Agent skills
Install repeatable Uwear workflows or read the machine-readable manifest before connecting a tool.
Product · MCP
Turn every fashion brief into a reusable production workflow.
Bring the AI assistant and subscription you already use, whether that is Claude, ChatGPT, Codex, or another compatible client. Run the work manually in Uwear, drive supported tools through MCP, or build with chat inside the Automation Builder canvas. Carry one brief through art direction, generation or edits, automatic QA, and repeatable runs.
Uwear MCP
Shoot this drop as an urban editorial. One model across every look.
Opening your catalog. Pick the garments and the model, then confirm the context.
I prepared 19 looks, one image per look, QA enabled. Estimated total: 76 credits. Nothing runs until you confirm.
The flow in miniature: ask, pick the context, approve the costed brief. Nothing runs without your confirm.
Agent Mode is moving into workflow-building and MCP. We are retiring the standalone Agent Mode destination, while keeping conversational help where production happens: inside the Automation Builder canvas and, where supported, inside the AI assistant you already use through Uwear MCP. Your Uwear assets and production history stay connected as you turn a brief into art direction, generation or edits, automatic QA when enabled, and a reusable workflow you can review and run again.
Install
Connect your assistant. Build the workflow once.
Bring the AI assistant and subscription you already use, whether that is Claude, ChatGPT, Codex, or another client that supports remote MCP servers. With the Uwear tools available through MCP, your assistant can prepare the brief, shape art direction, start generation or edits, and run automatic QA when enabled. You keep approval points where you need them. Automation Builder carries the same production chain into a reusable workflow you can adjust, rerun, or guide with chat inside the canvas.
Start with a local agent if you can. Claude Code and Codex read garments straight from your folders and write finished images back to disk, exactly where your pipeline expects them. Chat workspaces take a short trip through Settings.
One command, then authenticate. A local agent reads your product folders and writes results back to disk.
- 1
Add the server:
claude mcp add --transport http uwear https://api.uwear.ai/mcp
- 2
Run /mcp inside Claude Code and complete the OAuth login with your Uwear account.
- 3
Ask for a Uwear photoshoot plan. The brief comes back for approval before any run.
The full agent surface
The MCP endpoint is the action layer. Skills, UWEAR.md, llms.txt, the JSON blog API, and the REST API help agents discover Uwear, learn the production contract, and choose the right way to work.
Agent-readable docs
UWEAR.md documents the production contract. llms.txt gives AI crawlers a concise map of the product.
JSON content API
A public, structured feed lets agents discover Uwear product guides and updates without scraping pages.
REST API
No MCP client? The same production over REST, with webhooks, QA, and metadata traceability.
See the workflow from prompt to costed brief in How to run an AI fashion photoshoot without leaving ChatGPT or Claude.
The toolkit
Ask for work, not for features.
Each of these is one message in the chat where you installed Uwear. Every generation stops at a costed brief before credits are spent.
01
One prompt becomes a costed brief.
Uwear MCP
Shoot this drop as an urban editorial. One model across every look.
I prepared 19 looks, one image per look, QA enabled. Estimated total: 76 credits. The brief is ready to review; nothing runs until you confirm.
02
Local agents read your files.
Uwear MCPIn Codex
Here is drops/s26/line-sheet.csv. Prepare a photoshoot plan for every SKU and show me the cost first.
Read 24 SKUs from the line sheet and matched them to the workspace. One image per SKU comes to 96 credits. Want the itemized plan?
drops/s26/
line-sheet.csv · 24 SKUs
flats/ · 24 images
plan
24 looks · one image per SKU
estimated 96 credits
✓ brief ready for review
03
QA comes back with reasons.
Uwear MCP
Run QA on the finished results and retry anything rejected.
Queued QA on 3 results. 2 approved, 1 rejected: five visible buttons instead of the four on the reference jacket. I re-ran it with the fix; the retry passed every check.
Rejected: five buttons
Approved on retry04
Results land where you work.
Uwear MCPIn Claude Code
Download the approved images into assets/pdp, named by SKU.
Done. 12 files written to assets/pdp, named from the metadata on each garment.
assets/pdp/
DJ-2026-BLU_front.jpg
DJ-2026-BLU_detail.jpg
SK-2026-TPE_front.jpg
...
✓ 12 files written
05
Every top meets its best bottom.
Uwear MCP
Pair every hoodie with the bottom that sells it, then shoot the set on one model.
Proposed 9 pairings from 3 tops and 3 bottoms, shot on the same model. The approved set is in your workspace.
Enterprise
Built for catalog work that starts outside Uwear.
Use the MCP when production begins in a conversation, a shared folder, a product feed, or an agentic workflow.
Creative teams
Turn one seasonal direction into consistent PDP, editorial, and video outputs.
Ecommerce teams
Prepare SKU-level production runs from product data without rebuilding briefs by hand.
Technical teams
Let Codex organize folders, CSVs, and briefs, then route approved work through Uwear MCP.
One platform, three ways in
The same production infrastructure, reached your way.
Studio, API, and the MCP share one model library, one clothing workspace, and one generation history. Pick the access path that fits the work, and move between them as the job changes.
Programmatic access
API
A REST API for async generation, edits, video, and identity. Wire production workflows into your catalog, DAM, and storefront.
ExploreOperator interface
Studio
The visual workspace for creative production. Batch catalogs, consistent models, edits, backdrops, video, and upscaling in one surface.
ExploreIn your own tools
MCP
Connect Uwear to Claude, ChatGPT, or any MCP client and run photoshoots from the tools your team already uses.
You are here
MCP FAQ
What enterprise teams usually ask about the MCP app.
A remote MCP server that turns your AI assistant into a fashion photoshoot tool. Inside ChatGPT, Claude, or Codex, the assistant browses your clothing and models, assembles looks, and prepares a costed photoshoot brief that you review and approve before anything runs.
Yes. Connect the Uwear MCP server and ask for a shoot in plain language. The assistant does the work on your behalf: it reads your garments, picks models, plans the looks, and shows you the itemized cost. Generation runs on Uwear once you confirm, and the finished product photos land in your workspace.
Because you never leave the chat. The assistant already has your context, from folders and CSVs to line sheets and earlier messages, so there is nothing to re-upload or re-explain. It handles the production steps for you, and the brief-approval gate keeps every credit spend under your control.
ChatGPT and Claude connect through their app and connector settings. Claude Code and Codex connect with one command plus an OAuth login. Any client that supports remote MCP servers works with the same URL, and agents can also read uwear.ai/llms.txt or UWEAR.md directly.
No. Every run goes through brief review first: the itemized looks, the request count, and the exact credit cost. Generation only starts after you confirm.
In your Uwear workspace, in the same library Studio uses. You can review and QA them in Studio, keep iterating in chat, or pull them through the API.
No. MCP authenticates with your existing Uwear account. Studio, the API, and MCP all use the same credits and asset workspace.
Run the first collection brief.
Install the MCP in your workspace, or bring one catalog workflow and we will run it with you.
Existing customer? Log in to Studio
Pairs with Studio · API · Batch workflows
