Unreal-MCP-Ghost

Overview Schema Source Related Servers Discussions Admin

setup_full_retargeting_pipeline

Create IK Rigs for source and target skeletal meshes, build an IK Retargeter, and optionally retarget animations to handle mismatched bone structures.

Instructions

One-shot pipeline: create IK Rigs for source + target, create IK Retargeter, and optionally batch-retarget a list of animations.

This matches Method 2 (Manual IK Retargeting) described in the UE5 docs:

Create IK Rig for source skeleton (auto-generate chains)
Create IK Rig for target skeleton (auto-generate chains)
Create IK Retargeter (source → target, auto-map chains + auto-align)
Export retargeted animations

If all your characters share an identical skeleton (same bone names and hierarchy) you can skip this and use the quick-retarget workflow in the editor; but this pipeline handles mis-matched bone structures.

Args: source_skeletal_mesh: Content path to source Skeletal Mesh (e.g. "/Game/Characters/Mannequin/SK_Mannequin") target_skeletal_mesh: Content path to target Skeletal Mesh (e.g. "/Game/Dantooine/Art/Characters/Player/SK_Player") source_ik_rig_name: Name for source IK Rig asset (e.g. "IKR_Mannequin") target_ik_rig_name: Name for target IK Rig asset (e.g. "IKR_Player") retargeter_name: Name for IK Retargeter asset (e.g. "RTG_Mannequin_To_Player") ik_rig_path: Folder for IK Rig assets retargeter_path: Folder for IK Retargeter asset animations_to_retarget: Optional list of animation content paths to retarget immediately after setup output_animation_path: Output folder for retargeted animations

Returns: dict with keys: success, steps (dict of per-step results), message

KB: see knowledge_base/05_ANIMATION_SYSTEM.md#overview Example: setup_full_retargeting_pipeline(source_skeletal_mesh="Example", target_skeletal_mesh="Example", source_ik_rig_name="ExampleName", target_ik_rig_name="ExampleName", retargeter_name="ExampleName")

Input Schema

TableJSON Schema

Name	Required	Default
`ik_rig_path`	No	/Game/Animation/IKRigs
`retargeter_name`	Yes
`retargeter_path`	No	/Game/Animation/Retargeters
`source_ik_rig_name`	Yes
`target_ik_rig_name`	Yes
`source_skeletal_mesh`	Yes
`target_skeletal_mesh`	Yes
`output_animation_path`	No	/Game/Animation/Retargeted
`animations_to_retarget`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 20, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations provided, the description carries the transparency burden. It clearly states asset creation, auto-generation of chains, auto-mapping, auto-aligning, optional batch retargeting, and the return dict structure with per-step results. It does not disclose overwrite/idempotency behavior when assets already exist, which is a minor 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?

The description is longer than typical but well-structured: front-loaded purpose, numbered pipeline steps, explicit when-to-use, Arg list, Returns, KB link, and example. Some redundancy exists between the intro and the numbered UE5 docs summary, but no filler and every section earns its place.

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 complex 9-parameter, no-annotation tool, the description covers purpose, process, parameters, return values, KB reference, and an example. It could be more explicit about interactions between animations_to_retarget and output_animation_path, and what happens if the optional list is omitted, but overall it is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description fully compensates by explaining all 9 parameters with content path semantics, naming conventions, examples, optionality, and output folder meaning. The example paths and asset name patterns give an agent enough to construct valid calls.

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 opens with a specific verb and resource: a one-shot pipeline that creates IK Rigs, an IK Retargeter, and optionally batch-retargets animations. It distinguishes itself from related tools like create_ik_rig, create_ik_retargeter, and batch_retarget_animations by framing itself as the full pipeline covering source, target, retargeter, and export.

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?

The description explicitly says when NOT to use it: if skeletons are identical, skip and use the quick-retarget workflow, while this pipeline handles mismatched bone structures. It also references UE5 Method 2, giving clear contextual grounding for when this approach is appropriate.

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

Deploy Server