Skip to main content
Glama
Svel26

Sigmatek LASAL MCP Server

by Svel26
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

build_project

Compile a LASAL CLASS 2 project or download it to a PLC, with optional background jobs that return a jobId to poll for completion.

Instructions

Compile the CLASS 2 project or download it to the PLC. Compilation kills CLASS 2 IDE. Download pings the PLC first. Supports async: true — the call then returns immediately with a jobId and you MUST poll check_job_status until it reports status completed/failed (the result is delivered there).

Input Schema

NameRequiredDescriptionDefault
asyncNoRun in the background: returns { status: 'pending', jobId } — poll with check_job_status. Default false.
actionYes'compile' builds the project; 'download' transfers it to the PLC.
optionsNoCompile mode (compile only). RebuildAll is safest; BuildChanges is faster for incremental work.RebuildAll
lcp_pathNoAbsolute path to the .lcp file. Omit to use the selected project.
timeout_sNoTimeout in seconds for compile or download. Omit for default (600s).
connectionNoConnection string (e.g. 'TCPIP:192.168.1.100') or address-book name (download only). Omit to use the connection saved in the .lss file.
add_loader_anywayNoForce loader download even if the target OS already has a compatible loader (download only). Default: auto — the loader is sent for local LARS/loopback targets, skipped otherwise. Set false to disable, true to force.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.3.2
    • removedInput schema / properties / add_loader_anyway / default
      Removed value: -false
    • changedInput schema / properties / add_loader_anyway / description
      Previous value: -"Force loader download even if the target OS already has a compatible loader (download only)."New value: +"Force loader download even if the target OS already has a compatible loader (download only). Default: auto — the loader is sent for local LARS/loopback targets, skipped otherwise. Set false to disable, true to force."
    • addedInput schema / properties / async
      Added value: +{
+  "default": false,
+  "description": "Run in the background: returns { status: 'pending', jobId } — poll with check_job_status. Default false.",
+  "type": "boolean"
+}
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Only openWorldHint is annotated, so the description carries the burden and does so well: it discloses the side effect that compilation kills the CLASS 2 IDE, that download pings the PLC first, and that async returns a jobId whose result must be retrieved via check_job_status. This is exactly the destructive/lifecycle context annotations do not provide.

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?

Front-loaded with the core verb/resource, then builds outward to side effects and async workflow. Every sentence carries distinct, non-redundant information with no filler.

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 7-parameter build/deploy tool with no output schema, it covers the critical gaps: side effects, the PLC ping, and the async job/poll workflow. It stops short of describing the sync return value or result shape, a minor omission given the otherwise strong behavioral coverage.

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

Parameters3/5

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

Schema description coverage is 100% and the schema already documents action, options, async, timeout, connection, lcp_path, and add_loader_anyway in detail. The description reinforces the async parameter's return contract but adds little meaning beyond what the structured fields already contain, so baseline 3 applies.

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 specific verbs (compile/download) and resource (CLASS 2 project), and explicitly names the sibling it hands off to (check_job_status) when async is used. An agent can tell it apart from deploy_all/deploy_solution without opening any 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 clear operational context: compile vs download distinction is present, async usage is spelled out with the mandatory polling loop. It does not, however, contrast this tool against the other deployment siblings (deploy_all, deploy_solution), so the alternative-choice guidance is incomplete.

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