mcp.common.backend.Backend


   
   Return the currently active backend instance.





   :Returns:

       :obj:`Backend`
           Value computed by the helper for the requested CFX workflow.











   ..
       !! processed by numpydoc !!



Attribute detail
----------------

.. py:attribute:: leaf_name
   :type:  str
   :value: 'fluids'


.. py:attribute:: default_backend_kind
   :type:  Optional[str]
   :value: None


.. py:attribute:: cache_ttl_seconds
   :type:  float
   :value: 30.0


.. py:attribute:: connect_on_startup
   :type:  bool
   :value: False


.. py:attribute:: component_label
   :type:  str
   :value: ''


.. py:attribute:: error_remediation_description
   :type:  str
   :value: 'Generate a Markdown remediation / how-to answer for a natural-language request (error message,...




Method detail
-------------

.. py:method:: run(transport: str = 'stdio', host: str | None = None, port: int | None = None) -> None

   
   Run the MCP server event loop for the configured transport.


   :Parameters:

       **transport** : :class:`python:str`, :obj:`optional`
           LLM transport implementation to use. Default is ``'stdio'``.

       **host** : :class:`python:str` | :data:`python:None`, :obj:`optional`
           Host interface for the MCP transport. Default is ``None``.

       **port** : :class:`python:int` | :data:`python:None`, :obj:`optional`
           Port of the running CFX service to attach to. Default is ``None``.



   :Returns:

       :data:`python:None`
           No value is returned; side effects are applied to the relevant cache, session, or
           server.











   ..
       !! processed by numpydoc !!

.. py:method:: product_startup() -> None

   
   Run product-specific startup hooks before serving MCP requests.





   :Returns:

       :data:`python:None`
           No value is returned; side effects are applied to the relevant cache, session, or
           server.











   ..
       !! processed by numpydoc !!

.. py:method:: product_cleanup() -> None

   
   Run product-specific cleanup hooks before shutdown.





   :Returns:

       :data:`python:None`
           No value is returned; side effects are applied to the relevant cache, session, or
           server.











   ..
       !! processed by numpydoc !!

.. py:method:: build_toolsets() -> list[dict[str, Any]]

   
   Build toolset metadata for the tools exposed by this leaf server.





   :Returns:

       :class:`python:list`\[:class:`python:dict`\[:class:`python:str`, :obj:`Any`]]
           List of structured records matching the request.











   ..
       !! processed by numpydoc !!

.. py:method:: register_run_code_observer(observer: Callable[Ellipsis, Awaitable[None] | None]) -> None

   
   Register a callback that observes successful run-code executions.


   :Parameters:

       **observer** : :obj:`Callable`\[..., :obj:`Awaitable`\[:data:`python:None`] | :data:`python:None`]
           Callback to notify after run-code execution.



   :Returns:

       :data:`python:None`
           No value is returned; the callback is stored for later notifications.











   ..
       !! processed by numpydoc !!