Skip to main content
Glama
elibarnett

kie-mcp

by elibarnett
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

seedream_layer_decompose

Split ANY image into independent layers with Seedream 5.0 (billed per OUTPUT layer incl. base). tier="pro" (default): 7 cr @1K, 14 @2K, so a 3-layer split ≈ 21 cr. tier="flash" (NEW): 3.24 cr/layer at any size, so ≈ 10 cr.

Instructions

Split ANY image into independent layers with Seedream 5.0 (billed per OUTPUT layer incl. base). tier="pro" (default): 7 cr @1K, 14 @2K, so a 3-layer split ≈ 21 cr. tier="flash" (NEW): 3.24 cr/layer at any size, so ≈ 10 cr. Works on any public image URL (upload local files with upload_file first). Describe which elements become layers in the prompt, optionally bounding them with x1 y1 x2 y2 tags. Downloads every layer image to kie/assets/raw/.

Input Schema

NameRequiredDescriptionDefault
sizeNoauto, 1K, 1.5K or 2K. Pro: 7 cr/layer at 1K/1.5K, 14 at 2K. Flash: 3.24 at any size.auto
tierNopro = Seedream 5.0 Pro (7 cr/layer @1K, 14 @2K; prompt required). flash = Seedream 5.0 Flash (NEW: 3.24 cr/layer at any size; prompt optional — but WITHOUT a prompt it splits out every element: a poster gave 12 layers = 38.9 cr. Name the elements you want to cap the layer count).pro
promptNoWhich elements to separate into layers, e.g. "Separate the title text <bbox>179 58 809 197</bbox> and the parrot <bbox>330 274 641 991</bbox> into independent layers"
filenameNoBase output filename; layers get -2, -3... suffixes
image_urlYesPublic URL of the source image (singular — one image per call)
max_creditsNoRefuse to submit if the estimated cost exceeds this many credits (overrides KIE_MAX_CREDITS_PER_CALL). Estimates come from published rates; kie bills the actual amount.
download_dirNoAbsolute directory to save into (created if missing). Defaults to the server's kie/assets/raw/.
estimate_onlyNoReturn the estimated credit cost WITHOUT submitting anything. Use before expensive runs (video, 4K, 1080p upgrades, layer splits).
output_formatNopng recommended for transparencypng

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.8.0
    • addedInput schema / properties / estimate_only
      Added value: +{
+  "description": "Return the estimated credit cost WITHOUT submitting anything. Use before expensive runs (video, 4K, 1080p upgrades, layer splits).",
+  "type": "boolean"
+}
    • addedInput schema / properties / max_credits
      Added value: +{
+  "description": "Refuse to submit if the estimated cost exceeds this many credits (overrides KIE_MAX_CREDITS_PER_CALL). Estimates come from published rates; kie bills the actual amount.",
+  "type": "number"
+}
  2. Changed3 schema fields changedv5.5.0
    • changedInput schema / properties / size / description
      Previous value: -"1K/1.5K = 7 cr per layer, 2K = 14"New value: +"auto, 1K, 1.5K or 2K. Pro: 7 cr/layer at 1K/1.5K, 14 at 2K. Flash: 3.24 at any size."
    • addedInput schema / properties / tier
      Added value: +{
+  "default": "pro",
+  "description": "pro = Seedream 5.0 Pro (7 cr/layer @1K, 14 @2K; prompt required). flash = Seedream 5.0 Flash (NEW: 3.24 cr/layer at any size; prompt optional — but WITHOUT a prompt it splits out every element: a poster gave 12 layers = 38.9 cr. Name the elements you want to cap the layer count).",
+  "enum": [
+    "pro",
+    "flash"
+  ],
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "image_url",
-  "prompt"
-]New value: +[
+  "image_url"
+]
  3. Addedv5.3.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the per-layer billing model (including the base layer), the exact credit rates per tier/size, the side effect of downloading every layer to kie/assets/raw/, the public-URL-only constraint with upload_file as the workaround, and the max_credits submission guard. It omits failure/overwrite behavior and whether the call is blocking or async.

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-loads the core action, then cost, then workflow in a compact block with no filler sentences. There is mild redundancy, since the tier/size credit rates appear in both the description and the schema descriptions.

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 nine-parameter, no-output-schema tool, the description covers the essentials: what it produces (per-layer downloads), where output lands, prerequisites, cost controls, and how to shape the split via prompt. Only error handling and output naming/ordering detail are absent.

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 coverage is 100%, so the schema already documents all nine parameters, including tier and size pricing. The description largely restates the tier/cost tradeoff rather than adding new meaning, though it does supply a concrete prompt example with <bbox> syntax that illustrates how the prompt parameter is used.

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 precise verb+resource+engine: 'Split ANY image into independent layers with Seedream 5.0'. It is immediately distinguishable from siblings like generate_image, grok_image_edit, or audio tools, and it even names the upload_file prerequisite for local files.

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 real selection guidance — tier='pro' vs tier='flash' with cost tradeoffs, the warning that flash without a prompt explodes layer count (12 layers = 38.9 cr), and 'use estimate_only before expensive runs'. It never names an alternative tool to use instead, so it falls short of the 5-bar.

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