# scentrev-mcp

> India's first Model Context Protocol (MCP) server for structured perfume and fragrance data.

## Links

- Website: https://mcp.scentrev.com
- Documentation: https://mcp.scentrev.com/docs
- MCP endpoint: https://api.scentrev.com/mcp/
- REST API base: https://api.scentrev.com
- GitHub: https://github.com/kandimallashashank/scentrev-mcp-frontend
- Smithery: https://smithery.ai/servers/kandimallashashankreddy-7rf1/scentrev-mcp
- Main site: https://scentrev.com

## What it does

Community-powered fragrance intelligence for AI agents: longevity, sillage, projection, seasonality, gender lean, appreciation, accords, note pyramids, and similarity, normalized to 0-1 scores with confidence counts. 126,000+ fragrances.

## MCP tools (14)

- search_fragrances: Text search by name, brand, or slug.
- search_fragrances_filtered: Search by notes, accords, season, wear metrics, discovery sort.
- search_by_references: Multi-reference note pyramid blending (Layering Lab style).
- list_brands: Catalog brands with optional name/slug filter.
- resolve_slug: Fuzzy slug, name, or brand resolution.
- compare_fragrances: Compare rating, wear, and price_value for 2+ scents.
- get_fragrance_profile: Longevity, sillage, seasonality, sentiment, accords, and more.
- get_wear_summary: Season and occasion wear breakdown.
- get_identity: Brand, release year, gender, and basics.
- get_performance: Longevity, sillage, and projection scores.
- get_appreciation: Community sentiment and rating ratios.
- get_reminds_of: Similar fragrances from community votes.
- get_note_pyramid: Top, heart, and base note layers.
- get_accords: Dominant accords with strength percentages.

## Clients

Works with Cursor, Claude Desktop, Cline, Windsurf, LangChain, and any HTTP client via REST.

## Auth

Bearer API key from the dashboard (`frag_live_` prefix). Same key for MCP and REST.