stykanimate-mcp

generate_motion_sequence

Generate animation timeline frames from keyframes, presets, or math expressions by computing joint rotation changes and injecting the resulting sequence into the document model.

Instructions

Accepts keyframes or mathematical expressions (e.g., sine waves for walking/running loops) to automatically compute absolute/relative joint rotation changes across a specified number of frames. Returns an array of calculated timeline frames injected into the document model state.

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": {
      "mode": "<mode>"
    },
    "name": "generate_motion_sequence"
  }
}

Input Schema

Name	Required	Description
`mode`	Yes	Generation mode: "preset" (pre-programmed loop), "expression" (math formulas), or "keyframes" (in-between interpolation)
`easing`	No	Default easing method between keyframes (default: "ease_in_out")
`preset`	No	Built-in motion preset: walk_loop, run_loop, idle_breathe, wave_hand, jumping_jacks, punch_combo, sword_slash, spin_kick, backflip, dash_dodge
`keyframes`	No	Keyframes to interpolate between (used when mode is "keyframes")
`frameCount`	No	Number of frames to generate (default: 24)
`expressions`	No	Mathematical motion expressions (used when mode is "expression")
`targetFigureId`	No	Target figure_type_id to animate (default: first figure in project)
`durationPerFrame`	No	Hold duration per keyframe in ticks (default: 1)
`injectIntoDocument`	No	Whether to replace current project keyframes with the generated sequence (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.1Nov 3, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose the key mutation: the generated frames are injected into the document model state. However, it does not say whether this overwrites existing keyframes (injectIntoDocument defaults to true), what happens if no figure exists, or what errors can occur.

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?

Two tightly packed sentences with no filler, and the input-to-output flow is front-loaded. Slightly dense phrasing ('absolute/relative joint rotation changes') but nothing wasteful.

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?

For a 9-parameter, nested-object, mutating tool with no output schema, the description does cover the essential mechanics: inputs, computation, and what the return value is. Remaining gaps (prerequisites, overwrite semantics) are moderate rather than fatal.

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 description coverage is 100%, so every parameter including mode, easing, frameCount, and nested expression fields is already documented. The prose adds no parameter-level detail such as units, defaults, or index conventions, so it sits at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: it accepts keyframes or math expressions and computes joint rotation deltas across frames, then returns injected timeline frames. That is much more informative than the bare name, though it never contrasts itself with siblings like add_figure_instance or render_and_export_media.

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

Usage Guidelines3/5

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

Usage is only implied through 'keyframes or mathematical expressions', which maps onto the schema's mode enum but omits the third 'preset' path entirely. There is no statement of prerequisites (a rigged figure/project must exist) or of when a sibling tool should be chosen instead.

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

Deploy Server