TWFoodMCP
Provides access to Taiwan packaged food and chain restaurant nutritional information, including search, nutrition calculation, and draft creation for new data.
README
TWFoodMCP
台灣食品營養、成分與過敏原的開放知識 MCP。
TWFoodMCP 將台灣包裝食品、官方連鎖餐飲品項與一般食品資料整理成可版本化、可追溯、可供 AI Agent 使用的 OKF 文件,並預計透過 Cloudflare Remote MCP 對外提供查詢、營養計算與投稿能力。
Why
一般 AI 雖能搜尋食品資訊,但常遇到產品版本混淆、每份與每 100 g 基準不一致、估算值來源不明、過敏原資訊過期,以及缺值被誤當成 0 等問題。
TWFoodMCP 的目標是讓每一筆資料都能回答:
- 這是哪一個精確產品與版本?
- 數值的 serving basis 是什麼?
- 資料來自包裝、品牌、政府、第三方還是估算?
- 何時被驗證,現在是否可能過期?
- 哪些欄位未知,不能進一步推論?
Architecture
Human / Agent
│
├── query ───────────────────────────────┐
│ │
└── create_draft │
│ │
▼ │
Draft OKF │
│ │
validation → comparison → review → commit │
│ │
▼ │
GitHub main │
│ │
▼ │
GitHub Actions build/index/sync │
│ │
▼ │
Cloudflare KV / R2 │
│ │
▼ │
Cloudflare Remote MCP ◄────────────────────┘
MVP Principles
- GitHub OKF 是 source of truth。
- Cloudflare KV / R2 是 runtime storage,不是正式資料來源。
- MCP runtime 不直接抓 GitHub。
- MVP 使用 deterministic keyword search,不使用 embedding。
- Runtime 與 pipeline 不依賴付費 LLM API。
- 公開寫入只提供
create_draft。 - Draft 建立後固定進入 validation、comparison、review、commit pipeline。
- Draft 不進正式搜尋,也不參與營養計算。
- 只有真人 reviewer 能標記 human-reviewed。
- MCP 是基礎設施;一般使用者仍會有 Web UI。
Planned MCP Tools
Read
search_foodget_foodcalculate_nutritioncompare_foodsget_dataset_status
Write
create_draft
下游驗證、比對、審核與發布步驟屬於固定內部 workflow,不各自暴露為公共 MCP tool。
Specification
完整產品與技術規格:
Current Status
目前處於 specification / repository foundation 階段。下一步將依序建立:
- Food OKF schema 與範例資料。
- Validator 與 deterministic index builder。
- Read-only Remote MCP。
- Cloudflare KV versioned deployment。
create_draft與 GitHub PR review pipeline。- Public Web UI。
Safety Boundary
本專案提供食品標示與公開資料整理,不構成醫療、營養治療或疾病管理建議。產品配方與標示可能變動;過敏或特殊飲食需求請以最新實體包裝、品牌資訊與專業人員意見為準。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.