Unreal-MCP-Ghost

Overview Schema Source Related Servers Discussions Admin

import_animation_fbx

Import animation-only FBX onto an existing Unreal Engine Skeleton while disabling mesh, material, and texture imports to protect production SkeletalMesh.

Instructions

Import an animation-only FBX onto an existing UE Skeleton.

This is the receiving half of DCC animation handoffs such as Cascadeur's Animation FBX preset. It deliberately disables mesh, material, and texture import so a validation or animation pass cannot silently replace a production SkeletalMesh.

Args: file_path: Absolute path to an FBX file on the Unreal host. skeleton: Existing Skeleton asset path, for example /Game/Characters/Mannequins/Meshes/SKM_Manny_Skeleton. destination_path: Content Browser folder for AnimSequence assets. destination_name: Optional asset name override. Empty preserves the FBX take/file naming chosen by Unreal. animation_length: exported_time (default) or animated_key. import_custom_attributes: Preserve authored FBX custom attributes. remove_redundant_keys: Allow Unreal's lossless redundant-key cleanup. use_default_sample_rate: Sample at Unreal's default rate when true. custom_sample_rate: Explicit sample rate when greater than zero. replace_existing: Replace same-named destination assets only when explicitly requested. Defaults false for non-destructive proof.

Returns: StructuredResult JSON with imported AnimSequence paths, the resolved Skeleton, and the effective import settings.

KB: see knowledge_base/05_ANIMATION_SYSTEM.md#import-and-retargeting Example: import_animation_fbx( file_path="C:/Animations/Walk.fbx", skeleton="/Game/Characters/Mannequins/Meshes/SKM_Manny_Skeleton", destination_path="/Game/Animations", )

Input Schema

TableJSON Schema

Name	Required	Default
`skeleton`	Yes
`file_path`	Yes
`animation_length`	No	exported_time
`destination_name`	No
`destination_path`	No	/Game/Animations/
`replace_existing`	No
`custom_sample_rate`	No
`remove_redundant_keys`	No
`use_default_sample_rate`	No
`import_custom_attributes`	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 full burden. It discloses key behavioral traits: it deliberately disables mesh/material/texture import to prevent replacing production SkeletalMesh, and it explains the non-destructive default for replace_existing. It also describes the return type (StructuredResult JSON). While it does not cover all possible failure modes or prerequisites, the description transparently communicates the most significant behaviors and safety characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite having 10 parameters, the description is well-structured with a summary, parameter list with one-line explanations, Returns section, KB reference, and an example. It is front-loaded with the core purpose and then organizes details logically. Each sentence serves a purpose, and the length is appropriate for the tool's complexity. No fluff or repetition.

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?

The description covers all essential aspects: what the tool does, when to use it (DCC handoffs), behavioral safeguards, all parameters with semantics, return value, a KB reference for deeper context, and a concrete example. An agent has enough information to invoke the tool correctly with confidence. The presence of an output schema reduces the need to describe return format in detail, though it still summarizes it.

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 must explain every parameter. It does so concisely: file_path (absolute path), skeleton (existing skeleton asset path), destination_path (folder), destination_name (override behavior), animation_length (two options), import_custom_attributes (preserve), remove_redundant_keys (cleanup), sample rate options, and replace_existing (non-destructive default). It also includes an example call. This fully compensates for the schema's lack of descriptions.

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 clear, specific statement: 'Import an animation-only FBX onto an existing UE Skeleton.' It names the exact operation, the resource type, and the target. It further distinguishes itself by stating it disables mesh, material, and texture import, which differentiates it from sibling import tools like import_skeletal_mesh and import_static_mesh. An agent can immediately understand what this tool does and how it differs.

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 provides context: 'This is the receiving half of DCC animation handoffs such as Cascadeur's Animation FBX preset.' It also explains the intentional restriction to animation-only data, which implies when to use it. However, it does not explicitly state when NOT to use this tool or name alternative import tools (e.g., import_skeletal_mesh for mesh import). The usage context is clear but lacks explicit exclusions or direct comparisons that would earn a 5.

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

Deploy Server