Velox TriFit: Virtual Try-On API

Name: Velox TriFit: Virtual Try-On API
Author: Velox-XR

作者：Velox-XR版本 2.0.1i★ –i在云端运行

注册名称io.github.Velox-XR/velox-trifit-developer

安装

概览

作者提供的说明（英文原文）

Virtual try-on (VTO) API docs and SDK examples; OAuth account/guest photo uploads and try-ons.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i3 项中通过 3 项依据公开信息检查；尚未扫描代码
使用情况i非常新★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在云端运行
传输方式: Streamable HTTP
分类: 设计、图片与音频

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：3 项中通过 3 项
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
可以做 18 件事（工具） get_trifit_account, get_trifit_profile, get_trifit_allowance, list_trifit_library …
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://studio.v3lox.com/partner/trifit/mcp

在终端中运行这条命令

claude mcp add --transport http velox-trifit-developer https://studio.v3lox.com/partner/trifit/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "velox-trifit-developer": {
      "url": "https://studio.v3lox.com/partner/trifit/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "velox-trifit-developer": {
      "type": "http",
      "url": "https://studio.v3lox.com/partner/trifit/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://studio.v3lox.com/partner/trifit/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月7日报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

get_trifit_account
Identify whether this verified connection is a guest session or a personal TriFit account before choosing tools. Does not link, switch, create an account or trust a conversational email hint.
get_trifit_profile
Read the stable profile represented by this connection. No account creation, switching, uploads or generation. Use get_trifit_account for connection mode and allowance source.
get_trifit_allowance
Read the same daily, weekly and monthly allowances as the TriFit website. Does not create, reset or spend credits.
list_trifit_library
Read metadata for your saved personal photos, products, looks and DressMe requests. No image bytes or guest history transfer.
prepare_trifit_upload
For a user-selected local file in Codex, with explicit permission: create a private, one-use upload URL valid for at most five minutes. PUT only that JPEG/PNG/WebP file as raw bytes, with its image Content-Type, no API/OAuth headers and no redirects. Do not print or share the URL
upload_trifit_image
With explicit permission, import the selected personal or clothing image into the connected TriFit account. Resizes automatically, saves it in the website library and selects its photo/product slot. Product images also use the existing cached description preparation. Never import
create_trifit_try_on
Only after explicit user approval, submit one DressMe request using two existing account image IDs. Uses the website queue and existing account allowance, not the guest demo. The attempt can consume allowance. Never automatically retry, replace the request ID or claim that a time
get_trifit_try_on
Read the status, recorded duration and result ID of an existing account DressMe request without generating or replaying. A missing receipt means acceptance is uncertain, not that it never ran.
show_trifit_try_on
Show a completed account DressMe image inside the conversation. Requires separate private-image permission. Uses only the existing result; no generation, upload, public share or new allowance is used.
get_guest_demo_status
Read the current private guest-session allowance and its perSessionLimit denominator. Does not upload images or generate anything.
prepare_guest_upload
For Codex/local files: reserve one single-use HTTPS PUT upload for a personal photo or product image. Upload the user-selected file bytes to the returned URL; do not disclose that capability. Server resizes JPEG, PNG or WebP automatically. At most one upload per role per guest se
create_try_on
Generate a DressMe virtual try-on from the user’s personal photo and clothing reference only after their explicit request and permission. In ChatGPT pass both attached image files; in Codex pass the two asset IDs returned by completed private uploads. Use one method, not both. Co
get_try_on
Read only an existing request belonging to this authenticated guest session. With include_image=true, shows the completed image in a result card in ChatGPT and an inline image in other MCP clients. Does not create/retry a generation. Poll no more often than once every five second
search
Find official Velox DressMe virtual try-on integration documentation, authentication, SDK languages, upload, polling and recovery guidance. Searches only the deployed public documentation corpus.
fetch
Read the full public document for an ID returned by search, with an official source URL and deployed content checksum. Does not fetch arbitrary URLs or private files.
get_integration_example
Retrieve the runnable offline JavaScript/Node.js integration example or accompanying TypeScript declarations. Other language SDKs are not released. The example uses dummy local responses, with no cloud calls or generation charges.
get_partner_access_requirements
Explain how to apply for manually provisioned Velox Partner API access and keep the scoped application key on a backend. Does not create accounts, issue keys, send an application or promise a universal free allowance.
get_partner_application_guide
Read the official in-chat Partner API application workflow: partner@v3lox.com, sender confirmation, optional project details, draft preview, send approval and actual reply verification. Public guidance only; this tool does not send email, inspect a mailbox, submit a form, issue k

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 Velox-XR 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
✓ 通过
端点有响应
在 387 毫秒内响应（HTTP 200）
– 不适用
使用 OAuth 登录
无需登录
✓ 通过
工具描述中没有隐藏指令
已读取 18 个工具描述，未发现针对 AI 的隐藏指令

与“设计、图片与音频”中的其他服务器比较i

星标数多于此分类中其他 2784 个服务器的 0%
发布到注册中心的时间比此分类中其他 2784 个服务器的 74% 更新
基础检查结果等于或优于此分类中其他 2784 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Velox TriFit: Virtual Try-On API 安全吗？

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（2.0.1）于12天前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Figma Context MCP, Claude Real Video, Figma MCP Server

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Figma Context MCP

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

作者：GLips广泛使用↓ 16.1万/周★ 1.6万5个月前更新

在你的电脑上运行

安装

Claude Real Video

Let any LLM watch a video locally — and search everything it has ever watched.

作者：HUANGCHIHHUNGLeo广泛使用↓ 1106/周★ 22842个月前更新

在你的电脑上运行

安装

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

作者：figma正在增长★ 215213个月前更新

在云端运行✓ mcp.figma.com

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Velox TriFit — Virtual Try-On API, MCP Server and JavaScript SDK

Build virtual try-on (VTO) into a website, mobile app or retail platform with the Velox TriFit Partner API, or connect a coding agent to the Velox TriFit MCP server for official API guidance or a user-approved account/guest clothing preview. Use the hosted MCP connection and tool reference for the latter; authenticated client acceptance remains incomplete. DressMe is the virtual try-on operation: it turns a shopper photo and a garment image into an AI outfit preview. The TriFit app is the consumer experience; using it is separate from obtaining Partner API credentials.

This official developer repository contains the JavaScript SDK with TypeScript declarations, runnable REST integrations, tutorials, Codex, GitHub Copilot and Gemini CLI MCP configuration examples, and a portable integration skill. Read the API overview, then choose the integration route below. Other languages can use the documented HTTP API; this repository does not claim an unshipped SDK.

Virtual dressing and visual fitting rooms

Use DressMe for photo-based virtual dressing: a shopper photo and clothing reference produce an AI outfit preview. A virtual fitting room built with DressMe provides a visual preview, not body measurements, clothing-size prediction or a guarantee of physical fit. The REST quickstart explains the upload, job submission and status flow; the JavaScript SDK provides the integration code.

Choose REST API or MCP

Integration route	What it provides	Start here
REST API in your application backend	Submit virtual try-on requests using your separately approved partner configuration; keep keys out of browsers and mobile apps	REST quickstart · JavaScript SDK · Access requirements
MCP in a coding agent	Search official docs, fetch API contracts and get integration examples while building an application	Virtual try on MCP: Codex, Copilot and Gemini setup · Public MCP guide
MCP for a personal clothing preview	Use the connected TriFit account or limited guest session through normal OAuth and consent; generation uses that route's allowance	Hosted endpoint, inputs and result tools · Verified release status
Portable integration skill	Reusable instructions for an agent to plan and implement the integration; it can also use the public source without MCP	Skill source and installation

For a new direct MCP connection, use https://studio.v3lox.com/partner/trifit/mcp. Documentation-only work needs no TriFit sign-in or Partner API key: allow only search, fetch, get_integration_example and get_partner_access_requirements as described in the client guide. The server as a whole is not read-only. Its account/guest upload and try-on tools require separate OAuth authorization and user consent; they are not part of a documentation check. Connecting MCP or installing a skill does not grant Partner API credentials, generation allowance or deployment access.

The published OpenAI Developer plugin is a separate installation route. Its existing reviewed connection is managed separately; a new direct MCP setup or this README update does not migrate it.

Start here

Want to…	Go here
Try without an account	Hosted demo — free shared, limited queue
Try with your own saved photos, products and history	TriFit app — sign in/create an account and use its available free daily/weekly/monthly allowance
See your demo requests and download the SDK ZIP	Demo dashboard & SDKs
Explore immediately on your computer, without credentials	Download this repository; run `npm run preview` with Node.js 22+
Build a real integration	Getting started · Apply for access
Run real DressMe from code with my existing TriFit account, without a partner key	Example 2: account sign-in
Understand which access route to use	All DressMe options
Read the API flow	Technical walkthrough
Choose an SDK	SDK catalogue
Use Codex or GitHub Copilot to build a web/mobile integration	MCP setup and mobile starter prompt · Portable integration skill
Use Gemini CLI or Google Antigravity for API guidance	Native Google client setup — documentation tools only
Verify the agent connection, then build safely offline	Four-call MCP check · Agent-to-backend tutorial
Install the published OpenAI Developer plugin	Velox TriFit Developer — read-only API guidance
Connect the current MCP server	Velox TriFit MCP — protocol endpoint; documentation-only client setup · account/guest connection reference
Find the current MCP server in the official registry	Velox TriFit registry listing · Publication record
Find the public API overview	Velox TriFit Partner API

Two public pages, not the Velox operator admin. The dashboard shows only the visitor's own browser-session requests and public SDK downloads. It exposes no keys, routing, quota editing, other visitors' photos or traffic-test controls. Hosted UI updates follow the Studio Development-to-Production release gates; the public host may run an earlier accepted version than the source you inspect.

See real public try-on examples

Existing official TriFit examples: AI personal portraits, clothing references and their actual TriFit outputs. These are historical examples, not mocks, newly run tests or performance/quality comparisons. Provenance and media notes.

Example	Personal photo	Clothing reference	TriFit result
Amara · activewear
Mateo · overshirt

Try your own photos in the TriFit app with available account allowance, or the shared demo without an account. The live host receives UI updates through its separate release.

Outfit-collage starter products

The demo source includes the same five clothing collages used in our provider comparison tests, copied without image edits. Select a whole board as the product reference and use a separate personal photo. Reference models inside a board are not the target person. Accessory transfer and garment fidelity can vary.

Green trench · details	Green trench · full look	Burgundy trench & skirt

Navy blazer & argyle skirt	Leather jacket & denim

These are product inputs, not generated result images or proof of provider rankings. They are separate from the matched Amara/Mateo examples above. Brand names within the boards do not imply endorsement.

Install the Codex plugin

The Velox TriFit Developer OpenAI listing is published as Velox TriFit API Docs 1.1.6 (verified 28 October 2026). Its reviewed binding remains the legacy /partner/docs/mcp with four public documentation tools. It has not migrated to the unified endpoint. You can also connect the public documentation MCP directly in Codex or Copilot without installing the full plugin. Neither route grants live Partner API access. The official MCP Registry listing, io.github.Velox-XR/velox-trifit-developer version 2.0.1, was independently verified active and latest on 28 October 2026. It points to the current connection: https://studio.v3lox.com/partner/trifit/mcp. This follows 2.0.0 and supersedes the initial 1.1.0 legacy-endpoint publication under the same identifier, not a second listing. GitHub's curated registry onboarding is pending; the listing request has been submitted, not approved. See the publication record and update checklist. Registry publication does not guarantee search rankings or automatic agent recommendations.

See installation and test prompts. The GitHub marketplace package is separate from universal directory review and approval.

Velox TriFit — API guidance and try-on in one plugin

The Velox TriFit ChatGPT/Codex plugin combines API guidance with consented account or guest try-on in one package. The v1.2.3 Production-targeted source and reproducible ZIP builder are available for inspection. The current Production endpoint's initial 18-tool inventory and four anonymous documentation calls were verified on 24 October 2026. The 1 November check covered all five public tools; see the dated release status. Neither check proves authenticated try-on/client acceptance or public-directory approval. This repository distributes Production packages only. Private D

只显示了开头部分；其余内容请在仓库中阅读