outfit-assistant
Your own closet in your AI: outfits from clothes you own, rendered on a model inline.
Install
mcp_config.json
{
"mcpServers": {
"ai-outfitmaker-outfit-assistant": {
"url": "https://outfitmaker.ai/mcp/wardrobe",
"type": "streamable-http"
}
}
}Documentation
OutfitMaker MCP Server
Ask your AI assistant what to wear. OutfitMaker speaks MCP, so Claude, ChatGPT, Cursor and every compatible client can get weather-aware outfit advice with one URL.
Server URL:
https://outfitmaker.ai/mcp
Transport: Streamable HTTP. No API key, no account, free.
Connect in 10 seconds
Claude (web and desktop): Settings, Connectors, Add custom connector, paste the URL.
Claude Code:
claude mcp add --transport http outfitmaker https://outfitmaker.ai/mcp
Cursor / Windsurf / any client that accepts remote MCP servers by URL: same address, HTTP transport.
Tools
| Tool | What it does |
|---|---|
what_to_wear_today | Live weather for your city (today or tomorrow with day=tomorrow) plus a complete outfit formula for the occasion. Detects big morning-to-afternoon temperature swings and adds layering advice. |
suggest_outfit | Curated outfit formulas: 7 occasions across every weather. Accepts min/max temperature and wind for layering and footwear advice. Weather words work in 5 languages. |
about_outfitmaker | What connecting your real closet unlocks. |
Example, asked in Claude on a September evening:
Tomorrow in Besancon: 13C in the morning up to 22C, clear sky.
Denim jacket over a plain tee + chinos + white sneakers
Heads-up: 9C swing between morning and afternoon: build on a light base with a removable layer you can shed at midday.
The tools are generic. Your closet isn't.
These formulas are what a good stylist would tell a stranger. The real product is OutfitMaker: photograph your wardrobe once, get daily outfit suggestions from clothes you actually own, weather-aware, previewed on a model. Free to start.
Full setup guide: outfitmaker.ai/mcp
Launch story: Ask your AI what to wear
Notes
- Rate limited per IP (fair use).
- No account data is exposed: the public tools are anonymous by design.
- Server implemented in Rails with the official mcp gem.
Sourced from the repository README.
More in AI & Agents
- PonytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.109,599
- AgentsMulti-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity39,079
- Frontend SlidesCreate beautiful slides on the web using a coding agent's frontend skills28,060
- Agent Skills Search ServerSearch and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.25,980
- Agency Agents Zh🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉等)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。19,868
- Watermarks RemoverStrip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD17,822