:class:`PyLumericalMCP`
=======================


.. py:class:: ansys.lumerical.mcp.server.PyLumericalMCP(config: Optional[ansys.lumerical.mcp.config.Config] = None, python_executable: Optional[str] = None, working_directory: Optional[str] = None, **kwargs)

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


   
   MCP server exposing Ansys Lumerical (via PyLumerical) to LLM agents.

   Hosts a single :class:`PersistentPythonSession` subprocess that owns all
   live Lumerical handles. Multiple named sessions of any product type
   (FDTD/MODE/DEVICE/INTERCONNECT) live in that subprocess as
   ``_lumerical_sessions[name]``. The MCP server only tracks metadata.















   ..
       !! processed by numpydoc !!


.. py:currentmodule:: PyLumericalMCP

Overview
--------

.. tab-set::



   .. tab-item:: Methods

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

          * - :py:attr:`~create_context`
            - Build the typed app context with the Lumerical-aware subprocess.
          * - :py:attr:`~product_startup`
            - Run framework startup logging after subprocess launch.
          * - :py:attr:`~cleanup_python_session`
            - Close Lumerical handles *before* tearing down the subprocess.
          * - :py:attr:`~product_cleanup`
            - No-op: Lumerical handle cleanup happens in ``cleanup_python_session``.
          * - :py:attr:`~product_lifespan`
            - Lifespan wrapper that keeps the event loop responsive on shutdown.








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

.. code-block:: python

    from ansys.lumerical.mcp.server import PyLumericalMCP



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

.. py:method:: create_context() -> ansys.lumerical.mcp.context.PyLumericalContext

   
   Build the typed app context with the Lumerical-aware subprocess.

   Uses :class:`LumericalPersistentPythonSession` so that long, silent
   Lumerical startup phases (``FDTD()`` / ``MODE()`` / ...). Don't trip
   the framework's 0.5 s no-data safety break and lose their output.















   ..
       !! processed by numpydoc !!

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

   
   Run framework startup logging after subprocess launch.
















   ..
       !! processed by numpydoc !!

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

   
   Close Lumerical handles *before* tearing down the subprocess.

   ``_lum_close_all()`` must run while the subprocess is still alive. It
   is flushed here (best-effort, bounded by ``_CLOSE_ALL_JOIN_TIMEOUT_S``
   via a daemon thread) before delegating to the base teardown. Running it
   in ``product_cleanup`` would be too late. The subprocess is gone by
   then, and lumapi's child processes are left orphaned.

   Stays synchronous so direct unit tests work without an event loop;
   :meth:`product_lifespan` offloads the call via :func:`asyncio.to_thread`.















   ..
       !! processed by numpydoc !!

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

   
   No-op: Lumerical handle cleanup happens in ``cleanup_python_session``.
















   ..
       !! processed by numpydoc !!

.. py:method:: product_lifespan(server: fastmcp.FastMCP) -> AsyncIterator[ansys.lumerical.mcp.context.PyLumericalContext]
   :async:


   
   Lifespan wrapper that keeps the event loop responsive on shutdown.

   Identical to the base :meth:`PyAnsysBaseMCP.product_lifespan` except
   that the potentially slow :meth:`cleanup_python_session` (which runs
   ``_lum_close_all()`` against the live subprocess) is dispatched via
   :func:`asyncio.to_thread`, so the synchronous teardown can't freeze
   the event loop and block the STDIO transport from flushing its final
   JSON-RPC writes. Startup stays on the loop -- it's fast and runs
   before any tool traffic.















   ..
       !! processed by numpydoc !!