Noteboxd MCP

Noteboxd MCP

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.

Category
Visit Server

README

Noteboxd Fragrance & Perfume MCP

A Model Context Protocol server (and API) for fragrance and perfume data. Connect Claude, ChatGPT, Cursor, or any MCP client to the Noteboxd fragrance encyclopedia: fragrances, notes, accords, brands, perfumers, community reviews, and charts.

npm version license

Once connected, you can ask things like:

  • "I own Oud Wood and Aventus. What else should I try for cold-weather formal wear?"
  • "Compare Bleu de Chanel and Dior Sauvage."
  • "What are reviewers saying about Baccarat Rouge 540?"

The assistant answers from Noteboxd's data instead of guessing.

Quickstart

  1. Create an API key at developers.noteboxd.com. The free tier is 50 calls/day and needs no card.
  2. Add the server to your MCP client (see below).
  3. Ask your assistant about fragrance.
NOTEBOXD_API_KEY=nb_live_your_key npx -y @noteboxd/mcp

Install

Every client uses the same command (npx -y @noteboxd/mcp) with your key in NOTEBOXD_API_KEY.

Claude Desktop / Claude Code

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "noteboxd": {
      "command": "npx",
      "args": ["-y", "@noteboxd/mcp"],
      "env": { "NOTEBOXD_API_KEY": "nb_live_your_key" }
    }
  }
}

Cursor

Add to Cursor

Then set your real key. Or add the JSON block above to ~/.cursor/mcp.json.

VS Code

{
  "servers": {
    "noteboxd": {
      "command": "npx",
      "args": ["-y", "@noteboxd/mcp"],
      "env": { "NOTEBOXD_API_KEY": "nb_live_your_key" }
    }
  }
}

Hosted alternative

Noteboxd also runs a hosted MCP server at https://mcp.noteboxd.com/mcp (Streamable HTTP, with OAuth sign-in) if you would rather not run anything locally. This package is the local, open-source option.

Tools

All tools are read-only and return JSON. Each call is authenticated with your key and counts against your Noteboxd developer plan (the free tier covers 50 calls/day).

Search and discovery

Tool Description
search Search across fragrances, brands, notes, perfumers, collections
search_fragrances Filter fragrances by query, brand, note, family, or price range
trending Trending searches and most-worn fragrances
list_charts, get_chart Chart rankings and leaderboards

Fragrances

Tool Description
get_fragrance Full profile: notes, accords, perfumer, community score
get_fragrance_reviews Paginated community reviews
get_similar_fragrances Fragrances with a similar accord profile
get_wearing_stats Wearing counts over recent windows
compare_fragrances Two fragrances compared side by side
get_review_digest Short summary of a fragrance's reviews
batch_get_fragrances Up to 50 fragrances by id in one call
enrich_fragrance Profile plus notes, accords, reviews, and similar in one call

Brands, perfumers, notes

Tool Description
get_brand, list_brand_fragrances Brand profile and catalogue
get_perfumer Perfumer profile and top creations
list_notes, get_note Browse notes and single-note profiles
list_accords List accord families

Configuration

Variable Required Description
NOTEBOXD_API_KEY yes Your nb_live_ key from developers.noteboxd.com
NOTEBOXD_API_BASE_URL no Override the API origin (default https://api.noteboxd.com)

You can also pass the key with --api-key nb_live_....

How it works

This is a thin local server. It speaks MCP to your client over stdio and forwards each tool call to api.noteboxd.com/v1 using your key. It stores no data and holds no credentials beyond the key you provide.

AI client  --stdio-->  noteboxd-mcp  --HTTPS + your key-->  api.noteboxd.com/v1

Examples

See examples/ for runnable code: curl, TypeScript, and Python.

Pricing

The server is free and open source. API usage follows your Noteboxd developer plan: a free tier (50 calls/day), then pay-as-you-go per call. Most reads are $0.01; the AI tools cost a few cents. See developers.noteboxd.com/#pricing.

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured