Showoff.dev – AI Mockup Generator

Export the final image

export_image

Renders the finished mockup on the server with the real 3D renderer — models, materials, light, screens, background: exactly what the editor exports, no sketch lines. Returns the image to look at and a download URL (valid 7 days) you can hand on or process further. Takes 5–30 seconds. If the renderer is busy, it says so right away and nothing is charged; call it again after the time it names. Use render_preview for quick checks while building, this for the result. A store set (set_store_set) exports every image in every language as PNG in one ZIP, one folder per store and language (a few minutes; the whole set counts as one export). A set for phones exports both stores, App Store and Google Play. Width and format do not apply there.

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": {
      "project_id": "<project_id>"
    },
    "name": "export_image"
  }
}

Input Schema

Name	Required	Description	Default
`play`	No	Old name for `stores`: false leaves Google Play out.
`width`	No	Output width in pixels; default: the full size of the scene. Leave it out for the final image. Pro exports any size without limit. On Free the default uses the one full-quality export of the month while it is left, then the 720p size (longest edge 1280 px), which Free exports without limit.
`format`	No	File type: "png" (default) or "jpeg" for a smaller file. Store sets are always PNG.	png
`stores`	No	Store sets for phones only (store "iphone" or "play"): which stores to export. Default both, App Store (1320×2868) and Google Play (1080×1920). The second store keeps the width of every image and shows a little less or more of its height, on the side away from the headline.
`folders`	No	Store sets only: how the ZIP is laid out. "plain": "App Store/<language>/01.png" and "Google Play/<language>/01.png", for uploading by hand. "fastlane": the folders fastlane deliver and supply upload from — only when the user uploads with fastlane.	plain
`languages`	No	Store sets only: export just these languages of the set (default all).
`project_id`	Yes	Project id (from create_project or list_projects).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 28, 2026

removedInput schema / properties / accept_charge

Removed value: -{
-  "description": "Only after the user agreed to it: confirms the extra charge for a full-quality export beyond the monthly allowance (the tool names the amount first).",
-  "type": "boolean"
-}

changedInput schema / properties / width / description

Previous value: -"Output width in pixels; default: the 720p size (longest edge 1280 px), which every plan exports without limit. Above that (longest edge over 1280 px) an export counts toward the organization's monthly full-quality exports (Free: 1, Pro: 15, then a small charge each). Only pass a larger width when the user wants full quality."New value: +"Output width in pixels; default: the full size of the scene. Leave it out for the final image. Pro exports any size without limit. On Free the default uses the one full-quality export of the month while it is left, then the 720p size (longest edge 1280 px), which Free exports without limit."

First observedOct 1, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well past the annotations: 5–30 second duration, immediate failure with no charge when the renderer is busy, 7-day URL validity, several-minute duration for set exports, and that a whole set counts as one export. It stops short of describing the response shape or what the returned URL yields beyond an image.

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 what it does and the key timing/cost caveats before the set-export detail. It runs long and the second half is dense with set-specific rules, but nearly every clause carries actionable information an agent would otherwise have to discover.

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

Completeness5/5

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

With no output schema, the description still explains what comes back (viewable image plus a 7-day download URL) and covers the non-obvious failure and retry path. An agent can call this correctly without further context.

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%, so the baseline is 3, but the description adds cross-parameter relationships the schema does not state: 'Width and format do not apply there' for store sets, and the interplay of folders/languages with set exports. That is real semantic value beyond the per-field descriptions.

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?

Specific verb and output: 'Renders the finished mockup on the server with the real 3D renderer' producing an image plus a download URL. It explicitly differentiates from the nearest sibling ('Use render_preview for quick checks while building, this for the result') and from set_store_set for bulk exports.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States when to use this versus render_preview, when the store-set path applies, and what to do on a busy renderer ('call it again after the time it names'). Alternatives and exclusion conditions are both named explicitly.

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

All Showoff.dev – AI Mockup Generator 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.

Resources

Need Help?