Skip to main content
Glama
Sign In
ls-dyna-mcp

ls-dyna-mcp

by codersag
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

run_lsprepost

Execute LS-PrePost command files to automate post-processing in an allowed working directory, with optional headless mode and a hard timeout that kills the process tree.

Instructions

DISABLED unless the server is started with LSDYNA_MCP_ENABLE_LSPREPOST=1. Run an LS-PrePost command file (post-processing automation) in working_dir (must be an allowed folder). headless=True uses 'runc=' (no graphics: only non-graphical commands work); False uses 'c= -nographics'. The call runs on a worker thread with a hard timeout (at most 900 s) that kills the whole process tree. Files created are listed. Args: commands (cfile text, at most 20000 characters), working_dir, headless, timeout_s

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "commands": "<commands>",
      "working_dir": "<working_dir>"
    },
    "name": "run_lsprepost"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandsYes
headlessNo
timeout_sNo
working_dirYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.2

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the env-var gate, the worker-thread execution, a hard timeout capped at 900 s that kills the entire process tree, and that created files are reported. It does not state what happens to partial output when a timeout fires or how failures surface, leaving a meaningful gap for a process-spawning tool.

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

Conciseness4/5

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

Front-loads the most consequential fact (the DISABLED gate) and then covers mode and timeout behavior compactly. The trailing 'Args:' line slightly restates parameter names but does add non-obvious semantics such as the character cap and allowed-folder constraint.

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

Completeness4/5

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

For a 4-param process-execution tool with an output schema present, the description covers gating, execution model, timeout/kill behavior, headless modes, and that output files are listed. Remaining gaps — error/failure reporting and whether files persist after a kill — are minor given the output schema.

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 0%, so the description must supply all parameter meaning, and it largely does: commands is cfile text capped at 20000 chars, working_dir must be an allowed folder, headless toggles 'runc=' vs 'c= -nographics', and timeout_s is bounded by the 900 s hard cap. The timeout_s default (300) and the exact per-call vs overall nature of the timeout are only implied.

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 — 'Run an LS-PrePost command file (post-processing automation)' — plus the target directory. The resource is clearly distinct from sibling script/job runners like run_mechanical_script and submit_lsdyna_job, so an agent can route without opening the schema.

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 concrete preconditions: disabled unless LSDYNA_MCP_ENABLE_LSPREPOST=1, and working_dir must be an allowed folder. It also scopes headless=True to non-graphical commands only. It does not explicitly contrast with sibling automation tools (e.g. run_mechanical_script), so routing between them is left partly to inference.

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

Deploy Server

Other Tools