Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Export

export

Export KOMPAS-3D documents to STEP, IGES, STL, PDF, DXF, or SVG as a background job that leaves the sources unmodified; poll job status until the export finishes.

Instructions

Export documents to exchange formats as a background JOB (one checkpoint per file): returns the job state after wait_s; poll job_status(job_id) until status is done/partial/failed. Sources are never modified. File names: . in out_dir. STEP/IGES headers carry no local paths or Windows user name. Drawings are exported from their saved file (save first).

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": {
      "sources": "<sources>",
      "formats": "<formats>",
      "out_dir": "<out_dir>"
    },
    "name": "export"
  }
}

Input Schema

NameRequiredDescriptionDefault
authorNoauthor written into STEP/IGES headers (default: none)
verifyNore-open exported STEP/IGES and compare the volume (±0.1 %)
wait_sNowait up to this long before returning
formatsYes3D: step214, step242, iges, stl, png; drawings: pdf, dxf (mm, 1:1), dwg (AutoCAD 2018, mm 1:1, header says inches), svg, png; specifications: pdf, xlsx, ods
out_dirYesexisting folder inside the allowed roots
sourcesYesdocument handles
overwriteNoreplace existing files (only after the user agreed)
organizationNoorganisation for STEP/IGES headers

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.0
    • changedInput schema / properties / formats / description
      Previous value: -"3D: step214, step242, iges, stl, png; drawings: pdf, dxf (mm, 1:1), svg, png"New value: +"3D: step214, step242, iges, stl, png; drawings: pdf, dxf (mm, 1:1), dwg (AutoCAD 2018, mm 1:1, header says inches), svg, png; specifications: pdf, xlsx, ods"
    • changedInput schema / properties / formats / items / enum
      Previous value: -[
      -  "step214",
      -  "step242",
      -  "iges",
      -  "stl",
      -  "png",
      -  "pdf",
      -  "svg",
      -  "dxf"
      -]New value: +[
      +  "step214",
      +  "step242",
      +  "iges",
      +  "stl",
      +  "png",
      +  "pdf",
      +  "svg",
      +  "dxf",
      +  "dwg",
      +  "xlsx",
      +  "ods"
      +]
  2. First observedv0.4.2

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare it is not read-only and not destructive; the description goes well beyond by disclosing the asynchronous job model with one checkpoint per file, that source documents are never modified, and the privacy guarantee that STEP/IGES headers carry no local paths or Windows user names. It also specifies the output file naming pattern and the save-first precondition for drawings.

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 async-job fact, then packs polling, source safety, naming, header privacy, and the drawing precondition into short clauses with no filler. Every sentence carries distinct information an agent needs to call the tool correctly.

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 an eight-parameter, mutation-adjacent tool with no output schema, the description covers the return shape (job state), the polling loop, file naming, and safety guarantees. It leaves the meaning of the 'partial' terminal status unexplained and does not describe what the job state object contains, but the essentials are present.

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%, so all eight parameters are already documented in structured form; the description adds only marginal meaning beyond that, clarifying wait_s as the pre-return wait and out_dir through the '<document name>.<ext>' naming rule. It does not elaborate on formats, author, organization, or verify beyond what the schema states.

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 ('Export documents to exchange formats') and immediately qualifies the execution model ('as a background JOB'), which is the distinguishing trait versus a synchronous save. An agent can tell this apart from doc_save or batch without inspecting 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 operating instructions: returns after wait_s, then poll job_status(job_id) until done/partial/failed, and save drawings before exporting them. It names the follow-up tool explicitly but does not contrast itself against other export-like siblings or state when not to use it.

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