tripo-studio-mcp
Works with the official Tripo Blender add-on (0.7.3) by pointing its BASE_URL at the local gateway and pasting in a gateway-issued key, so text-to-3D generation and other Tripo tasks run from inside Blender and results (GLB/FBX) are imported directly into the scene.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tripo-studio-mcp Generate a 3D model of a low-poly treasure chest and download the GLB"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tripo-studio-mcp
English · 简体中文
An MCP server that turns text or a reference image into a 3D model by spending your Tripo Studio subscription credits, then hands the agent a local GLB file.
⚠️ Unofficial. This drives the internal endpoints behind the Tripo Studio web app, not Tripo's official OpenAPI. Endpoints can change without notice, and your account is your own responsibility. See Disclaimer.
Why this exists
Tripo's official API is pay-as-you-go: $1 buys 100 credits, one generation costs about 40–50 credits, so roughly $0.40–0.50 per model. Credits never expire.
A Studio subscription works the other way. Pro is about ¥140/month for 3000 credits, which puts one generation near 25 credits. The catch is documented: subscription credits cannot be used to call the API.
So this project skips the API. It takes the session cookie your browser gets after you log in to Studio, and calls the same endpoints Studio's own frontend calls. Billing still runs through your subscription, but now an agent can drive it.
Use it if you already pay for Studio and want an agent to produce assets in bulk. Do not use it for anything that needs webhooks, job queues, or a support contract — those belong to the official API.
Related MCP server: Meshy MCP Server
Tools
Every tool below has been run against a real Studio account, not just probed. The third column names the matching task in the official API.
Tool | What it does | Official API |
| Credit balance, plan, expiry, special quota pools, recent credit ledger, progress of one operation |
|
| Lists the projects in your account, newest first |
|
| Text prompt → 3D model; waits and downloads it |
|
| Reference image → 3D model; uploads and audits the image first |
|
| 2–4 views (front, left, right, back) → 3D model |
|
| 2D images: text → image, edit with reference images, templates (T-pose, character split…), one image → front/left/back/right views |
|
| Uploads your own GLB/FBX/OBJ/STL as a project so the tools below can work on it |
|
| Retopology to a target face count, quad or triangle |
|
| Regenerates textures, optionally from a reference image |
|
| Adds PBR maps to a textured model |
|
| Upscales textures to 4K or 8K | — (Studio only) |
| Smart UV unwrap; generates a candidate and applies it |
|
| Splits a mesh into parts: simple / balanced / detailed |
|
| Fills the hidden geometry of segmented parts: AI completion or quick cap |
|
| Rig pre-check, then auto rigging; humanoids can use a Mixamo, UE5, Unity, ActorCore or VRM skeleton |
|
| Puts a motion on a rigged model: one of 97 biped presets, a motion you generated earlier, or a new one from text |
|
| Your generated motions plus the preset names per rig type | — |
| Downloads a project as glb, fbx, obj, stl or 3mf; |
|
Not available, because Studio itself has no such feature: stylization (lego / voxel / voronoi / minecraft), image → Gaussian splat, image → depth, USDZ export, and webhooks.
Parameter names follow the official docs, so anything you already know from the official API carries over:
model_version, face_limit, face_preset (low 30k / medium 150k / high 800k), texture, pbr, texture_quality (standard/detailed/extreme), geometry_quality (standard/detailed), texture_alignment (original_image/geometry), quad, auto_size, orientation (default/align_image), compress (geometry/meshopt), smart_low_poly, generate_parts, export_uv, model_seed, texture_seed, visibility (private/public/shareable).
A few defaults are worth knowing. model_version defaults to v3.1-20260211 (H3.1 highest quality) and costs about 55 credits per run. Studio's version list differs from the official one: v3.0-20250812 is H3.0, v2.5-20250123 is H2.5, and Nexus-v1.0-20260214 / Nexus-v2.0-20260801 are the "smart mesh" P1 / P2 models that output clean low-poly topology (P2 with quad=true gives mostly quads, delivered as FBX). Setting quad=true forces quad topology, and then face_limit cannot exceed 150,000. Setting generate_parts=true conflicts with texture, pbr and quad.
Install
You need Node 18 or newer.
git clone https://github.com/Neko-Yukari/tripo-studio-mcp.git
cd tripo-studio-mcp
npm i # installs playwright for the login script only
npm run login # opens real Chrome, and saves the session once you log inThe login script writes ~/.tripo/studio-state.json. That session usually lasts about a month; run npm run login again when it expires.
Login has to happen in a headed browser. Studio sits behind Cloudflare, so plain HTTP requests cannot obtain a valid session on their own. The script reuses the Chrome you already have installed.
Register with an MCP client
Generic JSON, works for Claude Desktop and similar:
{
"mcpServers": {
"tripo-studio": {
"command": "node",
"args": ["/absolute/path/to/tripo-studio-mcp/server.mjs"]
}
}
}For opencode with magpie, which is what this project was built and tested on:
magpie library mcp add tripo-studio node /absolute/path/to/server.mjs agents=opencode --local--local keeps the entry on this machine, so it will not follow your config sync to another computer.
Configuration
Everything is an environment variable, and all of them have defaults.
Variable | Default | Purpose |
|
| Path to the saved session |
|
| Optional file, supports |
| empty | HTTP proxy such as |
| empty | Same as above, lower priority than |
| empty | Set to anything to force a direct connection |
| Chrome 156 UA | Rarely needs changing |
| empty | Set to |
|
| Gateway port |
|
| Gateway listen address |
|
| Key hashes, task records and cached outputs |
| derived from host and port | Prefix for download links; only needed behind a reverse proxy |
| empty | Certificate and key; set both to serve HTTPS |
Official API gateway
gateway.mjs runs a local HTTP server that speaks the official Tripo API, both V3 (/v3/*) and V2 (/v2/openapi/*). Point an official SDK, the CLI or the Blender add-on at it, give it a key the gateway issued, and the client works unchanged, except that it spends your Studio subscription credits.
Starting it
Issue a key first:
node gateway.mjs keygen blender # printed once; keys.json only stores its hash
node gateway.mjs revoke blender # revoke itOnce a key exists, the MCP server starts the gateway whenever it starts, and the gateway exits when the MCP server does, so you do not need a separate autostart. With no key, no port is opened; TRIPO_GATEWAY=0 turns it off entirely. Without the MCP server, run it on its own with npm run gateway.
If several MCP instances run at once (opencode starts one per directory, for example), only one gets the port and the rest retry every minute. When the owner exits, another instance takes over within a minute.
Pointing clients at it
Client | Setting | Tested |
Python SDK 1.x (V3) |
| text generation, rig check, FBX conversion, download |
Python SDK 0.4.x (V2) |
| image generation, download |
Official Blender add-on 0.7.3 | see below | text generation, imported into the scene |
tripo-cli 0.8 |
| not tested |
|
| not tested |
Blender add-on
The official add-on bundles SDK 0.4.x. When Blender's Python has no aiohttp, the SDK falls back to a minimal client that hardcodes port 443 and TLS, so whatever port you put in the URL is ignored. That means two steps:
Install aiohttp where Blender loads user dependencies. Blender 5.2 reads
scripts\addons\modules, notscripts\modules:& "<Blender install>\5.2\python\bin\python.exe" -m pip install --target "$env:APPDATA\Blender Foundation\Blender\5.2\scripts\addons\modules" aiohttpBecause it lives in your user folder, a Blender upgrade or Steam update will not wipe it.
Change
BASE_URLin the add-on'stripo3d/client.pytohttp://127.0.0.1:8787/v2/openapi, then paste the gateway key into the add-on's API Key field.
If you would rather not install aiohttp, run the gateway on 443 with --tls-cert and --tls-key. That route was tested too, but it needs your own CA imported into the system's trusted roots, because Python 3.13 and later reject a single self-signed certificate. And if a tool such as Clash has taken over 127.0.0.1:443, bind to ::1 instead and use https://::1/v2/openapi in the add-on.
Differences from the official API
The gateway only maps what Studio can do equivalently. Everything else gets an explicit error in the official format; it never silently substitutes something similar.
Supported tasks:
text_to_model,image_to_model,multiview_to_model,texture_model,highpoly_to_lowpoly,mesh_segmentation,mesh_completion,mesh/uv,animate_prerigcheck,animate_rig,animate_retarget,convert_model,import_model,text_to_image,generate_image,image_to_multiview, plus task query, task list, balance, usage and file upload.Model versions:
v3.1-20260211,v3.0-20250812,v2.5-20250123andP2-20260801(Studio's Smart Mesh P2). Turbo, P1, v2.0 and v1.4 have no Studio equivalent and return an error listing the available versions. As in the official V3 API,modelis required.Narrower options:
texture_modeltakes a reference image but no text prompt;highpoly_to_lowpolyrequiresface_limit; rigging does not offer thetriposkeleton spec; retargeting takes presets only, one per task; multi-view needs all four views.Not supported: negative prompts,
style, refine, Gaussian splats, depth maps, USDZ, webhooks, WebSocket task watch.Projects are linear. Studio's post-processing rewrites a project's current model, so
original_model_task_idmust be the project's latest task, and a project runs one operation at a time. The official API has no such limit.Outputs are local. Finished files are cached in
~/.tripo/gateway/filesand served from signed local links.
The gateway listens on 127.0.0.1 by default. A key can spend your subscription credits, so do not hand it out, and think about who can reach the port before exposing it to your LAN.
Cost
Every generation spends Studio subscription credits: about 55 for a default text or image run. Choosing texture_quality=extreme adds more. The MCP calls themselves are free, and no API credits are touched.
Known limits
Formats are converted locally. Studio serves a GLB (or an FBX once a project has been quad-remeshed): when you export in its web app, it converts that file in your browser with an Assimp WASM worker, and
operation/export-litemerely records the action. This server does the same conversion on your machine with a bundled Assimp build, soformat: "fbx" | "obj" | "stl" | "3mf"works offline. FBX and OBJ come out as a folder holding the model plus its textures. If the project is already FBX and you ask for GLB, you get the FBX unchanged, because a second conversion would lose the quads.Animated downloads are merged locally. Studio stores each applied motion as a separate GLB that holds only bones and animation tracks. With
animated: truethe server merges it into the rigged mesh by bone name, so one file imports into Blender with mesh, armature and actions;all_animations: trueputs every applied motion in as its own action.Conversion needs the meshopt decoder. Tripo's GLB is gltfpack output using
EXT_meshopt_compressionandKHR_mesh_quantization; a stock Assimp cannot read it. The bundled build handles both. Seevendor/assimp/README.mdfor how to swap in your own build.Multi-view wants 2 to 4 images that match.
operation/multiview_to_modeltakes the sameimagearray as the single-image endpoint, but every element must have been uploaded and pass the image audit first, and the array order is the view order: front, left, right, back. Two views are enough; four give the best silhouette.S3 uploads bypass the proxy. The
PUTtotripo-data.s3.<region>.amazonaws.comgets its TLS handshake reset when routed through a local proxy, so those hosts connect directly and a failing proxy falls back to direct automatically.Some operations have model limits. Rigging needs at most 100k faces. UV unwrapping needs at most 80k triangles or 40k quads. Segmentation does not work on a quad-remeshed model. Upscaling must go above the current texture resolution, and H3.1 already outputs 4K, so in practice that means 8K (
extreme). Runtripo_remeshfirst when a model is too dense.No webhooks. The server polls
progressinstead. A tool waits up to 8 minutes by default; if it times out you getoperator_idandproject_id, and can fetch the model later withtripo_download.The cookie expires, usually after about a month.
No compatibility promise. These are internal endpoints; a Tripo redesign can break them at any time.
How it works
Recorded here so the next maintainer does not have to reverse-engineer it again.
text: POST /v2/studio/operation/text_to_model → task_id + project_id
image: POST /v2/studio/operation/batch_image_to_model → [{project_id, operator_id}]
poll: POST /v2/studio/progress {ids:[id]} → status / progress / left_time
fetch: GET /v2/studio/project/detail/v3/{project_id} → data.model_url (signed S3 URL)
quota: POST /v2/studio/operation/quota → special quota poolsImage upload takes three steps:
POST /v2/studio/storage/temporary_token {client:"aws", format:"webp"} → STS credentials + resource_bucket / resource_uri
PUT https://{bucket}.{host}/{resource_uri}?x-id=PutObject → SigV4, region us-east-1
POST /v2/studio/audit/image {image:{bucket,key}} → {result:"pass"}Five things cost real time to find:
Uploads go to the s3-accelerate endpoint. The signature must use
us-east-1, and thex-id=PutObjectquery string has to be part of the canonical request.You must send an explicit
Content-Length. Chunked uploads get a bare501 NotImplemented, and the reported offending header isTransfer-Encoding, which sends you looking in the wrong place.The image payload is an array, and every item needs both
image_audit_resultandimage_source. Miss either one and you get11002 Image audit result not found— a message that invites you to re-run moderation, when the real problem is an incomplete request body.imageonly accepts a{bucket, key}object. A string or a URL returns1004.progressoccasionally answers 502, so polling has to survive several consecutive failures.Export is a dead end on the server side.
operation/export-litereturns{data:{}}and the browser then converts the GLB itself with/_assimp/wasm/assimpjs-meshopt. Anything that claims to fetch a server-side FBX will fail withdownload_with_name→13001 Operator not found.
Security
The cookie inside studio-state.json is equivalent to your account credentials. Never commit it and never share it.
This project collects nothing and talks only to Tripo. Generated models are governed by Tripo's own terms.
Disclaimer
This project is not affiliated with or endorsed by Tripo. It uses internal endpoints of the web app, which may violate their terms of service, may stop working at any time, and may put your account at risk. It is meant for personal study and research; you use it at your own risk and the author accepts no liability. For commercial or production use, go with the official Tripo API.
License
MIT
Available Tools
18 toolstripo_animateA
给已绑定的模型套动画(operation/retarget_model)。三选一:preset 用内置动作(不生成新动作);motion_asset_id 复用已生成的动作;prompt 先用 motion/generate 文字生成动作(仅人形)。可选值用 tripo_list_motions 查。模型必须先 tripo_rig;取结果用 tripo_download 加 animated:true。
Inputs: project_id (required), preset, prompt, rig_type, +3 more.
tripo_completeA
部件补全:给 tripo_segment 拆出的部件补齐被遮挡的几何。mode=ai 调 operation/ai_completion(AI 补全),mode=quick_cap 调 operation/mesh_fill(快速封口)。项目必须先拆分。
Inputs: project_id (required), mode, part_names, wait_seconds, +1 more.
tripo_downloadA
把一个已有项目(project_id)的模型下载到本地。format 可选 glb / fbx / obj / stl,后三种在本地用 assimp 转换;FBX 和 OBJ 会连同贴图解到同名目录。
Inputs: project_id (required), format, animated, out_path, +3 more.
tripo_generate_imageA
参考图生成 3D 模型。对应内部接口 operation/batch_image_to_model(单图即长度为 1 的数组),参数名与官方文档 image_to_model 一致。本地图片会先上传到 Tripo 并送审,默认阻塞等待并下载 GLB。
Inputs: image_path (required), pbr, quad, texture, +18 more.
tripo_generate_multiviewA
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。
Inputs: image_paths (required), pbr, quad, texture, +17 more.
tripo_generate_textA
文字生成 3D 模型(Studio 订阅额度,H3.1 基准约 55 积分/次)。对应内部接口 operation/text_to_model,参数名与官方文档 text_to_model 一致。默认阻塞等待完成并下载 GLB。
Inputs: prompt (required), pbr, quad, texture, +17 more.
tripo_imageA
生成 2D 图片(对应官方 text_to_image / generate_image / image_to_multiview):文字生图、带参考图改图、套模板,或把一张图扩成前/左/后/右四视图。内部接口 image/gen_image_v2 + image/gen_multiview,结果下载为 PNG,可直接给 tripo_generate_image / tripo_generate_multiview 用。套餐内每月有免费生图次数。
Inputs: model, amount, prompt, t_pose, +8 more.
tripo_importA
把本地模型(GLB / FBX / OBJ / STL,≤150MB)导入 Studio 变成一个项目(对应官方 import_model),之后可以对它用 tripo_texture / tripo_remesh / tripo_rig / tripo_animate 等。内部接口 operation/import_user_model。
Inputs: model_path (required), name, wait_seconds, use_original_uv, +1 more.
tripo_list_motionsA
列出可用的动作:自己文字生成过的动作资产(可用 motion_asset_id 复用),以及按骨骼类型分组的内置预设动作名。
Inputs: rig_type.
tripo_list_projectsB
列出账号里的模型项目(按时间倒序),拿 project_id 给其他工具用。对应内部接口 assets/v2。
Inputs: size, offset.
tripo_pbrB
给已有贴图的项目生成 PBR 材质(金属度/粗糙度/法线),对应内部接口 operation/pbr_generate。
Inputs: project_id (required), wait_seconds, model_version.
tripo_remeshA
重拓扑/减面:把已有项目重新布线到指定面数,对应内部接口 operation/remesh。会覆盖项目当前模型(生成新版本),完成后用 tripo_download 取。
Inputs: project_id (required), bake, quad, face_limit, +3 more.
tripo_rigA
自动骨骼绑定:先跑 operation/pre_rig_check(免费,对应官方 animate_prerigcheck),再调 operation/rigging_model。人形可选骨骼规范(Mixamo / UE5 / Unity / ActorCore / VRM);非人形按预检给出的 rig_type 绑。模型面数需 ≤10 万,否则先 tripo_remesh。
Inputs: project_id (required), spec, force, rig_type, +3 more.
tripo_segmentB
部件拆分,对应内部接口 operation/ai_segmentation。只支持未经重拓扑的原始网格;重拓扑过的项目会没反应。
Inputs: project_id (required), granularity, wait_seconds, model_version.
tripo_statusB
查看 Tripo Studio 账号状态:剩余积分、套餐、到期时间、特殊额度;可查某个操作的进度和最近的积分流水。
Inputs: ledger, task_id.
tripo_textureA
重新生成贴图,对应内部接口 operation/texture_model。可以给一张参考图,也可以不给(纯靠几何推纹理)。会覆盖项目当前模型,完成后用 tripo_download 取。
Inputs: project_id (required), delight, image_path, part_names, +3 more.
tripo_upscaleB
纹理放大到 4K / 8K,对应内部接口 operation/texture_upscaler。项目必须已有贴图。
Inputs: project_id (required), wait_seconds, model_version, texture_quality.
tripo_uvA
智能 UV 展开:uv_edit/context → generate(首次,消耗 uv_edit 额度)或 retry(同一上下文内前 3 次免费)→ apply。已有候选且 next_action=apply 时直接应用,不再消耗额度。模型需 ≤8 万三角面或 ≤4 万四边面,超了先 tripo_remesh。
Inputs: project_id (required), apply, candidate_id, wait_seconds.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools map to clearly distinct pipeline stages (generate, remesh, uv, rig, animate, segment, pbr, upscale), and descriptions explicitly disambiguate overlapping ones like tripo_texture vs tripo_pbr vs tripo_upscale. The weakest pair is tripo_image (2D image generation) vs tripo_generate_image (image-to-3D), whose names invite misselection even though the descriptions clarify.
All tools share a tripo_ prefix and snake_case, which is highly predictable. However, the stems mix verb_noun (generate_text, list_projects, download) with bare nouns/verbs (status, remesh, uv, rig, pbr, image, complete), so the pattern is recognizable but not uniform.
18 tools is slightly above the comfortable range, but this is a multi-stage 3D asset pipeline where each tool corresponds to a genuine, non-redundant operation. No tool looks padded, and consolidating further (e.g., merging rig/animate) would harm clarity.
Strong lifecycle coverage: import, text/image/multiview generation, remesh, texture, UV, rig, animate, segment, complete, PBR, upscale, plus discovery (list_projects, list_motions) and download. Gaps are operational rather than core — no delete/cleanup, no explicit cancel-job, and no asset/project metadata retrieval beyond listing.
Maintenance
Related MCP Connectors
Generate and edit images, video, voice, lip-sync and 3D models from your AI agent.
Let your AI agent operate any website through a real, logged-in browser session.
Turn text or an image into an animation-ready 3D model (GLB): generate, rig, animate, retexture.
Generate 3D models, worlds, PBR materials, and coordinated asset packs from AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with the Tripo3D AI API to generate 3D models from text, images, or multiview inputs. It supports advanced features like model animation, stylization, and real-time task status tracking.7ISC

Meshy MCP Serverofficial
AlicenseAqualityBmaintenanceEnables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation.2826,720 npm93MIT- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation using the Meshy AI platform.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create, edit, and export 3D models (GLB, USDZ) from natural-language descriptions and YAML, with rendering and problem detection.16 npmMIT