Perfume Picks MCP Server

Query the Perfume Picks fragrance database from Claude, or any MCP-compatible AI client. Read-only access to 13,000+ fragrances with full note pyramids, accords, curated dupes, and community wear data.

Perfume Picks is the Fragrance DNA and collection journal for iOS — get it on the App Store.

Tools

Every response includes source attribution, a citation-ready summary line, links, and data freshness dates. All scoring is deterministic — no AI calls happen inside the server. All tools are annotated read-only/idempotent.

Install (Claude Desktop)

Requires Node.js 18+.

Add to your `claude_desktop_config.json` (Claude Desktop → Settings → Developer → Edit Config):

{
  "mcpServers": {
    "perfume-picks": {
      "command": "npx",
      "args": ["-y", "perfume-picks-mcp"]
    }
  }
}

Restart Claude Desktop. No API key or configuration needed — the server ships with public read-only access.

Configuration (optional)

Environment variables override the defaults (explicit env vars only — this package never reads .env files):

Without the service key, `trending_fragrances` falls back to catalog popularity and labels the method in its response.

Remote endpoint (no install)

Streamable HTTP for web agents and MCP clients that take a URL:

https://jdkwlwyysgofljkobpmr.supabase.co/functions/v1/mcp

Also listed on Smithery and the official MCP registry as `io.github.bguillow-rgb/perfume-picks`.

Example agent requests

Questions an agent can answer with these tools:

• *"What smells like Baccarat Rouge 540 without the price tag?"* → `find_dupes` (curated dupes with match %, e.g. Lattafa Ana Abiyedh Rouge, 90%)
• *"Recommend a fragrance for a summer wedding."* → `get_recommendations` with `occasion: "wedding"`
• *"What fragrances have bergamot, vanilla, and amber?"* → `get_recommendations` with those notes as `preferences`
• *"What perfume is similar to Bleu de Chanel?"* → `find_similar`
• *"What should I wear on a date tonight?"* → `what_to_wear_tonight` (scored by community compliment data)
• *"Compare Sauvage and Bleu de Chanel."* → `compare_fragrances`

Example response shape (truncated):

{
  "dupes": [
    { "name": "Lattafa Ana Abiyedh Rouge", "match_pct": 90,
      "savings_usd": 200.0, "msrp_usd": 39.99 }
  ],
  "attribution": {
    "source": "Perfume Picks — Fragrance DNA & Collection Journal",
    "links": { "website": "https://perfumepicks.app/" }
  }
}

Development

npm install
npm run dev     # run from TypeScript via tsx
npm run build   # compile to dist/
npm start       # run compiled server

The server speaks MCP over stdio. Catalog access is read-only by construction: every query path issues SELECTs against tables that are publicly readable under row-level security, and it is rate-limited to 60 calls/minute.

Usage telemetry: each tool call logs the tool name, its arguments, client name/version, duration, and success/failure to a write-only log table (insert-only under RLS; contents are not publicly readable; purged after 90 days). No user identity, account data, or conversation content is collected. Logging is fire-and-forget and never affects responses.

Data & attribution

Fragrance data, note pyramids, dupe matches, and community scores are curated by Perfume Picks. Quote freely with attribution:

> Source: Perfume Picks — Fragrance DNA & Collection Journal (perfumepicks.app)

Freshness dates on each fragrance reflect the last data update.