Content Tools
mycarnet.app
Provides fragrance search and detail retrieval from the Carnet catalog using natural-language, image, and similarity queries.
ENDPOINT 1
https://api.mycarnet.app/mcp
MCP server metadata
- Name
- Carnet
- Version
- 1.27.0
Carnet is a personal, editorial perfume discovery engine that helps people find scents that feel like them. Use these tools when users describe taste, mood, vibe, desired impression, a known fragrance they want to understand, or a bottle image they want to use as a discovery seed. Prefer emotionally legible explanations over raw database language.
Known tools 4
search_fragrances_by_vibeSearch Carnet for fragrances matching a natural-language vibe.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.carnet]
url = "https://api.mycarnet.app/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"carnet": {
"type": "http",
"url": "https://api.mycarnet.app/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: carnet
Remote MCP URL: https://api.mycarnet.app/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"carnet": {
"url": "https://api.mycarnet.app/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"carnet": {
"type": "http",
"url": "https://api.mycarnet.app/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "carnet",
"transport": "streamable-http",
"url": "https://api.mycarnet.app/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for mycarnet.app was fetched 2026-08-03T19:53:19.538Z and is being refreshed.
mycarnet.app is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.