Capsule Wardrobe

Inspiration

A useful outfit planner should respect what is actually clean and available, not just suggest an ideal combination. Capsule Wardrobe models that small inventory constraint.

What it does

It stores garments with category, color labels, warmth, and clean state; selects clean garments for required categories at an entered temperature; marks worn items unavailable; and resets them after laundry. Occasion is retained as descriptive context.

How we built it

Python tools use SQLite-backed state and are exposed through a local Python MCP server tested via Streamable HTTP (MCP 2025-11-25). A static browser replay, when used, is a JavaScript/localStorage equivalent and is not connected to MCP or Alexa.

Challenges

The planner must honor clean availability and required categories while keeping manually entered temperature separate from real weather and avoiding claims of style intelligence.

What we learned

Inventory state and explicit constraints are enough to make a small planning workflow demonstrable without pretending to understand dress codes.

Accomplishments

The local workflow and fresh Streamable HTTP transcript verify adding garments, planning a required-category outfit, and marking a garment worn.

What's next

Add optional weather input, stronger preference handling, accessibility considerations, and more expressive wardrobe views with user-controlled privacy.

This is a local single-user prototype: no cloud or LLM claim, no camera, forecast, advanced color/style matching, Alexa/Echo integration, laundry automation, or dress-code reasoning.

Built With

• css3
• fastmcp
• html5
• javascript
• json-schema
• localstorage
• model-context-protocol
• pytest
• python
• sqlite
• streamable-http