Skip to main content
Glama
Ref2Blender MCP Server

Ref2Blender MCP Server

by evarynstudio

export_model

Export a Blender scene as a game-ready FBX or GLB for Unity, Unreal Engine, Godot or generic use, with optional LODs, convex collision and palette materials written to a path you specify.

Instructions

Export the model for a game engine. Writes a file on the user's disk: only call it when the user asked for an export, with an absolute path they chose.

The scene is not modified (the export works on copies): modifiers are applied, parts without UVs are unwrapped, everything is joined into one mesh named after the file (separate keeps the parts), and the pivot goes to the bottom centre. The extension is set by the engine: FBX for unity and unreal, GLB for godot and generic.

lods: extra detail levels, each with half the triangles (0-4). collision: add a convex collision mesh named the way the engine expects. palette: replace all materials with one material and a small colour-swatch PNG written next to the model (colour only).

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": {
      "path": "<path>"
    },
    "name": "export_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
lodsNo
pathYes
assetNo
pivotNobottom
engineNounity
paletteNo
separateNo
collisionNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the disk write, that the scene is not modified, that modifiers are applied and parts joined, and how the target extension is chosen. Remaining gaps are overwrite behavior when the path already exists and failure modes, which matter for a file-writing tool.

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 constraint and side effect are front-loaded, then behavior, then a compact labelled list of parameters. There is little waste; every clause either sets a precondition or changes the exported result.

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 an 8-parameter tool that writes to disk, the description covers effect, non-destructiveness, transformation behavior, and most options, and an output schema exists so return values need no explanation. It is only short of complete on overwrite/error behavior and the unexplained asset parameter.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate, and it explains most parameters: lods (0-4, halving triangles), collision (convex mesh named for the engine), palette (single material plus swatch PNG, colour only), separate (keeps parts), engine (extension mapping), and pivot. Two parameters, asset and the exact path semantics, remain undocumented.

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?

States a specific verb and resource ("Export the model") plus the concrete effect ("Writes a file on the user's disk") and target domain (game engine). That is enough to separate it from siblings like export_all_assets or render_views without opening a 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?

Gives an explicit precondition: only call when the user asked for an export, with an absolute path they chose. That is strong when-to-use guidance. It stops short of naming alternatives (e.g. export_all_assets) or stating when not to export, so it lands just under the top band.

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