ScentVerdict MCP server
com.scentverdict/fragrancesscentverdict.comstreamable-httpv2.0.0Scanned
Fragrance catalogue with verdicts, similarity scores, scent profiles, drydowns and local prices.
6 tools: 1 change things and 5 only read.
- Reads private data · 3
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the ScentVerdict MCP server can do
The ScentVerdict MCP server is published by scentverdict.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (1 tool: recommend_fragrances), but cannot delete data. 5 tools only read.
3 tools read private data (get_scent_profile, compare_fragrances and get_fragrance).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 2.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
6 tools
Changes things 1Claude Code: ask
recommend_fragrancesRecommend fragrances matching what the user describes: season, occasion, budget, strength, staying power and notes they like.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Recommend fragrances matching what the user describes: season, occasion, budget, strength, staying power and notes they like. Use this when the user wants a suggestion but names no fragrance to work from - for example something for winter, for the office, or under a budget. Season, occasion and intensity are scored numerically per fragrance in ScentVerdict, and the budget is applied against current bottle prices for the user's country, so the constraints are filtered rather than approximated. Each priced row carries its price in the shop's own currency, and the bottle size and price per millilitre wherever the retailer published a size. Pass as many of the constraints as the user gave; all are optional. Use find_similar_fragrances instead when they name a fragrance to anchor on.
Annotations the server declares
- title: Recommend Fragrances
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
Only reads 5Show 5 read-only tools
compare_fragrancesCompare exactly two fragrances side by side using ScentVerdict's own note data: which notes they share, which differ, both verdicts, and both prices for the user's country.Reads private dataNo findings
Why it is in this group
- The name "compare_fragrances" says "compare": a word for reading.
What it can reach
- private-dataThe description's first sentence says "compare" and "note": it reads notes.
Description, as the server wrote it Compare exactly two fragrances side by side using ScentVerdict's own note data: which notes they share, which differ, both verdicts, and both prices for the user's country. Use this whenever the user is choosing between two named fragrances, or asks which of two is better, or how two differ. Use find_similar_fragrances instead when they want alternatives to one fragrance rather than a head to head.
Annotations the server declares
- title: Compare Two Fragrances
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
find_similar_fragrancesFind fragrances similar to one the user already knows, optionally steered in a direction such as cheaper, fresher, longer lasting or less sweet.No findings
Why it is in this group
- The name "find_similar_fragrances" says "find": a word for reading.
Description, as the server wrote it Find fragrances similar to one the user already knows, optionally steered in a direction such as cheaper, fresher, longer lasting or less sweet. Use this whenever the user names a fragrance and wants something like it: a cheaper alternative, a budget version, something that smells similar, or a gift for someone whose current fragrance they know ('he wears X, what else would suit him'). Each match carries a similarity score computed by ScentVerdict for that specific pair. The cheaper direction lists pairings ScentVerdict has curated first, then similar fragrances priced below the anchor where we hold its price. Each match carries its bottle price for the user's country, in the shop's own currency. Use recommend_fragrances instead when the user names no fragrance to anchor on.
Annotations the server declares
- title: Find Similar Fragrances
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_fragranceLook up one perfume or fragrance in ScentVerdict's catalogue: its notes, ScentVerdict's own verdict, concentration, launch year, and the lowest current price for a full-size bottle…Reads private dataNo findings
Why it is in this group
- The name "get_fragrance" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
Description, as the server wrote it Look up one perfume or fragrance in ScentVerdict's catalogue: its notes, ScentVerdict's own verdict, concentration, launch year, and the lowest current price for a full-size bottle for the user's country, in the shop's own currency. Use this whenever the user names a fragrance and asks what it is, what it smells like, what is in it, what it costs, or whether it is any good. Use search_fragrances first if the name is partial or could mean several variants. Use get_scent_profile instead when the question is about how it develops over the wear.
Annotations the server declares
- title: Look Up a Fragrance
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_scent_profileGet how a fragrance develops over the wear: opening, heart and base phases, the notes in each, and how many hours each note persists on skin.Reads private dataNo findings
Why it is in this group
- The name "get_scent_profile" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "note": it reads notes.
Description, as the server wrote it Get how a fragrance develops over the wear: opening, heart and base phases, the notes in each, and how many hours each note persists on skin. Use this when the user asks how something evolves, how long it lasts, how it changes through the day, or what the drydown is like. The per-note hours are values held by ScentVerdict against each note rather than a general impression of the fragrance, and they are estimates. Use get_fragrance instead for the verdict, price and general description.
Annotations the server declares
- title: Scent Profile and Drydown
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_fragrancesResolve a perfume or fragrance name to catalogue entries.No findings
Why it is in this group
- The name "search_fragrances" says "search": a word for reading.
Description, as the server wrote it Resolve a perfume or fragrance name to catalogue entries. Call this FIRST whenever a name is partial, misspelled, or could mean more than one product, then pass the returned slug to another tool. Many fragrances share a name across concentrations and launch years, and flankers hide behind qualifiers, so guessing the variant silently produces the wrong answer for the rest of the conversation. Results carry concentration and launch year precisely so you can tell them apart, and you should offer the user the choice when several match. Use get_fragrance instead when you already hold an exact slug.
Annotations the server declares
- title: Search Fragrances by Name
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:46 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://scentverdict.com/mcp: tools/list returned 6 tools to an anonymous client, including recommend_fragrances (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:get_fragranceOnly readsdescription
- Changed:search_fragrancesOnly readsdescription
Install
Pinned to version 2.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http fragrances https://scentverdict.com/mcpclaude mcp add --transport http fragrances https://scentverdict.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__fragrances__get_scent_profile",
"mcp__fragrances__search_fragrances",
"mcp__fragrances__find_similar_fragrances",
"mcp__fragrances__compare_fragrances",
"mcp__fragrances__get_fragrance"
],
"ask": [
"mcp__fragrances__recommend_fragrances"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as fragrances. Review it before you use it.
Capability tags behind 3 rules
- mcp__fragrances__get_scent_profile private-data
- mcp__fragrances__compare_fragrances private-data
- mcp__fragrances__get_fragrance private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.scentverdict/fragrances/verify?hash=61618b0861126a8810155d2daf20fb8e7aa6a292c446b952b102b8de2aab579c" | jq -e '.changed == false'Pinned hash 61618b086112, from Nov 14, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.scentverdict/fragrances/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.scentverdict/fragrances)Source: MCP Registry. Synced Oct 21, 2026, 18:02 UTC.
ScentVerdict MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ScentVerdict MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ScentVerdict MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ScentVerdict MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ScentVerdict MCP server have?
- 6 tools: 1 write, 5 read. recommend_fragrances, get_scent_profile, search_fragrances, find_similar_fragrances, compare_fragrances and get_fragrance.
Does the ScentVerdict MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ScentVerdict MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ScentVerdict MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 1, 2026. Every change is on this page and in its Atom feed.