MCP.Market

Menus Recommender MCP server

by spyyps·io.github.spyyps/menus-recommender·v1.0.1

全球美食加权随机推荐:基于 396 道菜的知识库,给出多样化的就餐推荐。

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

0 stars22 downloads/wk

Reviews

Write one

Nobody has reviewed Menus Recommender yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Menus Recommender tools (2)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • list_keywords

    列出推荐器支持的全部关键词与价格档。

  • recommend_dishes

    基于全球美食知识库做加权随机推荐。

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan8 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 103 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Menus Recommender compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
2
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
22
more than 8% of 12,191 servers with a package

What its tools let an agent do: 2 read

Install Menus Recommender in Claude Code, Cursor or VS Code

claude mcp add menus-recommender -- uvx menus-mcp
Add to Cursor

What the publisher says

From the Menus Recommender repository's README, as published. We do not edit it. Read it on GitHub

环球美食推荐 Plugin

一个 AI agent 插件:当用户表达就餐意向(「推荐晚餐」「不知道吃什么」「想吃点辣的」),基于 462 道菜的全球美食知识库做加权随机推荐。

  • 零依赖:纯 Python 3 标准库
  • 跨 agent:Claude Code(plugin)+ Gemini CLI(GEMINI.md)+ 任何 MCP 兼容 agent(规划中)
  • 智能兜底:本地知识库 → 自动放宽 → 网络搜索 → LLM 常识,4 层兜底
  • 去偏置 + 多样性:避免大菜系(如中餐)压制小菜系;避免推荐 3 道全是同一菜系

快速测试

python3 scripts/recommender.py --count 3 --keywords "辣,牛肉"

返回 JSON:

{"dishes": [{"id": "...", "name": "麻婆豆腐", "price": 38, "cuisine": "川菜", ...}, ...], "exhausted": false, ...}

完整参数:

python3 scripts/recommender.py --help

安装到不同 AI Agent

Claude Code

方式 A:自建 marketplace(推荐)

/plugin marketplace add spyyps/recommend-dish
/plugin install menus-recommender@spyyps-recommend-dish

安装后在任意目录的 Claude Code 会话里说「推荐晚餐」「想吃点辣的」即可触发。 后续更新插件:/plugin update menus-recommender。

方式 B:本地 git clone

git clone https://github.com/spyyps/recommend-dish ~/.claude/plugins/menus-recommender

Gemini CLI

git clone https://github.com/spyyps/recommend-dish
cd recommend-dish
gemini   # 在本目录运行 Gemini CLI,会自动加载 GEMINI.md

Cursor / Codex

待添加(参考 .cursor-plugin/ 与 .codex-plugin/ 的多 manifest 适配,第二阶段交付)。

MCP 兼容的任意 Agent

适用于 Claude Desktop / Cline / Cursor / Continue 等任何 MCP 客户端。

uvx 方式(推荐,无需 pip install):

{
  "mcpServers": {
    "menus": {
      "command": "uvx",
      "args": ["menus-mcp"]
    }
  }
}

或者 pip install:

pip install menus-mcp
{
  "mcpServers": {
    "menus": { "command": "menus-mcp" }
  }
}

详见 mcp-server/README.md。

触发示例

算法核心

  1. 关键词硬过滤:用户传了关键词时,菜品必须至少命中一个(OR 语义)
  2. 多重命中加权:命中 N 个关键词的菜,权重 ×2^(N-1)
  3. 菜系反偏置:权重 ×1/√(该菜系总菜数),平衡中餐占 35% 的天然偏差
  4. 多样性贪心:同一菜系上限 ≤ ceil(count/3)
  5. 价格档松弛:候选不足自动去掉价格档重试一次

关键词白名单

只接受以下关键词,超出范围的(如「不辣」「清淡」)由 LLM 在调用前消化掉:

  • 口味:麻辣 / 辣 / 甜 / 酸 / 咸 / 鲜
  • 食材:海鲜 / 牛肉 / 羊肉 / 猪肉 / 鸡肉 / 素食
  • 类型:面食 / 米饭类 / 汤 / 甜品 / 烧烤 / 火锅 / 咖喱 / 汉堡披萨 / 饮品

数据来源

  • 全球菜系 462 道菜(10 个地区、41 个菜系、69 个子风味)
  • 价格范围 ¥6 ~ ¥388(CNY)
  • 完整数据见 menu.json 与 knowledge_base/ 各索引文件

发布到他人(仓库 owner 视角)

作为 Plugin 分享

  1. git push 到 GitHub(本仓库已就绪:spyyps/recommend-dish)
  2. 仓库内 .claude-plugin/marketplace.json 已配置好,列出所有可装插件
  3. 在 README 贴出一行安装命令,分享仓库链接即可

作为 MCP 分享

仓库内 mcp-server/ 目录已实现 MCP server(Python,复用同一 recommender.py),暴露 recommenddishes 与 listkeywords 两个工具。发布方式:

  • PyPI(推荐):
cd mcp-server
  pip install build twine
  python3 -m build
  twine upload dist/*

用户 uvx menus-mcp 或 pip install menus-mcp 即可。

  • 社区目录:发布完成后,提 PR 到 github.com/modelcontextprotocol/servers 把 menus-mcp 加进列表。
  • MCPB 单文件(Claude Desktop 专用):npx @anthropic-ai/mcpb pack → GitHub Release → 用户拖入 Claude Desktop 即装。

详见 mcp-server/README.md。

许可

MIT

Nothing above is checked by us. What we check is on the safety report.

Menus Recommender: common questions

Is Menus Recommender MCP server safe?
Mostly: it is graded B (82/100). Read the Menus Recommender safety report
How do I install Menus Recommender?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Menus Recommender need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Menus Recommender maintained?
The last commit was 141 days ago (2026-06-16). The latest release is v1.0.1.
How does Menus Recommender compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.