MCP Server for SketchUp

export_scene

Export the current SketchUp scene to a temp file as SKP, OBJ, DAE, STL, PNG, or JPG for sharing, archiving, or viewport renders.

Instructions

Export the current scene to a temp file on the SketchUp host.

Formats: skp (native), obj / dae / stl (geometry), png / jpg (viewport render, default 1920×1080). The file is written on the machine running SketchUp — on a split-host setup the path is not directly readable here.

Returns: JSON {path, format} plus a "warning" field when exporting skp from a never-saved model (SketchUp binds the live document to the export path — relay the warning to the user).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "export_scene"
  }
}

Input Schema

Name	Required	Description	Default
`format`	No	skp (native), obj / dae / stl (geometry), png / jpg (viewport render)	skp

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Sep 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses important behavioral traits: the file is written on the SketchUp host, split-host path unreadability, and a warning field for certain exports. It does not explicitly state that the tool is non-destructive to the model, but the verb 'export' implies reading the scene without modification.

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?

The description is concise with a clear front-loaded purpose statement, followed by compact listing of formats and return information. Every sentence adds value without redundancy.

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 single-parameter tool with an output schema, the description covers the essential behavior, return format, and an edge case (warning for never-saved models). Minor gaps include file naming conventions and how to access files on split-host setups, but these are acceptable given the output schema likely provides additional structure.

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?

The schema has one parameter 'format' with enums and a default. The description adds meaning beyond the schema by noting that skp is native, obj/dae/stl are geometry, png/jpg are viewport renders with default resolution 1920x1080. This provides valuable context for the AI agent.

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?

The description clearly states the tool exports the current scene to a temp file, lists all supported formats (skp, obj, dae, stl, png, jpg), and distinguishes it from sibling tools like get_viewport_screenshot which captures a viewport image without exporting.

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?

The description provides context about the export destination (SketchUp host), split-host implications, and warning conditions for skp exports from unsaved models. However, it does not explicitly state when to use this tool versus alternatives like get_viewport_screenshot for image-only needs.

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