Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Virtual try-on (VTO) API docs and SDK examples; OAuth account/guest photo uploads and try-ons.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://studio.v3lox.com/partner/trifit/mcpRun this in your terminal
claude mcp add --transport http velox-trifit-developer https://studio.v3lox.com/partner/trifit/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"velox-trifit-developer": {
"url": "https://studio.v3lox.com/partner/trifit/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"velox-trifit-developer": {
"type": "http",
"url": "https://studio.v3lox.com/partner/trifit/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://studio.v3lox.com/partner/trifit/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
get_trifit_accountIdentify 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_profileRead 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_allowanceRead the same daily, weekly and monthly allowances as the TriFit website. Does not create, reset or spend credits.
list_trifit_libraryRead metadata for your saved personal photos, products, looks and DressMe requests. No image bytes or guest history transfer.
prepare_trifit_uploadFor 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_imageWith 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_onOnly 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_onRead 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_onShow 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_statusRead the current private guest-session allowance and its perSessionLimit denominator. Does not upload images or generate anything.
prepare_guest_uploadFor 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_onGenerate 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_onRead 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
searchFind official Velox DressMe virtual try-on integration documentation, authentication, SDK languages, upload, polling and recovery guidance. Searches only the deployed public documentation corpus.
fetchRead 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_exampleRetrieve 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_requirementsExplain 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_guideRead 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
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account Velox-XR, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 387 ms (HTTP 200)
No sign-in needed
Read 18 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (2.0.1) reached the registry 12 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
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.
| 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.
| 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.
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.
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.
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.
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
Only the beginning is shown; read the rest in the repo