<h1 align="center">Wellness Nourish</h1>

<h3 align="center"> Local-first nutrition MCP — food search, barcode lookup, intake logging, hydration. Works without OAuth.<br> Local-first MCP server — <strong>tokens never leave your machine</strong>. </h3>

<p align="center"> <strong>📈 Published on npm and used by AI agents and MCP clients</strong> — see the live <a href="https://www.npmjs.com/package/wellness-nourish">download badge</a> above for current numbers.<br> <sub>If Nourish helps your agent, a ⭐ on this repo makes it easier for other AI builders to find.</sub> </p>

⚡ One-command install — pick your runtime: - Delx Wellness for Hermes: npx -y delx-wellness-hermes setup - Delx Wellness for OpenClaw: npx -y delx-wellness-openclaw setup Both preconfigure this connector and the full Delx Wellness stack into a dedicated profile. Or wire it standalone into Claude Desktop / Cursor / ChatGPT Desktop — see the install section below. Want runnable agent examples? Use the Delx Agent Workbench for prompt packs, MCP client configs and local-first workflow templates.

What's new in 0.7.1: Offline fixture demo works from the published npm package (fixtures shipped + path resolved from package root). 0.7.0: Brazilian TACO 4 meal estimator for pt-BR foods (cafezinho, feijão, concha, churrasco-style meals) plus Smithery install. Offline demo: NOURISH_FIXTURE_MODE=1 npx -y wellness-nourish search banana. Notes: CHANGELOG.md · eval: docs/evals/pt-br-meal-estimator.json (52 cases).

Public proof: Nourish is tracked in the Delx Open Source Growth Snapshot alongside downloads, stars and next-action priorities. If this saves you setup time, star this repo so other agent builders can find the local-first nutrition path faster.

---

Local-first nutrition MCP for AI agents — food search, barcode lookup, photo-assisted meal estimation, intake logging, hydration, goals and coach-style workflows. No OAuth, no hosted account.

Front door

Install one connector — npx -y wellness-nourish setup --client claude
Run it in Claude · Cursor · ChatGPT · Hermes · OpenClaw — see the client examples.
Local-first — your tokens and food logs never leave your machine (privacy).
Which connector should I use? — see the front-door guide.

Quickstart (60 seconds)

npx -y wellness-nourish doctor
npx -y wellness-nourish search banana
npx -y wellness-nourish barcode 0000000000000
npx -y wellness-nourish log --preview "2 ovos, banana e café preto"

doctor checks readiness, search/barcode hit the food providers, and log --preview estimates a meal locally without writing anything.

Zero-secret demo (offline, no API key)

NOURISH_FIXTURE_MODE=1 serves the bundled fixtures/ instead of calling USDA or Open Food Facts, so you can see the exact shape of every response with zero network access or keys:

$ NOURISH_FIXTURE_MODE=1 wellness-nourish search banana
Bananas, raw	usda	89 kcal/100g
BANANA	usda	312 kcal/100g

Try it with your agent

Three copy-paste prompts, all backed by existing tools:

"Estimate the calories and protein in 2 eggs, a banana and black coffee." → nourish_estimate_meal
"Look up the barcode 737628064502 and tell me what it is." → nourish_lookup_barcode
"What should I eat next today, given my goals?" → nourish_daily_coach / nourish_suggest_next_meal

Mutating tools (log intake, water, goals, clear-day) never run without explicit user save intent — they return USER_ACTION_REQUIRED until the agent passes explicit_user_intent: true.

Tools

Nourish exposes food search, barcode lookup (text + image), photo-assisted meal estimation, intake logging, hydration, goals, exports, daily/weekly summaries, personal meal memory, and coach-style workflows over stdio (default) or Streamable HTTP (POST /mcp).

Full CLI (20+ commands), install, client configs & ChatGPT dashboard → docs/cli.md
Hermes / Telegram personal setup (10-step flow) → docs/telegram.md
Data providers & attribution (USDA, Open Food Facts, ZXing) → docs/providers.md
pt-BR meal-estimator eval set (52 examples) → docs/evals/pt-br-meal-estimator.json
Reproducible Telegram/Hermes demo transcript → docs/telegram-demo-transcript.json

Food photo decision tree

Agents should route Telegram/Hermes/OpenClaw food photos by the strongest signal they can extract:

Barcode is visible and image bytes are available: call nourish_lookup_barcode_image.
Barcode is blurry or no product is found: ask for sharper barcode digits, or call nourish_analyze_food_image with barcode_observation plus any OCR/meal clues.
Nutrition facts are readable: OCR the label and call nourish_analyze_food_image with product_name and nutrition_label_text.
It is a plate or unpackaged food: describe visible foods/portions and call nourish_analyze_food_image with detected_items or image_description.
Never log from an image response until the user confirms the product or meal, serving size and save intent.

Image tools accept exactly one of these input forms:

{ "image_path": "/tmp/telegram-food-photo.jpg" }

{ "image_base64": "<base64 image bytes>", "image_mime_type": "image/jpeg" }

{ "image_data_uri": "data:image/jpeg;base64,<base64 image bytes>" }

If barcode decoding fails, the response includes fallback and next_actions so the agent can ask the user for the typed digits, OCR the nutrition label, or route the photo as a meal without silently inventing a food.

The capture above is generated from a real MCP run in fixture mode with a temporary local directory:

npm run demo:capture

The committed transcript proves the exact tool sequence: nourish_estimate_meal → user confirmation → nourish_log_intake → nourish_daily_summary.

Privacy & what runs offline

Intake, hydration and goals are stored locally under ~/.wellness-nourish/ (override with NOURISH_LOCAL_DIR). The connector does not require hosted accounts and does not send local intake logs to Delx Wellness. Provider lookups may contact USDA FoodData Central or Open Food Facts — unless NOURISH_FIXTURE_MODE=1 keeps everything offline against the bundled fixtures.

Agents should never ask users to paste API keys, tokens, raw health exports, or private food logs into chat — configure secrets through environment variables or local files. Full detail in docs/providers.md.

See the full agent demo →

Watch Nourish work alongside the other connectors in one reproducible run:

npx -y delx-living-body demo

Anchor question: "Should I train hard today?" — the demo combines wearable recovery signals with nutrition context to answer it. This is the shared, reproducible proof for the whole Delx Wellness stack.

Not medical advice

Nutrition estimates are approximate and intended for personal tracking and agent workflow context. They are not diagnosis, treatment, or medical advice. Confirm important nutrition decisions with a qualified professional.

Unofficial. Not affiliated with, endorsed by, or sponsored by USDA, Open Food Facts, or any third party. All trademarks belong to their respective owners.

📧 Contact & Support

📨 support@delx.ai — general questions, integration help, partnerships
🐛 Bug reports / feature requests — GitHub Issues
🐦 Updates — @delx369 on X
🌐 Site — wellness.delx.ai

wellness-nourish

Front door

Quickstart (60 seconds)

Zero-secret demo (offline, no API key)

Try it with your agent

Tools

Food photo decision tree

Privacy & what runs offline

See the full agent demo →

See also

Not medical advice

📧 Contact & Support

Score

Proud of your score? Add this badge to your README.

wellness-nourish FAQ

How do I install wellness-nourish?

Is wellness-nourish an official MCP server?

Related MCP servers

Related guides