Skip to main content
Glama
Perfume Picks MCP Server

Perfume Picks MCP Server

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

Tool

What it does

search_fragrances

Full-text catalog search with brand, family, gender, and MSRP filters

get_fragrance

Full record for one scent (by slug or name): note pyramid, accords, community scores

find_dupes

Curated cheaper smell-alikes with match percentage — "what smells like X without the price tag"

find_similar

Most-similar fragrances from a precomputed similarity ranking

get_recommendations

Picks from note/accord preferences + budget + occasion + gender

compare_fragrances

Side-by-side: notes, shared/distinct accords, scores, price delta

trending_fragrances

What Perfume Picks users are adding to their wardrobes right now

what_to_wear_tonight

A scent for right now — date-night picks use community compliment data, office picks use office-safety scores

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.

Related MCP server: Epicure MCP Server

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):

Variable

Purpose

SUPABASE_URL

Override the database URL

SUPABASE_SERVICE_ROLE_KEY

Internal use only — unlocks live 30-day wardrobe-add trending. Never distribute this key.

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.

Available Tools

8 tools
compare_fragrancesCompare two fragrancesA
Read-onlyIdempotent
Inspect

Side-by-side comparison: note pyramids, shared and distinct accords, longevity/sillage/compliment scores, concentration, and price difference.

Inputs: fragrance_a (required), fragrance_b (required).

find_dupesFind dupes (cheaper smell-alikes)A
Read-onlyIdempotent
Inspect

Curated dupes for a fragrance — cheaper scents documented to smell like the original, with match percentage and price comparison. The answer to 'what smells like X without the price tag'.

Inputs: fragrance (required).

find_similarFind similar fragrancesA
Read-onlyIdempotent
Inspect

Fragrances most similar to a given one, from Perfume Picks' precomputed similarity ranking over notes and accords.

Inputs: fragrance (required), limit.

get_fragranceGet fragrance detailsA
Read-onlyIdempotent
Inspect

Detailed record for one fragrance: full note pyramid (top/heart/base), accords, concentration, community longevity/sillage/compliment scores, and MSRP. Accepts a Perfume Picks slug or a name like 'Bleu de Chanel'.

Inputs: slug_or_name (required).

get_recommendationsGet personalized recommendationsA
Read-onlyIdempotent
Inspect

Personalized fragrance picks from note/accord preferences (e.g. 'vanilla', 'oud', 'citrus'), a budget in USD, an occasion ('office', 'date night', 'gift', 'signature scent'), and gender presentation.

Inputs: preferences (required), limit, budget, gender, +1 more.

search_fragrancesSearch the Perfume Picks catalogA
Read-onlyIdempotent
Inspect

Full-text search across 13,000+ fragrances in the Perfume Picks database. Filter by brand, fragrance family, gender, and MSRP (USD). Returns note pyramids, accords, and community wear scores with source attribution.

Inputs: brand, limit, query, gender, +3 more.

what_to_wear_tonightWhat should I wear tonight?A
Read-onlyIdempotent
Inspect

A fragrance suggestion for right now, based on mood, occasion (e.g. 'date', 'office tomorrow', 'night out', 'cozy evening in'), and season — scored with Perfume Picks' community compliment, office-safety, and versatility data.

Inputs: mood, gender, season, occasion.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 8 tools

    Disambiguation4/5

    Each tool targets a distinct read-only fragrance discovery step: lookup, search, dupes, similar scents, recommendations, comparison, trends, and a now-oriented suggestion. There is minor overlap between get_recommendations and what_to_wear_tonight, and between find_similar and find_dupes, but the descriptions clarify their different inputs and intents.

    Naming Consistency4/5

    Most tool names follow a readable snake_case action_noun pattern such as get_fragrance, search_fragrances, and compare_fragrances. The main deviations are trending_fragrances and what_to_wear_tonight, which are still understandable but break the consistent verb-first pattern.

    Tool Count5/5

    Eight tools is a well-balanced size for a fragrance discovery server. Each tool covers a meaningful step in the experience—exploring, understanding, comparing, recommending, and discovering—without unnecessary duplication.

    Completeness5/5

    The tool set covers the core discovery loop thoroughly: search the catalog, fetch details, compare fragrances, find alternatives, get personalized recommendations, check trends, and get a contextual suggestion. Any omitted write-oriented operations are outside the server's apparent read-only scope.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Read-only X/Twitter research MCP server allowing AI assistants to search viral content, analyze accounts, track trends, and discover niche leaders without requiring the official X API.
      50
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Public, anonymous, read-only MCP server for the Epicure ingredient-embedding model, offering tools for ingredient pairings, flavor profiling, and culinary exploration via cosine similarity and other embedding analyses.
      82
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Read-only MCP server for finding Discord messages. It enables searching guild messages, locating messages from jump URLs, and reading context around results.
      7
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server that lets AI assistants query the Noteboxd fragrance encyclopedia for fragrances, notes, accords, brands, perfumers, reviews, and charts. Enables natural-language queries like comparisons, recommendations, and review digests.
      19
      53 npm
      1
      MIT