find_similar_perfumes
Find perfumes that smell like one the person already likes, ranked by shared notes, accords and style, each saying exactly what it shares and how close it is (very close, similar vibe, same spirit). Works from a perfume in the index (name and house, or id) OR from free notes/accords for any other...
This record as markdown: /tools/10ml-perfume-finder-mcp/find-similar-perfumes.md
What find_similar_perfumes does on Perfume Finder
AI agents call find_similar_perfumes to retrieve information from Perfume Finder without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
house | string | — | House of the perfume when the name alone is ambiguous, e.g. "Maison Francis Kurkdjian" |
limit | integer | — | How many results per page (1-15, default 8). |
notes | array | — | Known notes of the starting perfume, for perfumes outside the index. Example: ["jasmine","saffron","ambergris","cedar"] |
steer | string | — | Move away from the starting point in one direction: fresher, sweeter, darker, lighter, longer_lasting (needs a perfume in the index) or more_projection (same). |
cursor | string | — | next_cursor from the previous page; omit for the first page. |
gender | string | — | Only return perfumes for this audience (men and women include unisex) |
locale | string | — | Language of the 10ml.com links and labels. Perfume, house and note names stay as they are. |
accords | array | — | Known accords of the starting perfume. Example: ["amber","woody","sweet"] |
perfume | string | — | A perfume by name, optionally with its house, e.g. "Baccarat Rouge 540", "Dior Sauvage", "Delina". Or pass an id from another tool. |
response_format | string | — | concise (default) or detailed (adds note pyramid, seasons, occasions, longevity, projection). |
other_houses_only | boolean | — | True to leave out perfumes from the same house as the starting perfume |
Parameters from the server's own tool schema.
Why find_similar_perfumes is rated Low
Even though find_similar_perfumes only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
The rule that runs find_similar_perfumes safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Perfume Finder, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For find_similar_perfumes, this is the rule to start with:
find_similar_perfumes is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Perfume Finder, apply this rule, and every find_similar_perfumes call is checked against it from then on.
Questions about find_similar_perfumes
Find perfumes that smell like one the person already likes, ranked by shared notes, accords and style, each saying exactly what it shares and how close it is (very close, similar vibe, same spirit). Works from a perfume in the index (name and house, or id) OR from free notes/accords for any other perfume. Steer the result: fresher, sweeter, darker, lighter, longer_lasting or more_projection. Use for 'something like Baccarat Rouge 540', 'like Sauvage but fresher' or 'a perfume with notes of saffron and cedar'. Not for editorial dupes of a famous perfume from other houses (use find_perfume_alternatives) and not for free-text discovery (use search_perfumes). It is categorised as a Read tool in the Perfume Finder MCP Server, which means it retrieves data without modifying state.
find_similar_perfumes accepts 11 parameters: house, limit, notes, steer, cursor, gender, locale, accords, perfume, response_format, other_houses_only. The full parameter table on this page comes from the server's own tool schema.
Register the Perfume Finder MCP server in PolicyLayer and add a rule for find_similar_perfumes: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Perfume Finder. Nothing to install.
find_similar_perfumes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find_similar_perfumes rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for find_similar_perfumes. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
find_similar_perfumes is provided by the Perfume Finder MCP server (@10ml/perfume-finder-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Perfume Finder, and thousands of servers like it.
This server
Across the catalogue