Skip to main content
Glama
ODU33104

rive-mcp

by ODU33104
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Auto-rig a character PNG

riv_rig_character

Rig a character PNG into an animated .riv file with cutout ear and tail parts, a 2-bone head-tilt mesh, eyelid blink, idle and happy animations, and a state machine trigger.

Instructions

One call: character PNG -> fully rigged .riv with cutout parts (ears/tail via polygons), 2-bone head-tilt mesh (seamless), vector eyelid blink, idle + happy animations, and a state machine with a 'happy' trigger. Returns a preview. Fine-tune afterwards with riv_edit or riv_studio.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eyesNoEye rects in image px coords (generates blink overlays)
partsNoNamed cutout parts, e.g. {earL, earR, tail}. Names containing 'ear' attach to the head
outPathYesOutput .riv path
pngPathYesCharacter PNG (transparent background recommended)
furColorNoEyelid/patch color matching the fur (default #f8eee2)
headRatioNoTop fraction of the image that is 'head' (default 0.45)
artboardWidthNo
artboardHeightNo
backgroundColorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.1
    • changedInput schema / properties / parts / additionalProperties / properties / pivot / items
      Previous value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  }
-]New value: +{
+  "type": "number"
+}
    • changedInput schema / properties / parts / additionalProperties / properties / polygon / items / items
      Previous value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  }
-]New value: +{
+  "type": "number"
+}
  2. First observedv0.5.0

TDQS

A4.1/5.0
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 adds behavioral specifics (mesh is seamless, blink is vector, state machine trigger named 'happy', returns a preview). It does not disclose overwrite semantics for outPath or preview form, but for a generation tool that is a modest gap.

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?

Three sentences, front-loaded with the 'One call' hook, an information-dense feature list, and a closing recommendation to riv_edit/riv_studio. Nothing is repeated from structured fields; it's only marginally packed with feature lists without titles.

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 9-parameter complex pipeline with no output schema and no annotations, the description is largely complete: it defines scope, deliverables, return-of-preview, and next-steps. Missing edge conditions (malformed polygon or eyes absent) are minor given the breadth of the deliverable scope covered.

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 covers only 67% of params. The description reinforces semantics already in the schema (ears/tail via polygons -> parts, blink overlays -> eyes), so it adds marginal value, and the undocumented artboardWidth/artboardHeight/backgroundColor params don't get any description-level compensation — the description doesn't scaffold those during execution.

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 states a clear verb and resource: character PNG -> fully rigged .riv, and enumerates concrete deliverables (cutout parts, 2-bone head-tilt mesh, vector eyelid blink, idle + happy animations, state machine with 'happy' trigger). The follow-up clause ('Fine-tune afterwards with riv_edit or riv_studio') also separates it from its siblings, so an agent can tell it apart 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?

The description leads with 'One call' to position this tool as the one-shot auto-rigging entry point, and explicitly names riv_edit/riv_studio as the follow-up for fine-tuning. It lacks an explicit 'when NOT to use' / exclusion, and what the preview is for, but still gives agent-routing guidance beyond most siblings.

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