What are reliable alternatives to 10ML Perfume Finder?

Measured by Faceabot as working: Scento Perfume API (MCP server), Perfume Picks.

How do I connect an AI agent to 10ML Perfume Finder?

Use the MCP streamable HTTP endpoint https://mcp.10ml.com/mcp.

Catalog › com.10ml/perfume-finder

Is 10ML Perfume Finder reliable?

Reliable (measured) Yes. Faceabot measured 10ML Perfume Finder 9 times: 100% of checks succeeded, including the last 9 in a row (last check 2026-10-23 13:07 UTC).

Last check: 2026-10-23 13:07 UTC · answered in 8300 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Free perfume MCP server and fragrance API: 6,000+ perfumes, note pyramids, accords, similar scents.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 2.5.3 · publisher website

Connect your agent

{
  "mcpServers": {
    "perfume-finder": {
      "url": "https://mcp.10ml.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.10ml/perfume-finder"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Real task being tested — Faceabot asked search_perfumes to do a small read-only task 2 time(s): 2 returned a real result, the last 2 in a row. Last result: ok in 6504 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Other proven tools for the same job

Scento Perfume API (MCP server) Reliable (measured) · 100%
Free perfume & fragrance API and MCP server: notes, families, similar scents, 1,400+ perfumes. · https://www.scento.com/mcp

Perfume Picks Flaky · 86%
Search the Perfume Picks fragrance database: 10,000+ scents with notes, dupes, and wear data. · https://mcp.perfumepicks.app/?src=registry

Picked from Faceabot's live measurements. Or let Faceabot choose: GET https://faceabot.com/resolve?need=…

Faceabot measurements

When	Answers	Real task	Latency
2026-10-23 13:07 UTC	✅ ok	✅ done	8300 ms
2026-10-23 02:47 UTC	✅ ok	✅ done	3235 ms
2026-10-22 15:45 UTC	✅ ok	❌ tool_error	7147 ms
2026-10-22 04:30 UTC	✅ ok	❌ tool_error	4834 ms
2026-10-21 17:26 UTC	✅ ok	❌ tool_error	8000 ms
2026-10-21 06:20 UTC	✅ ok	❌ tool_error	3757 ms
2026-10-20 18:55 UTC	✅ ok	❌ tool_error	9359 ms
2026-10-20 07:20 UTC	✅ ok	❌ tool_error	8706 ms
2026-10-19 19:30 UTC	✅ ok	❌ tool_error	8314 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Publisher of 10ML Perfume Finder?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.10ml/perfume-finder.svg)](https://faceabot.com/tools/com.10ml/perfume-finder)

Data in JSON: /api/catalog?id=com.10ml/perfume-finder · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms