execute_code

MCP tool from Openstaad MCP by BentleySystems

Runs validated Python code against the connected STAAD.Pro model

How to use it

execute_code is exposed by the Openstaad MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the execute_code tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Openstaad MCP

$uvx --from git+https://github.com/BentleySystems/openstaad-mcp openstaad-mcp

FULL OPENSTAAD MCP LISTING

Other tools in Openstaad MCP (7)

discover_api

Lists available API skills and usage guidance

get_status

Returns connection state, STAAD version, model path, analysis status

input_data_path

Path to a .csv or .xlsx file. The server reads and parses it, then injects as the inputdata variable in the sandbox.

list_instances

Lists active STAAD.Pro instances with model paths and versions

output_data_path

Path where the sandbox return value will be written. The return value must be a list-of-lists (CSV) or a {sheetname: {columns, rows}} dict (multi-sheet XLSX).

overwrite

Allow overwriting an existing output file (default false).

read_skills

Returns detailed guidance for requested skills