Skip to main content
Glama
PyAEDT-MCP
by yuxuan6426

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

You are an expert AEDT (Ansys Electronics Desktop) simulation assistant powered by PyAEDT. You help engineers create, configure, run, and post-process electromagnetic, thermal, and circuit simulations across all AEDT applications.

Use this MCP for AEDT work whenever a supported tool exists. Do not treat this MCP as a code generator: if a workflow is not covered by a tool, the LLM must write the PyAEDT code directly and should usually execute it with run_python_code.

Current tools

PyAEDT-MCP exposes the full tool surface from startup. Some tools require an active AEDT session, but they remain visible so you can plan workflows before connecting.

Always visible tools to establish or inspect connectivity:

  • check_aedt_installed: Verify an AEDT installation exists.

  • check_aedt_status: Detect whether this MCP server already holds an active AEDT session and list discoverable local AEDT sessions. (Use it to decide between launch_aedt and connect_to_aedt.)

  • launch_aedt: Start a new AEDT session.

  • connect_to_aedt: Connect to an already-running AEDT instance.

  • get_pyaedt_logs: Read PyAEDT file logs and native AEDT Desktop messages for the active project and design.

Also visible from startup, but callable only after AEDT is connected:

  • Lifecycle: disconnect_from_aedt

  • Project/design: list_designs, list_projects, open_project, save_project, create_design, validate_design, analyze_design

  • Execution: run_python_script, run_python_code

  • Export/inspection: export_results, screenshot, export_config, get_model_info

  • Utility: clear_aedt

Rules

  1. Before any AEDT call, run check_aedt_installed first.

  2. First call check_aedt_status to see whether this MCP is already connected to an AEDT session and which local AEDT sessions are available. If the tool reports multiple connectable sessions, ask the user which session to connect to and include the option to open a new session instead. If the tool reports one connectable session, ask whether to connect to it or open a new session. Prefer connect_to_aedt whenever a connectable session exists. Only call launch_aedt(confirm_new_session=True) after the user explicitly confirms they want a new AEDT instance. If the user directly asks for a new instance or a new AEDT session, skip the question and call launch_aedt(confirm_new_session=True).

  3. After the session exists, check_aedt_status reports full project and design information. If the connected session has no open projects and the user asked for a specific solver such as Hfss, Maxwell3d, or Icepak, call create_design with the matching app_type to create a new design in that session. Prefer direct MCP tools for supported AEDT operations.

  4. If the MCP lacks a tool for the requested AEDT step, write PyAEDT code directly and prefer run_python_code over run_python_script unless the user already has a script file.

  5. When the user asks to build, modify, or troubleshoot a specific design, call validate_design programmatically after design changes and before calling analyze_design.

  6. Call get_pyaedt_logs after a failed AEDT operation, validation failure, or unexpected analysis result. Use its native AEDT Desktop messages and PyAEDT file logs to diagnose the issue before retrying or changing the design.

  7. Before code intended for run_python_code, include from ansys.aedt.core import settings, set settings.release_on_exception = False and settings.pyedb_use_grpc = True.

  8. Use the correct PyAEDT app class for the solver: Hfss, Maxwell3d, Maxwell2d, Icepak, Circuit, Q3d, Q2d, TwinBuilder, Mechanical, Emit, RMXprt, Hfss3dLayout.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": true
}
resources
{
  "subscribe": false,
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
display_htmlA

Display self-contained HTML inline or in a detached window.

No AEDT connection is required. Inline scripts and styles are supported, but network requests, external assets, forms, popups, and access to the MCP host are blocked. Embed images as data URLs. This does not execute Python.

In "auto" mode the HTML is shown inline when the client supports MCP Apps. Otherwise it opens in a lightweight detached window (a chromeless Edge/Chrome app window, or the default browser) on the machine running the MCP server. The detached window adjusts to the size of the rendered HTML unless width or height are given.

check_aedt_statusA

Check the status of AEDT initialization.

This tool is always reachable, even before a connection has been established. When no AEDT session is active, it returns a short hint describing how to establish one (launch_aedt or connect_to_aedt). When a session is active, it returns full status information.

This makes the tool the recommended pre-flight call to decide whether to launch_aedt (no active session) or connect_to_aedt (existing session detected).

This tool retrieves comprehensive information from the connected AEDT instance including version, active projects, designs, and connection details.

get_pyaedt_logsA

Return recent PyAEDT file logs and native AEDT Desktop messages.

This tool reads the active PyAEDT global log file and returns a tail view of its contents. When AEDT is connected, it also retrieves native info and error messages for the active project and design. Optionally filter file log lines using a case-insensitive substring.

check_aedt_installedA

Check if AEDT is installed on the system.

This tool checks for valid AEDT installations on the system and returns information about available versions.

When running inside a Docker container, the tool probes the remote gRPC endpoint (AEDT_MACHINE:AEDT_PORT) instead of searching for a local AEDT installation.

launch_aedtB

Launch a new AEDT instance.

This tool starts a new AEDT instance using PyAEDT's Desktop class, or it launches directly into a specific AEDT application session when requested. The launched instance is automatically connected and stored in the context for subsequent operations.

connect_to_aedtA

Connect to an existing AEDT instance via gRPC.

This tool establishes a connection to a running AEDT instance using gRPC. The AEDT instance must be started with a gRPC server enabled: ansysedt.exe -grpcsrv <port>

disconnect_from_aedtA

Disconnect from the AEDT instance.

This tool detaches the MCP session from the AEDT instance and releases associated resources. It can either keep the AEDT window open or close the AEDT desktop entirely.

run_python_scriptA

Launch a PyAEDT script file with CPython without opening a terminal.

The script runs asynchronously using the MCP server's Python interpreter and inherits the connected AEDT session through the same environment variables used by the PyAEDT script launcher. Scripts must use PyAEDT; native globals such as oDesktop, oProject, and oDesign are not injected. Standard output and errors are written to the returned log file.

run_python_codeB

Execute Python code inside AEDT.

This tool runs inline Python code within the AEDT environment. The code has access to the connected AEDT instance via the desktop variable.

list_designsB

List projects and designs for the connected AEDT instance.

list_projectsA

List all open AEDT projects.

open_projectC

Open an AEDT project.

save_projectC

Save an AEDT project.

create_designC

Create a new design in AEDT.

validate_designA

Validate an AEDT design without starting a solve.

analyze_designC

Run analysis on an AEDT design.

export_resultsC

Export simulation results from AEDT.

screenshotB

Capture a screenshot of the current AEDT design view.

This tool captures the current design preview as an image. It supports model views, field plots, and mesh visualizations, depending on what's currently displayed in AEDT.

export_configC

Export the active design configuration as a JSON file.

clear_aedtB

Clear the AEDT state by closing all projects.

get_model_infoC

Get information about the current model/design.

Prompts

Interactive templates invoked by user choice

NameDescription
system_promptSystem prompt for the PyAEDT-MCP simulation assistant. Provides identity, guideline tool dispatch table, core concepts, and workflow rules for AEDT electromagnetic and thermal simulations.

Resources

Contextual data attached and managed by the client

NameDescription
html_app_viewReturn the sandboxed viewer for custom HTML tool results.
toolsets_definitionToolset definitions for PyAnsys MCP service discovery.

TDQS

B3.3/5.0

Scored across 21 tools

Disambiguation4/5

Most tools target a distinct resource+action, and descriptions clarify boundaries like launch_aedt vs connect_to_aedt, and check_aedt_installed vs check_aedt_status. Overlap remains in a few spots: list_designs also returns projects (overlapping list_projects), get_model_info overlaps check_aedt_status's project/design reporting, and run_python_script vs run_python_code differ only subtly in execution context.

Naming Consistency4/5

Nearly all tools follow a clean snake_case verb_noun pattern (launch_aedt, list_projects, create_design, export_results, validate_design). The only deviation is the bare noun 'screenshot', which breaks the otherwise predictable pattern.

Tool Count4/5

21 tools is on the higher side but each maps to a real capability across connection lifecycle, project/design management, script execution, and reporting. The set is somewhat broad, with display_html being peripheral to the core AEDT workflow, but nothing feels redundant filler.

Completeness3/5

Core workflows (launch/connect, project open/save, design create/validate/analyze, results export, script execution) are covered. However there are notable asymmetries: no create_project or close_project, no delete operations for projects/designs, and export_config has no matching import_config, leaving agents with dead ends for common lifecycle steps.

Maintenance

ActivityActive
ResponsivenessOutdated data