Skip to main content
Glama
Sign In
tripo-studio-mcp

tripo-studio-mcp

by Neko-Yukari
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

tripo_generate_multiview

Generate a 3D model from 2–4 photos of the same object taken from different viewpoints; order images front, left, right, back and get a GLB file back.

Instructions

多视图生成 3D 模型：给 2~4 张同一物体的不同视角图，对应内部接口 operation/multiview_to_model。数组顺序即视角顺序，默认按 front、left、right、back 理解；每张图都会先上传并送审。默认阻塞等待并下载 GLB。

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": {
      "image_paths": "<image_paths>"
    },
    "name": "tripo_generate_multiview"
  }
}

Input Schema

NameRequiredDescriptionDefault
pbrNoPBR 材质，默认 true；为 true 时 texture 被强制为 true
quadNo四边面输出，默认 false；开启后输出为 FBX 且面数不超过 150,000
textureNo是否生成贴图，默认 true
compressNo纹理压缩方式，默认 meshopt；geometry 需要在建模软件里先解压
out_pathNo保存路径，默认 tripo-out/<第一张文件名>-mv.glb
auto_sizeNo按真实世界尺寸（米）缩放，默认 false
export_uvNo生成阶段是否做 UV 展开，默认 true；设 false 更快、模型更小
face_limitNo面数上限，不填自适应。v3.1/v3.0 detailed 最多 2,000,000、standard 1,500,000；v2.5 最多 500,000；quad=true 时不超过 150,000
model_seedNo几何随机种子，固定可复现（v2.0 及以上）
visibilityNo模型可见性，默认 shareable
face_presetNo面数预设：low 3万 / medium 15万 / high 80万，优先于 face_limit；游戏资产和 3D 打印建议 low 或 medium
image_pathsYes2~4 张本地图片，按 front、left、right、back 的顺序排列
orientationNo自动旋转对齐原图，默认 default；仅 texture=true 时生效
texture_seedNo贴图随机种子（v2.0 及以上）
wait_secondsNo阻塞等待上限，默认 480 秒；超时会返回 id，稍后用 tripo_download 取模型
model_versionNo模型版本，默认 v3.1-20260211（H3.1）。v3.0 = H3.0 快速，v2.5 = H2.5 经典；Nexus-v1.0 / Nexus-v2.0 = 智能网格 P1.0 / P2.0（对应官方 API 的 P1，输出干净拓扑低模）
generate_partsNo分部件生成，默认 false；与 texture/pbr/quad 不兼容
smart_low_polyNo手搓拓扑低模，默认 false；输入复杂时可能失败
texture_qualityNo贴图质量，默认 detailed；standard 为基准，detailed +20、extreme +30 积分
geometry_qualityNo几何精度，默认 detailed（Ultra）
texture_alignmentNo贴图对齐倾向：忠于原图 / 忠于几何，默认 original_image

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does meaningful work: it discloses that every image is uploaded and subjected to moderation/review, that the call blocks by default, and that a GLB is downloaded to disk. Undisclosed: credit cost, the timeout-and-recover-via-id path (only in the schema), and incompatible flag combinations.

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?

Four short clauses, front-loaded with the action, then constraints, then side effects, then default runtime behavior. No filler and nothing buried.

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 21-parameter, no-output-schema tool, the description covers the end-to-end flow an agent needs to reason about: input ordering, moderation side effect, blocking wait, and output artifact. It stops slightly short on cost and failure handling, which matter given the many quality/credit options in the schema.

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 description coverage is 100%, so the schema already explains all 21 parameters. The description's note that array order equals view order (front/left/right/back) largely restates the image_paths field description, adding no syntax or format detail the schema lacks. Baseline 3 applies.

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 ('多视图生成 3D 模型') plus the exact input modality (2-4 images of the same object from different views). This immediately distinguishes it from tripo_generate_text and tripo_generate_image, and the internal operation name (operation/multiview_to_model) removes any ambiguity.

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

Usage Guidelines3/5

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

The description establishes usage preconditions (2-4 images, same object, different viewpoints, order matters), which is real guidance. But it never names alternatives or exclusions – nothing says when to prefer this over single-image generation or remesh/upscale, and the recovery path on timeout is only implied.

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

Deploy Server

Other Tools