Skip to main content
Glama

generate_asset

Generate game-ready Roblox assets from a text prompt or image: Meshy creates the textured mesh, Blender auto-fixes Roblox limits, then the GLB uploads and inserts into your place.

Instructions

FULL PIPELINE: turn a text prompt (or an image) into a game-ready asset in the open place — Meshy AI generates the textured mesh, headless Blender lints it against Roblox limits and auto-fixes (decimates >20k tris, downscales >1024px textures; autoFix:false to skip), then the GLB uploads to the user's Roblox account via Open Cloud and inserts as a Model. SPENDS MESHY CREDITS (~30 ≈ $0.60 per asset) — first call returns a cost estimate and asks for confirm:true unless TUFAN_MESHY_AUTOCONFIRM=1. Generation takes minutes; on budget exhaustion you get a meshyTaskId to resume with (no re-spend). Position the inserted model afterwards with place_on. Needs TUFAN_MESHY_KEY + TUFAN_OPENCLOUD_KEY (Blender optional but recommended). For an EXISTING marketplace asset by id use insert_asset instead; for a local file you already have use import_file instead; to generate WITHOUT auto-inserting into the place (just the raw model), use meshy_generate instead.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "generate_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoDisplay name on Roblox (default: derived from the prompt)
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
anchorNoAnchor all parts after insert so the prop can't fall (default true)
insertNoInsert into the place after upload (default true)
promptNoText description of the asset (mutually exclusive with image*)
autoFixNoAuto-decimate/downscale when the lint flags Roblox-limit violations (default true)
confirmNoConfirm the credit spend for a NEW generation
imageUrlNoPublic image URL for image-to-3D
onGroundNoAfter insert+scale, drop the model flush onto whatever is below it
positionNo[x,y,z] world position for the inserted model's pivot (instead of onGround)
enablePbrNoGenerate PBR maps (default true)
imagePathNoLocal image file (.png/.jpg/.webp) for image-to-3D
parentPathNoWhere to insert in the place (default Workspace)
meshyTaskIdNoResume from an existing Meshy task (skips generation + credits)
waitSecondsNoMax seconds for the generation stage (default 240, max 600)
previewFirstNoText-to-3D only: stop after the geometry preview (20cr) and return a rendered thumbnail to approve BEFORE spending the texture refine (+10cr) and uploading. Approve by re-calling with { meshyTaskId } (without previewFirst).
targetPolycountNoTriangle budget requested from Meshy AND used by the decimate auto-fix (default 18000)
collisionFidelityNoSet on every MeshPart after insert — Hull is a good cheap choice for static props
targetHeightStudsNoScale the inserted model so its height equals this many studs (a character is ~5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only supply generic hints (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false); the description adds the material behavior: ~30 credits ≈ $0.60 per asset, a mandatory first-call cost estimate plus confirm:true unless TUFAN_MESHY_AUTOCONFIRM=1, multi-minute generation, and a resumable meshyTaskId on budget exhaustion that avoids re-spend. Required env keys (TUFAN_MESHY_KEY, TUFAN_OPENCLOUD_KEY) and the optional-but-recommended Blender dependency are also disclosed. Minor gap: it doesn't say what happens to the place if upload succeeds but insert fails.

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

Conciseness3/5

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

Every clause carries real information and the cost warning is front-loaded, but it is a single dense block of ALL-CAPS fragments and stacked parentheticals that is harder to scan than the content warrants. Splitting cost/risk, pipeline stages, and alternatives into distinct sentences would lose nothing.

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 19-parameter, multi-service, credit-spending pipeline with no output schema, the description covers cost, confirmation, credentials, timing, failure recovery, post-insert positioning, and sibling routing. An agent has enough to call it correctly and to handle the budget-exhaustion path without guessing.

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 100% so the baseline is 3, but the description adds cross-parameter semantics the schema can't: the confirm estimate flow, meshyTaskId as a no-credit resume path, and the previewFirst→re-call-with-meshyTaskId approval sequence. autoFix:false and the decimate/downscale thresholds are also spelled out as behavior rather than defaults.

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 end-to-end verb chain (prompt/image → Meshy mesh → Blender lint/fix → GLB upload → Model insert) with the exact resource produced. It explicitly disambiguates from three siblings by name (insert_asset for existing marketplace assets, import_file for local files, meshy_generate for no-insert generation), so an agent can route without opening any schema.

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?

Gives explicit when-to-use alternatives with the exact condition that selects each: existing asset by id → insert_asset, local file → import_file, raw model without insert → meshy_generate. It also names the natural follow-up (place_on) and the in-tool branch condition (previewFirst→meshyTaskId) for approving a spend.

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