kernelCAD

Get Catalogue Asset

get_asset

Read-only

Fetch one public catalogue asset by slug. Read-only. No sign-in and no API key. A built-in kit/id returns the free editable downloads.source (.kcad.ts), studio_url, thumbnail_url and license. Download the source with plain GET. Visual scene kits include usage.evaluate_script and usage.render_preview options to build or preview geometry without mechanism checks. This does not verify mechanical behavior. Manufacturing assets retain the default checks. For community slugs, returns the search fields plus params (the knob schema), presets, rig, and public download paths. UNITS: metres, Y is up. stats.size_m and stats.origin_y are metres. RIG: each rig entry is a named pivot. type "rotate" has range in degrees; type "slide" has range in metres; axis is the pivot's local x, y or z. license is the SPDX id to keep with the asset. The download paths are public catalogue routes. Call get_asset_pack for a short-lived signed zip URL. Do not send an API key.

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": {
      "slug": "<slug>"
    },
    "name": "get_asset"
  }
}

Input Schema

Name	Required	Description	Default
`slug`	Yes	Catalogue slug from search_assets.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only say read-only, non-destructive, open-world; the description adds genuine behavior: no auth or API key, three distinct response shapes by asset kind (built-in kit, visual scene kit, community slug, manufacturing asset), what evaluate_script/render_preview usage options do and do not verify, and the licence obligation. Unit conventions (metres, Y up) and rig axis/semantics are extra context an annotations-only reader would lack.

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-loaded with purpose and auth posture, then block-structured UNITS/RIG sections that are easy to scan. The all-caps headers and licence/download repetition make it longer than strictly necessary, but almost every sentence carries operational information.

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?

An output schema exists, so the description need not enumerate return fields, yet the polymorphic response shapes justify the extra detail. Unit and rig conventions cover the remaining ambiguity for a read-heavy catalogue lookup; a note on error behavior for unknown slugs would make it complete.

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% with a single documented slug parameter, so the baseline would be 3. The description adds meaning by distinguishing built-in kit/id slugs from community slugs and noting each yields a different payload, which helps the agent anticipate the input source.

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?

Opens with a specific verb and resource: "Fetch one public catalogue asset by slug." It distinguishes itself from search_assets (lookup source of the slug) and get_asset_pack (signed zip URL), so an agent can pick it out of a very large sibling list 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?

Establishes the retrieval path (search_assets -> slug -> get_asset) and routes packaging to get_asset_pack, plus states no sign-in/API key is needed. It lacks an explicit 'do not use this when...' beyond the download handoff, keeping it short of a 5.

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

All kernelCAD tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.