Search perfumes, fragrance notes, accords, and side-by-side scent comparisons on getscentai.com.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Compare two perfumes side-by-side by their brand/perfume slugs to analyze shared accords, overlapping notes, and key differences.
Brand slug of first perfume.
Brand slug of second perfume.
Perfume slug of first perfume.
Perfume slug of second perfume.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http fragrance-finder https://getscentai.com/api/mcp
Compare two perfumes side-by-side by their brand/perfume slugs to analyze shared accords, overlapping notes, and key differences.
| Argument | Type | Description |
|---|---|---|
| brandSlugA* | string | Brand slug of first perfume. |
| brandSlugB* | string | Brand slug of second perfume. |
| perfumeSlugA* | string | Perfume slug of first perfume. |
| perfumeSlugB* | string | Perfume slug of second perfume. |
{
"type": "object",
"required": [
"brandSlugA",
"perfumeSlugA",
"brandSlugB",
"perfumeSlugB"
],
"properties": {
"brandSlugA": {
"type": "string",
"description": "Brand slug of first perfume."
},
"brandSlugB": {
"type": "string",
"description": "Brand slug of second perfume."
},
"perfumeSlugA": {
"type": "string",
"description": "Perfume slug of first perfume."
},
"perfumeSlugB": {
"type": "string",
"description": "Perfume slug of second perfume."
}
}
}Retrieve detailed fragrance profile (notes, accords, concentration, release year) by brandSlug and perfumeSlug.
| Argument | Type | Description |
|---|---|---|
| brandSlug* | string | Brand slug from search_perfumes (e.g., 'dior'). |
| perfumeSlug* | string | Perfume slug from search_perfumes (e.g., 'sauvage'). |
{
"type": "object",
"required": [
"brandSlug",
"perfumeSlug"
],
"properties": {
"brandSlug": {
"type": "string",
"description": "Brand slug from search_perfumes (e.g., 'dior')."
},
"perfumeSlug": {
"type": "string",
"description": "Perfume slug from search_perfumes (e.g., 'sauvage')."
}
}
}Search perfumes, fragrance brands, scent notes, and accords in the ScentAI database on getscentai.com.
| Argument | Type | Description |
|---|---|---|
| query* | string | Search query (min 2 chars), e.g. 'Sauvage', 'Baccarat Rouge', 'vanilla', 'oud'. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Search query (min 2 chars), e.g. 'Sauvage', 'Baccarat Rouge', 'vanilla', 'oud'."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 21, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.