Caffeinated Wardrobe
Caffeinated Wardrobe is like an API for your closet.
What it can do
- List Tags: Get all unique tags used by the current user for their items.
- Create Item: Create a new wardrobe item. For brands, colors, and stores, you can provide either the name or ID: - brand: "Nike" (auto-creates if not found) OR brand_id: UUID - color: "Blue" (auto-crea
- List Items: Get a list of all wardrobe items with reduced details for MCP efficiency.
What data it sees
Do you need an account
No: the server works without sign-in
Caffeinated Wardrobe is like an API for your closet. This MCP server brings programmatic wardrobe management to any MCP-compatible AI client - track clothing items, compose (and remember) outfits, analyze wear patterns, and get AI-powered styling recommendations. Combine with filesystem, calendar, or browser MCP servers for context-aware outfit suggestions based on your schedule, weather, or recent purchases.
How to connect
How to connect Caffeinated Wardrobe to Claude
The server address to paste into Claude settings:
https://caffeinated-wardrobe--michelle.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Caffeinated Wardrobe to ChatGPT
The server address to paste into ChatGPT settings:
https://caffeinated-wardrobe--michelle.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Caffeinated Wardrobe to Cursor
The server address to paste into Cursor settings:
https://caffeinated-wardrobe--michelle.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (20)
Raw names from tools/list. Only developers need these.
| list_tags | Get all unique tags used by the current user for their items. |
| create_item | Create a new wardrobe item. For brands, colors, and stores, you can provide either the name or ID: - brand: "Nike" (auto-creates if not found) OR brand_id: UUID - color: "Blue" (auto-creates if not found) OR color_id: UUID - store: "Amazon" (auto-creates if not found) OR store_id: UUID You can also provide image_urls to upload images from publicly accessible URLs. Images will be uploaded after the item is created. If any image URLs fail to upload, the item will still be created successfully. No need to check if brands/colors/stores exist first - the system handles this automatically. |
| list_items | Get a list of all wardrobe items with reduced details for MCP efficiency. |
| get_item_details | Get details of a specific wardrobe item. |
| update_existing_item | Update an existing wardrobe item. For brands, colors, and stores, you can provide either the name or ID: - brand: "Nike" (auto-creates if not found) OR brand_id: UUID - color: "Blue" (auto-creates if not found) OR color_id: UUID - store: "Amazon" (auto-creates if not found) OR store_id: UUID You can also provide image_urls to upload images from publicly accessible URLs. Images will be uploaded after the item is updated. If any image URLs fail to upload, the item will still be updated successfully. No need to check if brands/colors/stores exist first - the system handles this automatically. |
| delete_item | Delete a wardrobe item. |
| upload_images_from_urls | Upload images for a specific wardrobe item from URLs. Designed for MCP tools to avoid base64 encoding overhead. |
| delete_image | Delete an image associated with a specific wardrobe item. |
| set_default_image | Set a specific image as the default for a wardrobe item. |
| get_related_items | Get all items that are related to the specified item. |
| create_item_relationship | Create a new relationship between two items. |
| delete_item_relationship | Delete a relationship between two items. |
| get_item_wear_history | Get wear history for a specific item. |
| list_outfits | Get a list of all outfits. |
| create_outfit | Create a new outfit. |
| get_outfit_details | Get details of a specific outfit. |
| update_outfit | Update an existing outfit. When modifying the item composition of an outfit that has been worn, a new outfit will be automatically created with the updated composition. The original outfit and its wear history will be preserved. The response will include the new outfit ID and a flag indicating whether a new outfit was created. Examples: - Updating unworn outfit composition: Returns updated outfit with new_outfit_created=False - Updating worn outfit composition: Returns new outfit with new_outfit_created=True - Updating outfit metadata only: Returns updated outfit with new_outfit_created=False |
| delete_outfit | Delete an existing outfit. |
| get_outfit_wear_history | Get wear history for a specific outfit. |
| record_wear | Record that an item or outfit was worn at a specific date/time. Will default to now if not provided. |