Skip to main content
Glama

FoodChecker

An open-source food label checker for ChatGPT and Claude. Ask "is this healthy?" with a barcode, a product name or a photo of the label. You get a 0-100 score with the reasons, the way Yuka or Oasis would show it, but inside your chat and with a scoring method anyone can read.

Score card for Coca-Cola: 15/100, Bad

Score

Rating

75-100

Excellent

50-74

Good

25-49

Poor

0-24

Bad

  • Nutrition: based on Nutri-Score 2023.

  • Additives: each one has a risk level and a cited reason.

  • Processing: based on NOVA, with a note on why a food counts as ultra-processed.

  • Alternatives: suggests healthier products in the same category.

  • Data: over 3 million products from Open Food Facts. Labels you photograph are scored too, even products that aren't in the database.

How the score is built: docs/METHODOLOGY.md.

How it works

One MCP server serves both assistants. ChatGPT and Claude both implement the open MCP Apps standard, so the same score card renders inline in each of them:

ChatGPT / Claude  ──MCP──▶  FoodChecker server  ──▶  Open Food Facts API
       ▲                         │
       └──── score card (MCP Apps UI) + text summary

Tool

What it does

check_food

Look up a product by barcode or name, and score it

analyze_label

Score a product from its label (photo or pasted text), including US per-serving labels

find_healthier_alternatives

Find similar products that score clearly higher

explain_additive

Explain an additive by E-number or name ("E471", "Red 40") with its risk level and sources

All tools are read-only and need no login.

Related MCP server: Open Food Facts MCP Server

Use the hosted server

A public instance runs at https://foodchecker-ebon.vercel.app/mcp. Paste that URL into ChatGPT or Claude as shown below. You can try the score card in a browser at https://foodchecker-ebon.vercel.app.

Run it locally

npm install
npm run dev

Add it to ChatGPT

Use the hosted URL or your own deployment. ChatGPT can't reach localhost.

  1. Go to chatgpt.com/plugins, click +, then Add custom MCP server.

  2. Server URL: https://foodchecker-ebon.vercel.app/mcp. Authentication: No authentication.

  3. Create it, then ask: "Is Nutella healthy?"

To list it in the ChatGPT app directory, follow OpenAI's submission flow at platform.openai.com/plugins. FoodChecker already supports two of its requirements through environment variables:

  • OPENAI_APPS_CHALLENGE: the domain-verification token, served at /.well-known/openai-apps-challenge.

  • CHATGPT_WIDGET_DOMAIN: your widget origin.

You'll also need a privacy policy URL, a terms URL, test prompts and a demo video.

Add it to Claude

  • claude.ai or Claude Desktop: go to Customize → Connectors → Add custom connector, paste https://foodchecker-ebon.vercel.app/mcp, and choose No sign-in. The score card renders on web, desktop and mobile.

  • Claude Code, remote server: run claude mcp add --transport http foodchecker https://foodchecker-ebon.vercel.app/mcp.

  • Claude Code, local server: run claude mcp add foodchecker -- npx tsx /path/to/repo/src/stdio.ts.

  • Claude Code plugin with a usage skill: this repo is a plugin marketplace. It points at the hosted server. If you self-host, change the URL in plugins/foodchecker/.mcp.json. Then run:

    /plugin marketplace add kjagsadvisors/foodchecker
    /plugin install foodchecker@foodchecker

Claude Code shows text, not the score card. The text summary carries the same information.

Deploy

The server is a standard web Request → Response handler (src/app.ts), so it runs almost anywhere.

  • Docker (Render, Fly.io, Railway, any VPS): docker build -t foodchecker . && docker run -p 3000:3000 foodchecker

  • Vercel: vercel deploy. vercel.json builds the project and routes everything to api/index.js.

  • Plain Node: npm run build && npm start

Set OFF_USER_AGENT to FoodChecker/0.1.0 (your contact email). Open Food Facts asks every app to identify itself. See .env.example for the other settings.

Rate limits: Open Food Facts allows roughly 15 product lookups and 10 searches per minute per IP. FoodChecker caches results in memory (products for 12 hours, searches for 1 hour). For heavy traffic, load the Open Food Facts data dump into your own database.

Project layout

src/core/        scoring engine: Nutri-Score 2023, additive table, ingredient parser, 0-100 score
src/off/         Open Food Facts client and data normalisation
src/mcp/         MCP server, tool definitions, score-card widget, text summaries
src/app.ts       web handler: /mcp, /preview, landing page
src/http.ts      Node server       src/stdio.ts   local stdio server
plugins/         Claude Code plugin (MCP config + food-check skill)
test/            scoring tests     scripts/       smoke test, dev MCP Apps host

Contributing

The most useful contributions are:

  • Additive table (src/core/additives.ts): challenge a risk level with a source, or add a missing additive and its label names in your language.

  • Ingredient parsing (src/core/ingredients.ts): label wording that gets missed. Add a test case in test/scoring.test.ts.

  • Product data: fix the product on Open Food Facts and everyone benefits.

npm run dev:host builds a small MCP Apps host on the official AppBridge. Then open /dev/host?barcode=… to check the widget the way ChatGPT and Claude embed it.

License and data

  • Code: MIT.

  • Product data: © Open Food Facts contributors, under the Open Database License. Product images are under CC BY-SA. Keep the attribution that the score card and text summaries show.

FoodChecker gives general information about packaged food. It is not medical advice.

Available Tools

4 tools
analyze_labelScore a food from its labelA
Read-onlyIdempotent
Inspect

Scores a food from its label: the ingredient list and/or the nutrition facts, for example from a photo of the packaging or pasted text, including products that aren't in the database. Most accurate with the ingredient list exactly as printed, including E-numbers and words in brackets. Nutrition values can be per 100 g or per serving (with the serving size). Returns the same 0-100 score and reports any missing data.

Inputs: brand, category, is_drink, nutrition, +3 more.

check_foodCheck a food productA
Read-onlyIdempotent
Inspect

Looks up a packaged food or drink in Open Food Facts (3M+ products) by barcode or by name and returns a 0-100 health score (Excellent / Good / Poor / Bad) with the reasons: nutrition (Nutri-Score), additives and their risk level, and how processed it is. For questions such as whether a product is healthy. A barcode gives the most precise match.

Inputs: query, barcode, country.

explain_additiveExplain a food additiveA
Read-onlyIdempotent
Inspect

Explains what a food additive is, what it does, and its risk level with sources, by E-number (E250) or name (sodium nitrite, Red 40, carrageenan).

Inputs: additive (required).

find_healthier_alternativesFind healthier alternativesB
Read-onlyIdempotent
Inspect

Finds similar products in the same Open Food Facts category that score clearly higher than the given product, best first, each with its score.

Inputs: barcode (required), limit, country.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 4 tools

    Disambiguation4/5

    The tools are mostly distinct: check_food is for database lookups, analyze_label is for label text or photos, find_healthier_alternatives is comparative, and explain_additive is educational. However, check_food and analyze_label both return the same health score and could be confused when an agent has both a product name and label information.

    Naming Consistency5/5

    All tool names use snake_case and begin with a clear verb: check_food, analyze_label, find_healthier_alternatives, explain_additive. The pattern is predictable and readable throughout.

    Tool Count5/5

    Four tools is a well-scoped set for a food health checker. Each tool covers a distinct workflow: database lookup, label analysis, alternatives, and additive explanation.

    Completeness4/5

    The surface covers the core health-checking workflows for known products, unknown products via labels, healthier alternatives, and additive explanations. Minor gaps remain, such as retrieving full ingredient or nutrition details beyond the score and reasons.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to access the Open Food Facts database to query detailed food product information, nutritional data, and environmental scores. Supports product lookup by barcode, smart search with filtering, nutritional analysis, product comparison, and dietary recommendations to help users make informed food choices.
      5
      1
      MIT