Fragrances MCP server
online · 100% uptimeio.github.parfica/fragrances·v1.0.2Fragrance encyclopedia: note pyramids, accords, perfumers and dupes (parfica.com).
0 stars37 downloads/wk
Reviews
Write oneNobody has reviewed Fragrances yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Fragrances tools (3)
write = sends, deletes, buys or postsfind_dupesFreeFind fragrances that smell similar ("dupes") to a given one, by distinctive-note overlap. Returns matches with similarity ranking.
fragrance_infoFreeFull profile of a fragrance on parfica.com by its slug: brand, year, gender, concentration, family, note pyramid, accords, perfumers, community rating.
search_fragranceFreeSearch the parfica.com fragrance encyclopedia by name (Latin or Cyrillic), brand, note or perfumer. Returns matching fragrances, brands, notes and perfumers with links.
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- Live reliabilityremote reachable in 2266ms17/20
- Tool poisoning3 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 57 days ago12/15
- Maintainer identityregistry namespace matches repository owner7/10
How Fragrances compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 86/100
- higher than 72% of 48,255 servers
- Tools
- 3
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 153 ms
- faster than 72% of 30,031 servers
- Downloads a week
- 37
- more than 28% of 12,191 servers with a package
What its tools let an agent do: 3 read
Install Fragrances in Claude Code, Cursor or VS Code
claude mcp add --transport http fragrances https://parfica.com/mcp
What the publisher says
From the Fragrances repository's README, as published. We do not edit it. Read it on GitHub
mcp-server-parfica
MCP (Model Context Protocol) server for parfica.com — the Ukrainian-first fragrance encyclopedia. Ask your AI assistant "what does Creed Aventus smell like?" or "find me cheaper fragrances similar to Baccarat Rouge 540" and it will answer with note pyramids, accords, perfumers, community ratings and note-overlap dupes.
This package is a thin stdio bridge to the site's native MCP endpoint (https://parfica.com/mcp). Tools are discovered at startup, so the package never goes stale.
Tools
Install
Claude Code
claude mcp add parfica -- npx -y mcp-server-parficaClaude Desktop
{
"mcpServers": {
"parfica": {
"command": "npx",
"args": ["-y", "mcp-server-parfica"]
}
}
}Remote (no install)
MCP clients that support remote servers can connect straight to:
https://parfica.com/mcpConfiguration
Related
- parfica.com — the encyclopedia itself
- fragrance-dupes — the open "smells like" matching algorithm
- parfica-open-data — open fragrance data (notes, taxonomy, OBF)
License
MIT © parfica.com
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-01restoreC → Ascore 86
Fragrances: common questions
- Is Fragrances MCP server safe?
- Yes, by our scan: it is graded A (86/100). Read the Fragrances safety report
- How do I install Fragrances?
- It runs remotely at parfica.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Fragrances need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Fragrances maintained?
- The last commit was 91 days ago (2026-08-05). The latest release is v1.0.2.
- Is Fragrances up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Fragrances compare with other MCP servers?
- safety score 86/100 (higher than 72% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.