A free perfume MCP server and fragrance API that gives Claude, ChatGPT and other AI assistants access to data on 6,000+ perfumes, including notes, accords and similar scents.
About
10ML Perfume Finder is a free Model Context Protocol (MCP) server and fragrance API that lets AI assistants such as Claude and ChatGPT answer perfume questions with structured, editor-curated data instead of guesswork. General-purpose chatbots often give vague or inconsistent fragrance advice because they lack a reliable source of note pyramids, accords and house information; this server supplies that knowledge base directly.
The service is built and maintained by 10ML, publisher of the 10ML Fragrance Index, which covers 6,019 perfumes from 249 houses along with 285 explained notes and 164 guides in ten languages. Connecting takes a single URL over Streamable HTTP with no API key, no sign-up and no authentication. A REST mirror with an OpenAPI 3.1 description is available for applications that do not use MCP, and the server can also run locally as a stdio server through npm or PyPI packages.
Key Features
Pricing & Fees
- Pricing: The MCP server and fragrance API are free, with no API key and no sign-up required.
- Platform availability: Works with Claude, ChatGPT, Cursor, VS Code, Windsurf, Cline and the command line; it is listed in the official MCP Registry and Claude's connectors directory, and on npm and PyPI.
- Benchmark results: In 10ML's own 40-question test, the server answered 39 of 40 questions correctly with one call each, at a median response time of 232 ms.
- Editorial depth: 481 perfumes have full editorial profiles covering longevity, projection and perfumers, on top of the standard note pyramids for every entry.
Who It's For
10ML Perfume Finder is aimed at people who use AI assistants and want trustworthy, specific fragrance answers, whether that is finding a summer office scent, comparing two popular perfumes or picking a gift. It also serves developers building chatbots, shopping assistants or fragrance apps who need structured perfume data through a free API or MCP connection. Fragrance enthusiasts who read review guides will find the linked multilingual articles and note explanations useful for deeper research.
FAQ
What is 10ML Perfume Finder?It is a free perfume MCP server and fragrance API, powered by the 10ML Fragrance Index, that gives AI assistants access to data on 6,019 perfumes, including notes, accords, families and similar scents.
Is 10ML Perfume Finder free to use?Yes, the server and API are free, with no API key and no sign-up; the single MCP URL is https://mcp.10ml.com/mcp.
Which platforms and clients does it support?It works with Claude, ChatGPT, Cursor, VS Code, Windsurf and Cline, and can run as a local stdio server via npm (`@10ml/perfume-finder-mcp`) or PyPI (`perfume-finder-mcp`).
Can it be used without MCP?Yes, the same data is available through plain HTTP GET requests against a REST API documented with an OpenAPI 3.1 description.
How accurate is it?In 10ML's own 40-question benchmark, it answered 39 of 40 questions correctly, always in a single call, at a median of 232 ms per question; these results are the vendor's, not independently verified.
Related Tutorials
View all →
Related Tools
View all →
OmniRoute - Free AI Gateway for Multi-Provider LLMs Free, open-source AI router with auto-fallback. 236 providers, one endpoint, 95 MCP tools, 17 routing strategies, A2A protocol, auto-combo engine, semantic cache, memory & skills. Deploy anywhere. 
OpenHands Open-source, model-agnostic platform for building and deploying cloud coding agents. Automate real engineering work securely with full transparency and control. 
Agent-Native Apps Framework Build agentic apps where AI agents and UI share the same database and state. Open source framework with ready-to-fork templates. 
DeerFlow - Agent Framework A LangChain-based framework for building super agents. Streamlines the development of advanced AI agents with ease. 
FunASR - End-to-End Speech Recognition Toolkit Industrial-grade speech recognition toolkit. 170x realtime on GPU, 50+ languages, speaker diarization, emotion detection, OpenAI-compatible API, vLLM acceleration, and agent integration.