Skip to main content
Glama
david-mamani

ETABS MCP Server

by david-mamani

Execute Python code

execute_code
Destructive

Run sandboxed Python against the ETABS COM API to query, analyze, design, or extract reports from a live model using a pre-connected SapModel object.

Instructions

Execute Python code in a sandbox against the ETABS COM API (call discover_api and read_skills first).

The sandbox provides a pre-connected model variable (SapModel) and optional input_data (if input_data_path is provided), plus json and math modules. import statements, dir(), getattr(), and dunder access are BLOCKED.

The last expression value or an explicit result = ... assignment is returned.

Input Schema

NameRequiredDescriptionDefault
codeYesPython source code to execute. Use ``model`` (SapModel) to interact with ETABS.
instanceNoAlias from ``list_instances`` (e.g. ``etabs1``). Omit when only one instance runs.
overwriteNoAllow overwriting an existing output file.
input_data_pathNoPath to a ``.csv`` or ``.xlsx`` file. Content is injected as immutable ``input_data``.
output_data_pathNoPath to write the ``result`` value as ``.csv`` or ``.xlsx``. ``result`` must be a list-of-lists (flat) or dict of sheet dicts (multi-sheet).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds meaningful sandbox behavior beyond the annotations: blocked imports, dir(), getattr(), and dunder access, plus how model, input_data, json, and math are provided. It also explains the return mechanism, though it does not cover error handling or timeout behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three tight sentences, front-loads the core action, and includes only operationally useful constraints. No sentence is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the annotations, full schema coverage, and output schema, the description supplies the key sandbox constraints and execution model an agent needs. It is complete enough for a destructive code-execution tool whose schema already documents instance, overwrite, and output paths.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameter documentation is already strong. The description still adds useful semantics for code execution by explaining the pre-connected model variable, optional input_data injection, and result return path.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: execute Python code in a sandbox against the ETABS COM API. It also names prerequisites (discover_api and read_skills first), which helps an agent distinguish this from simpler API-discovery siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear prerequisite to call discover_api and read_skills first before using this tool. It does not explicitly say when to choose this over siblings like get_model_geometry, but the usage context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.