Skip to main content
Glama
sakenowa-mcp

sakenowa-mcp

by mame0001

清酒風味感受器 (Sakenowa MCP)

幫你裝上數位味覺 🍶

English | 正體中文


English

Overview

A Model Context Protocol (MCP) server that transforms the Sakenowa Open Dataset into a flavor-space search engine for Japanese sake. Query by name, explore six-axis flavor profiles, discover similar bottles, and compare sake side-by-side—all powered by vector mathematics in taste space.

Key Features

  • 🍶 500+ Japanese Sake Brands — Comprehensive coverage with flavor profiles

  • 📊 6-Axis Flavor Profiles — Floral, Mellow, Rich, Calm, Light, Dry dimensions

  • 🔍 Fuzzy Search — Find sake by brand name or brewery (supports kanji & kana)

  • 🎯 Smart Similarity Matching — Discover taste-alikes or deliberate contrasts

  • 📈 Directional Flavor Exploration — Find sake that is "like this, but drier/richer/lighter"

  • 🔄 Auto-Refresh Cache — Weekly TTL with stale-serve fallback

  • 🔒 Multi-Process Safe — Atomic snapshot-based caching with cross-process isolation

Installation

git clone https://github.com/mame0001/sakenowa-mcp.git
cd sakenowa-mcp
uv sync
uv run sakenowa-mcp

5 Core Tools

Tool

Purpose

sync_sakenowa_data(force=False)

Fetch/refresh dataset; report scale & freshness

search_sake(query, limit=10, area="")

Find sake by name or brewery

get_sake_profile(brand_id)

ASCII radar, flavor tags, 4-type estimate, ranks

find_similar_sake(brand_id, mode, limit=5)

★ Find taste-alikes by flavor vector (7 directional modes)

compare_sake(brand_ids=[...])

Side-by-side comparison (2–5 sake, 6 axes)

Testing

uv run pytest -xvs
# Expected: 11/11 tests pass

Contributing

See CONTRIBUTING.md for development setup and code standards.

Architecture

See ARCHITECTURE.md for system design, data flow, and scalability.

Data Source & License

Sakenowa Data Project — https://sakenowa.com (© Sakenowa, CC-BY 4.0)

MIT License. See LICENSE.

Note: Dataset excludes rice polishing ratio, variety, SMV, ABV, price, grade, vintage. Never invent these fields.



Related MCP server: Alko MCP Server

正體中文版本

清酒風味搜尋引擎(第一個清酒 MCP)

輸入一支喝過的酒,找「像這支,但更乾爽」或「完全相反」的酒款。不用記牌子,用味覺找。

5 大功能

  • 🍶 500+ 清酒品牌 — 涵蓋完整風味檔案

  • 🔍 模糊搜尋 — 品牌名、釀造廠都能查(支援漢字、假名)

  • 🎯 風味相似度 — 找「這支的姊妹酒」或「完全相反的選擇」

  • 📈 風味探索 — 「像這支,但更乾/更濃/更輕」一句話找酒

  • 📊 並排對比 — 2~5 支酒側邊欄比較,一眼看出差異

快速開始

git clone https://github.com/mame0001/sakenowa-mcp.git
cd sakenowa-mcp
uv sync
uv run sakenowa-mcp

5 個工具

工具

用途

sync_sakenowa_data()

更新清酒資料庫

search_sake()

查品牌名、釀造廠

get_sake_profile()

看風味輪廓、排名

find_similar_sake()

★ 根據風味找相似酒

compare_sake()

並排對比多支酒

驗證安裝

uv run pytest -xvs
# 預期:11/11 測試通過

開發 & 架構

開源授權

MIT License(資料源於 Sakenowa 開放資料集,CC-BY 4.0)

Available Tools

5 tools
compare_sakeA

Compare 2–5 sake side by side across all six flavor axes, with the spread (max−min) per axis to highlight where they differ most.

Inputs: brand_ids (required). Returns: result

find_similar_sakeA

★ Core feature ★ Given one sake, find others by flavor-vector proximity.

`mode` steers the direction in flavor space:
  - similar       : nearest overall (a true taste-alike)
  - drier         : like this, but drier
  - sweeter       : like this, but less dry / rounder
  - lighter       : like this, but lighter & crisper
  - richer        : like this, but fuller & heavier
  - more_aromatic : like this, but more floral/fragrant
  - calmer        : like this, but quieter on the nose
  - contrast      : the opposite palate (for deliberate exploration)

Only sake that have a flavor chart can be matched.

Inputs: brand_id (required), mode, limit. Returns: result

get_sake_profileA

Return the six-axis flavor profile of one sake: an ASCII radar, the dominant flavor tags, an estimated four-type class (薫/爽/醇/熟, heuristic), and its overall/area popularity rank.

Also lists the bottle-spec fields the Sakenowa dataset does NOT provide
(polishing ratio, SMV, ABV, price, …) so they are never invented.

Inputs: brand_id (required). Returns: result

search_sakeA

Find sake by brand name or brewery name and return their IDs.

Names are Japanese; kanji queries (e.g. 八海山, 獺祭) match directly, and
so do Chinese kanji that share the glyphs. Use `area` to filter by
prefecture name (e.g. '新潟'). Use the returned `id` with
get_sake_profile / find_similar_sake / compare_sake.

Inputs: query (required), limit, area. Returns: result

sync_sakenowa_dataA

Fetch/refresh the Sakenowa open dataset into a local cache and report its scale. The cache auto-refreshes weekly, so you rarely need this — call it with force=True only to pull the latest monthly snapshot immediately.

Returns dataset counts, the data's year-month, and the required attribution.

Inputs: force. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: searching, profiling, comparing, finding similar, and data sync. No overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern (e.g., search_sake, get_sake_profile), making them predictable.

    Tool Count5/5

    Five tools is well-scoped for a domain-specific sake exploration server. It covers core functionality without being overwhelming or too sparse.

    Completeness4/5

    The tool set covers the main workflow: search, get profile, compare, and find similar. Minor gaps like lack of filtering by flavor attributes or listing all sake, but overall adequate.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Provides LLMs with specialized knowledge about fountain pen inks, enabling intelligent ink search, color matching, and recommendations through various tools.
      6
      GPL 3.0
    • A
      license
      A
      quality
      D
      maintenance
      Provides AI assistants with access to Finland's Alko alcohol product catalog, enabling product search across 11,900+ items, store availability checks, Vivino ratings lookup, and personalized recommendations based on food pairings and preferences.
      9
      17
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables querying the Pour Picks bourbon & whiskey database with tools for search, bottle details, recommendations, comparisons, and trending, providing structured tasting profiles, prices, pairings, and ratings.
      8
      55 npm
      MIT