Report configured workspace, optional backend availability, and execution gate.

Create a staged prompt-driven modeling job without running the LLM or simulator.

Run modeling stages through the requested stage and save all intermediate artifacts.

Generate a complete Python model artifact without starting AEDT or using a license.

The returned file is safe to import offline. It exposes build(hfss); calling that function later requires an explicitly supplied, licensed PyAEDT HFSS object.

Record the user's HFSS/image comparison notes without running or changing AEDT.

Use recorded feedback to produce the next versioned Python model, still without AEDT.

Recognize topology, labels, dimensions, materials, and uncertainties in antenna images/PDFs.

Reconcile raw visual evidence with extracted text; produces a hash-frozen review candidate.

Approve the reviewed source candidate before downstream model/code generation.

Apply a reviewed source audit deterministically and issue a new hash-frozen candidate.

Propose a value for a null/unresolved source parameter and return its review hash.

Approve the exact hash-frozen engineering assumption candidate after user review.

Deterministically compile approved evidence and assumptions into reviewed HFSS artifacts.

Hash every generated artifact and return the approval token required for HFSS execution.

Build reviewed artifacts; any edit after review invalidates the supplied approval hash.

Copy an existing HFSS project into an isolated job and prepare black-box optimization.

Run HFSS trials. Requires ANTENNA_MCP_ALLOW_SIMULATION=1 and never overwrites the source project.

Read current job state and artifact paths.

Create one end-to-end job spanning multimodal understanding, HFSS build, and optimization.

Run source understanding through optimization planning, then stop at the artifact review gate.

Build the approved pipeline model and stop before expensive optimization.

Run the planned HFSS optimization and produce the best project plus complete trial history.