FluidsLeafMCP

class ansys.fluent.mcp.common.base.FluidsLeafMCP(*, backends: dict[str, ansys.fluent.mcp.common.backend.Backend], expose_tools: Iterable[str] = ALL_TOOLS, name: str | None = None, **fastmcp_kwargs: Any)

Bases: ansys.common.mcp.server.PyAnsysBaseMCP

Base server class for a single Fluids MCP leaf.

Overview

Methods

run	Start the MCP server via the parent implementation when available.
product_startup	No persistent product session at startup. Backends connect lazily.
product_cleanup	Disconnect any active backend at shutdown.
build_toolsets	Build toolset definitions filtered to the tools this leaf exposes.
register_run_code_observer	Register a callable invoked after every run_code tool call.

Properties

backend

Return the active backend instance.

Attributes

leaf_name
default_backend_kind
cache_ttl_seconds
component_label

Import detail

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

Property detail

property FluidsLeafMCP.backend: ansys.fluent.mcp.common.backend.Backend

Return the active backend instance.

Returns:

Backend

Backend produced by the operation.

Attribute detail

FluidsLeafMCP.leaf_name: str = 'fluids'

FluidsLeafMCP.default_backend_kind: str | None = None

FluidsLeafMCP.cache_ttl_seconds: float = 30.0

FluidsLeafMCP.component_label: str = ''

Method detail

FluidsLeafMCP.run(transport: str = 'stdio', host: str | None = None, port: int | None = None) → None

Start the MCP server via the parent implementation when available.

Parameters:

transportstr

Transport name used to run the MCP server.

hoststr | None

Host interface used by the server transport.

portint | None

Port used by the selected server transport.

Returns:

None

The function completes through its side effects.

FluidsLeafMCP.product_startup() → None

No persistent product session at startup. Backends connect lazily.

Returns:

None

The function completes through its side effects.

FluidsLeafMCP.product_cleanup() → None

Disconnect any active backend at shutdown.

Returns:

None

The function completes through its side effects.

FluidsLeafMCP.build_toolsets() → list[dict[str, Any]]

Build toolset definitions filtered to the tools this leaf exposes.

Returns a list of toolset dicts conforming to the PyAnsysMCPService conductor contract.

Returns:

list[dict[str, Any]]

Mapping containing the operation result.

FluidsLeafMCP.register_run_code_observer(observer: Callable[Ellipsis, Awaitable[None] | None]) → None

Register a callable invoked after every run_code tool call.

The observer is called as observer(code=..., result=..., error=...). result is the backend’s RunCodeResult on success (and None on exception); error is the raised exception on failure (and None on success). Observers may be sync or async. Exceptions raised by an observer are logged and swallowed so the original tool result is preserved.

Parameters:

observerCallable[…, Awaitable[None] | None]

Observer callback invoked after run-code execution.

Returns:

None

The function completes through its side effects.