recommend_perfumes
Personal perfume recommendations from taste: perfumes they love or dislike, notes they like or avoid, plus gender, season, occasion, style and family. Every pick says why (shared notes with a loved perfume, a liked note, fits the season). Use when someone says what they enjoy or avoid and wants s...
This record as markdown: /tools/10ml-perfume-finder-mcp/recommend-perfumes.md
What recommend_perfumes does on Perfume Finder
AI agents call recommend_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 |
|---|---|---|---|
likes | array | — | Perfumes they love, e.g. ["Parfums de Marly Delina","Dior Sauvage"] |
limit | integer | — | How many results per page (1-15, default 6). |
style | array | — | Styles wanted, e.g. ["fresh","clean"] |
cursor | string | — | next_cursor from the previous page; omit for the first page. |
family | string | — | A fragrance family or word like "woody" or "citrus" |
gender | string | — | Audience the perfume is marketed to. men and women also include unisex perfumes. |
locale | string | — | Language of the 10ml.com links and labels. Perfume, house and note names stay as they are. |
season | string | — | Season the perfume suits (fall is accepted in text queries as autumn). |
dislikes | array | — | Perfumes they dislike; similar ones are pushed down |
occasion | string | — | Occasion the perfume suits: daytime, office, casual, evening, date night or special occasion. |
liked_notes | array | — | Notes they enjoy, e.g. ["vanilla","rose"] |
avoided_notes | array | — | Notes to exclude entirely, e.g. ["patchouli","oud"] |
Parameters from the server's own tool schema.
Why recommend_perfumes is rated Low
Even though recommend_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 (13 properties)
Attacks that exploit this kind of access
The rule that runs recommend_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 recommend_perfumes, this is the rule to start with:
recommend_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 recommend_perfumes call is checked against it from then on.
Questions about recommend_perfumes
Personal perfume recommendations from taste: perfumes they love or dislike, notes they like or avoid, plus gender, season, occasion, style and family. Every pick says why (shared notes with a loved perfume, a liked note, fits the season). Use when someone says what they enjoy or avoid and wants suggestions ('I love Delina and vanilla, nothing too sweet, for winter evenings'). Not for one-off filters without taste (use search_perfumes), not for a single occasion list (use pick_for_occasion) and not for gifts (use find_gift). It is categorised as a Read tool in the Perfume Finder MCP Server, which means it retrieves data without modifying state.
recommend_perfumes accepts 12 parameters: likes, limit, style, cursor, family, gender, locale, season, dislikes, occasion, liked_notes, avoided_notes. 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 recommend_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.
recommend_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 recommend_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 recommend_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.
recommend_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