← WebMCP Directory

aozu.mantle.tools

aozu.mantle.tools

live Unverified (seed import) Media & Personal 16 tools imperative implementation

AOZU is an agent-native workshop for creating, aligning, and exporting reusable layered character assets with WebMCP.

First seen 2026-09-21 · Last seen 2026-09-28 · Source: webmcp.com

Answer 0 · Act 16 · Transact 0 · Score: Not yet scored

Tool inspector

inspect_character_contract

act imperative

Use scope:model-sheet for reference art, scope:appearance (default) for composited layers. Inspect character.appearances and activeAppearanceId for named combinations. Use set_character_variant_selection with appearance to create/save-as/select/rename/delete a combination; then re-inspect its model sheet. For model sheets, use referenceId (a default view or a supplemental ID), optional label/kind/viewpoint/pose, and images (up to 5 IDs: appearance, canonical, or stored reference IDs) to obtain actual source PNGs. Image bytes are opt-in for model sheets. Save-as captures the current front; create starts with no selected variants or references, keeping the shared base body and assets. fromAppearance can explicitly capture or replace the front. Supplement it with head/structure/expression/detail/style references. Follow generationGuidance for identity, source precedence and the requested study, plus the returned task-specific policy and required browser visual-review workflow. Appearance only: The first Appearance body establishes a front A-pose: upright torso, neutral face, arms angled down and away from the torso, relaxed visible hands, stable feet, and the complete head-to-feet silhouette inside the canvas. This is the AOZU authoring convention, not a claim of skeleton compatibility. Preserve this pose and registration in derived outfits and expressions. Existing artwork is not automatically verified A-pose; review it visually before proposing a baseline change, which can make derived layers stale. Required before replacing, repairing, or aligning character art; use inspect_workspace first to identify the user's current view. Optionally name one target to receive its allowed operations, exact current asset hash, visual alignment reference, layer ownership, alpha policy, generation size (1024×1536) and final size (512×768), normalization, revision, z-order, diagnostics, and required browser visual-review workflow. Follow generationRecipe.backgroundPreparation before…

Input schema

PropertyTypeRequiredDescription
characterId string yes —
group — no —
images array no —
kind — no —
label string no —
layer — no —
needsReview boolean no —
pose string no —
referenceId string no —
scope — no —
sourceSha256 string no —
variantId string no —
viewpoint string no —
Raw JSON schema
{
  "additionalProperties": false,
  "properties": {
    "characterId": {
      "minLength": 1,
      "type": "string"
    },
    "group": {
      "enum": [
        "body",
        "expression",
        "outfit",
        "prop"
      ]
    },
    "images": {
      "items": {
        "pattern": "^[a-z0-9][a-z0-9_-]{0,39}$",
        "type": "string"
      },
      "maxItems": 5,
      "type": "array",
      "uniqueItems": true
    },
    "kind": {
      "enum": [
        "full-body",
        "head",
        "structure",
        "expression",
        "detail",
        "style"
      ]
    },
    "label": {
      "maxLength": 80,
      "minLength": 1,
      "type": "string"
    },
    "layer": {
      "enum": [
        "body",
        "head",
        "back",
        "front"
      ]
    },
    "needsReview": {
      "type": "boolean"
    },
    "pose": {
      "maxLength": 80,
      "minLength": 1,
      "type": "string"
    },
    "referenceId": {
      "pattern": "^[a-z0-9][a-z0-9_-]{0,39}$",
      "type": "string"
    },
    "scope": {
      "enum": [
        "appearance",
        "model-sheet"
      ]
    },
    "sourceSha256": {
      "pattern": "^[0-9a-f]{64}$",
      "type": "string"
    },
    "variantId": {
      "pattern": "^[a-z0-9][a-z0-9_-]{0,39}$",
      "type": "string"
    },
    "viewpoint": {
      "maxLength": 80,
      "minLength": 1,
      "type": "string"
    }
  },
  "readOnly": true,
  "required": [
    "characterId"
  ],
  "type": "object"
}

Similar websites

tracinginsights.com

tracinginsights.com

Analyze Formula 1 racing data with interactive charts for lap times, live telemetry, timing data and race performance. Explore and Compare drivers across multip…

live Unverified Media & Personal
52 tools A17 / Act35 / T0 Not yet scored Seen 2026-09-28
select-f1-data get-current-selection list-available-options get-data-status wait-for-data
Inspect tools
rough-cut.samarthsaxena1672003.workers.dev

rough-cut.samarthsaxena1672003.workers.dev

A human-first video editor with structured WebMCP tools for any compatible agent.

live Unverified Media & Personal
40 tools A6 / Act34 / T0 Not yet scored Seen 2026-09-28
request_video_upload get_project_state get_activity rename_project get_transcript
Inspect tools
fiveminutebrief.ai

fiveminutebrief.ai

live Unverified Media & Personal
31 tools A10 / Act21 / T0 Not yet scored Seen 2026-09-28
list_public_topics get_public_topic get_latest_brief get_public_topic_preview get_brief_newsletter
Inspect tools
panoptik-studio.vercel.app

panoptik-studio.vercel.app

Browser-native demo video editor where humans and AI agents co-edit on the same canvas via WebMCP. No uploads, no server.

live Unverified Media & Personal Transact tools
30 tools A9 / Act20 / T1 Not yet scored Seen 2026-09-28
get_project_state list_clips list_scenes get_silence_intervals get_transcript
Inspect tools

Related on Influzer