Skip to main content
Glama
Flux-Point-Studios

Unreal Engine MCP Server

manage_geometry

Create procedural meshes in Unreal Engine and apply booleans, deformers, UVs, collision, and LODs using Geometry Script.

Instructions

Create procedural meshes using Geometry Script: booleans, deformers, UVs, collision, and LOD generation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
axisNoAxis for deformation operations.
saveNoSave the asset(s) after the operation.
angleNoAngle in degrees.
depthNoDepth value.
scaleNo3D scale (x, y, z).
widthNoWidth value.
actionYesGeometry action to perform
amountNoGeneric amount for operations (bevel size, inset distance, etc.).
heightNoHeight value.
radiusNoRadius value.
uvScaleNoUV scale.
distanceNoDistance value.
locationNo3D location (x, y, z).
lodCountNoNumber of LOD levels to generate.
lodIndexNoSpecific LOD index to configure.
meshPathNoMesh asset path.
numRingsNoNumber of rings for sphere, torus.
numSidesNoNumber of sides for cylinder, cone, etc.
numStepsNoNumber of steps for stairs.
numTurnsNoNumber of turns for spiral.
rotationNo3D rotation (pitch, yaw, roll).
segmentsNoNumber of segments for bevel, subdivide.
strengthNoStrength or weight.
uvOffsetNoUV offset.
actorNameNoName of the actor.
hullCountNoNumber of convex hulls for decomposition.
overwriteNoOverwrite if the asset/file already exists.
stepDepthNoDepth of each stair step.
stepWidthNoWidth of each stair step.
uvChannelNoUV channel index (0-7).
exportPathNoExport file path.
includeUVsNoInclude UVs in export.
iterationsNoNumber of iterations for smooth, remesh.
outputPathNoOutput file or directory path.
screenSizeNoScreen size threshold for LOD switching.
stepHeightNoHeight of each stair step.
createAssetNoCreate as persistent asset.
edgeIndicesNoArray of edge indices.
faceIndicesNoArray of face indices.
innerRadiusNoInner radius for torus.
preserveUVsNoPreserve UV seams during LOD generation.
screenSizesNoArray of screen sizes for each LOD.
enableNaniteNoEnable Nanite for the output mesh.
exportFormatNoExport file format.
selectionBoxNoBounding box for selection.
weldDistanceNoDistance threshold for vertex welding.
collisionTypeNoCollision complexity type.
depthSegmentsNoSegments along depth.
hardEdgeAngleNoAngle threshold for hard edges (degrees).
hullPrecisionNoPrecision for convex hull generation (0-1).
vertexIndicesNoArray of vertex indices.
widthSegmentsNoSegments along width.
heightSegmentsNoSegments along height.
includeNormalsNoInclude normals in export.
radialSegmentsNoRadial segments for circular shapes.
targetMeshPathNoPath to second mesh for boolean operations.
includeTangentsNoInclude tangents in export.
preserveBordersNoPreserve mesh borders during LOD generation.
reductionPercentNoPercent of triangles to reduce per LOD.
smoothingGroupIdNoSmoothing group ID.
targetEdgeLengthNoTarget edge length for remeshing.
maxVerticesPerHullNoMaximum vertices per convex hull.
projectionDirectionNoProjection direction for UV.
targetTriangleCountNoTarget triangle count for simplification.
computeWeightedNormalsNoUse area-weighted normals.
Behavior2/5

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

The annotations already state readOnlyHint=false and destructiveHint=false, but the description adds no behavioral context beyond 'Create'. Many actions (boolean_subtract, remesh, generate_collision) modify existing geometry, which the wording 'Create procedural meshes' does not disclose; save/createAsset and overwrite parameters also imply persistence behavior that is not mentioned.

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?

The description is a single, front-loaded sentence with a colon-separated list of operation categories. No words are wasted, and the structure is easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high complexity (65 parameters, 46 enum actions, no output schema), the description is far too thin. It provides no information about how to select a target mesh, interpret return values, handle asset creation/saving, or choose among the many action variants.

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 coverage is 100%, so the schema itself carries parameter definitions. The description offers only high-level categories (booleans, deformers, UVs, etc.) with no mapping to the 65 parameters, leaving the agent to infer which parameters apply to which actions from generic schema descriptions like 'Depth value' or 'Distance value.'

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 clearly identifies the tool's function as creating procedural meshes via Geometry Script and lists key operation categories (booleans, deformers, UVs, collision, LOD generation). This distinguishes it from sibling asset/material tools, though it underrepresents non-create actions like get_mesh_info, export, and Nanite conversion that are present in the action enum.

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

Usage Guidelines2/5

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

No guidance is provided about when to use this tool versus alternatives, nor any exclusions or prerequisites. With 46 possible actions, the description gives no decision support for selecting the appropriate action, target mesh, or operation context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Flux-Point-Studios/unreal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server