{ "markdown": "\n

Wellness Nourish

\n\n
\n \"Wellness\n
\n\n

\n Local-first nutrition MCP — food search, barcode lookup, intake logging, hydration. Works without OAuth.
\n Local-first MCP server — tokens never leave your machine.\n

\n\n

\n \"npm\n \"GitHub\n \"npm\n \"CI\"\n \"License\n \"Site\"\n

\n\n

\n \"GitHub\n \"Built\n \"Verified\n \"Hermes\n \"OpenClaw\n \"Nourish\"\n

\n\n

\n ๐Ÿ“ˆ Published on npm and used by AI agents and MCP clients — see the live download badge above for current numbers.
\n If Nourish helps your agent, a โญ on this repo makes it easier for other AI builders to find.\n

\n\n> โšก **One-command install** — pick your runtime:\n> - [Delx Wellness for Hermes](https://github.com/davidmosiah/delx-wellness-hermes): `npx -y delx-wellness-hermes setup`\n> - [Delx Wellness for OpenClaw](https://github.com/davidmosiah/delx-wellness-openclaw): `npx -y delx-wellness-openclaw setup`\n>\n> 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.\n>\n> Want runnable agent examples? Use the [Delx Wellness hub](https://github.com/davidmosiah/delx-wellness#run-it-in-your-agent) for prompt packs, MCP client configs and local-first workflow templates.\n\n> **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, feijรฃo, concha, churrasco-style meals) plus Smithery install. Offline demo: `NOURISH_FIXTURE_MODE=1 npx -y wellness-nourish search banana`. Notes: [CHANGELOG.md](CHANGELOG.md) ยท eval: [`docs/evals/pt-br-meal-estimator.json`](docs/evals/pt-br-meal-estimator.json) (52 cases).\n\n> **Public proof:** Nourish is tracked in the Delx [Open Source Growth Snapshot](https://github.com/davidmosiah/delx-wellness/blob/main/docs/open-source-growth-snapshot.md) 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.\n\n---\n\n## HTTP (v2 stateless)\n\nDefault is **stdio**. Optional Streamable HTTP โ€” no session id, JSON responses, loopback only:\n\n```bash\nnpx -y wellness-nourish --http\n# GET http://127.0.0.1:3000/health\n# POST http://127.0.0.1:3000/mcp (sessionless)\n```\n\nEnv: `NOURISH_MCP_HOST`, `NOURISH_MCP_PORT`, `NOURISH_MCP_TRANSPORT=http`.\n\n\n\n\nLocal-first nutrition MCP for AI agents โ€” food search, barcode lookup, photo-assisted meal estimation, intake logging, hydration, goals and coach-style workflows. No OAuth, no hosted account.\n\n## Front door\n\n- **Install one connector** โ€” `npx -y wellness-nourish setup --client claude`\n- **Run it in** Claude ยท Cursor ยท ChatGPT ยท Hermes ยท OpenClaw โ€” see the [client examples](https://github.com/davidmosiah/delx-wellness#run-it-in-your-agent).\n- **Local-first** โ€” your tokens and food logs never leave your machine ([privacy](#privacy--what-runs-offline)).\n- **Which connector should I use?** โ€” see the [front-door guide](https://github.com/davidmosiah/delx-wellness#which-connector-should-i-use).\n\n## Quickstart (60 seconds)\n\n```bash\nnpx -y wellness-nourish@0.8.0 doctor\nnpx -y wellness-nourish@0.8.0 search banana\nnpx -y wellness-nourish@0.8.0 barcode 0000000000000\nnpx -y wellness-nourish@0.8.0 log --preview \"2 ovos, banana e cafรฉ preto\"\n```\n\n`doctor` checks readiness, `search`/`barcode` hit the food providers, and `log --preview` estimates a meal locally without writing anything.\n\n### How you can help\n\n| Action | Link |\n| --- | --- |\n| Star if it earned it | [stargazers](https://github.com/davidmosiah/wellness-nourish/stargazers) |\n| Docs GFI โ€” first meal in 2 minutes | [#25](https://github.com/davidmosiah/wellness-nourish/issues/25) |\n| File a real bug / pt-BR food miss | [issues](https://github.com/davidmosiah/wellness-nourish/issues) |\n| Full wellness hub | [`delx-wellness`](https://github.com/davidmosiah/delx-wellness) |\n\n### Zero-secret demo (offline, no API key)\n\n`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:\n\n```bash\n$ NOURISH_FIXTURE_MODE=1 wellness-nourish search banana\nBananas, raw\tusda\t89 kcal/100g\nBANANA\tusda\t312 kcal/100g\n```\n\n## Try it with your agent\n\nThree copy-paste prompts, all backed by existing tools:\n\n- \"Estimate the calories and protein in 2 eggs, a banana and black coffee.\" โ†’ `nourish_estimate_meal`\n- \"Look up the barcode 737628064502 and tell me what it is.\" โ†’ `nourish_lookup_barcode`\n- \"What should I eat next today, given my goals?\" โ†’ `nourish_daily_coach` / `nourish_suggest_next_meal`\n\nMutating tools (log intake, water, goals, clear-day) never run without explicit user save intent โ€” they return `USER_ACTION_REQUIRED` until the agent passes `explicit_user_intent: true`.\n\n## Tools\n\nNourish 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`).\n\n- **Full CLI (20+ commands), install, client configs & ChatGPT dashboard** โ†’ [`docs/cli.md`](docs/cli.md)\n- **Hermes / Telegram personal setup (10-step flow)** โ†’ [`docs/telegram.md`](docs/telegram.md)\n- **Data providers & attribution (USDA, Open Food Facts, ZXing)** โ†’ [`docs/providers.md`](docs/providers.md)\n- **pt-BR meal-estimator eval set (52 examples)** โ†’ [`docs/evals/pt-br-meal-estimator.json`](docs/evals/pt-br-meal-estimator.json)\n- **Reproducible Telegram/Hermes demo transcript** โ†’ [`docs/telegram-demo-transcript.json`](docs/telegram-demo-transcript.json)\n\n### Food photo decision tree\n\nAgents should route Telegram/Hermes/OpenClaw food photos by the strongest signal they can extract:\n\n1. Barcode is visible and image bytes are available: call `nourish_lookup_barcode_image`.\n2. 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.\n3. Nutrition facts are readable: OCR the label and call `nourish_analyze_food_image` with `product_name` and `nutrition_label_text`.\n4. It is a plate or unpackaged food: describe visible foods/portions and call `nourish_analyze_food_image` with `detected_items` or `image_description`.\n5. Never log from an image response until the user confirms the product or meal, serving size and save intent.\n\nImage tools accept exactly one of these input forms:\n\n```json\n{ \"image_path\": \"/tmp/telegram-food-photo.jpg\" }\n```\n\n```json\n{ \"image_base64\": \"\", \"image_mime_type\": \"image/jpeg\" }\n```\n\n```json\n{ \"image_data_uri\": \"data:image/jpeg;base64,\" }\n```\n\nIf 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.\n\n

\n \"Wellness\n

\n\nThe capture above is generated from a real MCP run in fixture mode with a temporary local directory:\n\n```bash\nnpm run demo:capture\n```\n\nThe committed transcript proves the exact tool sequence: `nourish_estimate_meal` โ†’ user confirmation โ†’ `nourish_log_intake` โ†’ `nourish_daily_summary`.\n\n## Privacy & what runs offline\n\nIntake, 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 โ€” unless `NOURISH_FIXTURE_MODE=1` keeps everything offline against the bundled fixtures.\n\nAgents should never ask users to paste API keys, tokens, raw health exports, or private food logs into chat โ€” configure secrets through environment variables or local files. Full detail in [`docs/providers.md`](docs/providers.md).\n\n## See the full agent demo โ†’\n\nWatch Nourish work alongside the other connectors in one reproducible run:\n\n```bash\nnpx -y delx-living-body demo\n```\n\nAnchor question: **\"Should I train hard today?\"** โ€” the demo combines wearable recovery signals with nutrition context to answer it. This is the shared, reproducible proof for the whole Delx Wellness stack.\n\n\n\n## See also\n\nThe full [Delx Wellness](https://wellness.delx.ai) connector library:\n\n| Provider | Package | Repo |\n|---|---|---|\n| WHOOP | [`whoop-mcp-unofficial`](https://www.npmjs.com/package/whoop-mcp-unofficial) | [whoop-mcp](https://github.com/davidmosiah/whoop-mcp) |\n| Oura | [`oura-mcp-unofficial`](https://www.npmjs.com/package/oura-mcp-unofficial) | [ouramcp](https://github.com/davidmosiah/ouramcp) |\n| Garmin | [`garmin-mcp-unofficial`](https://www.npmjs.com/package/garmin-mcp-unofficial) | [garmin-mcp](https://github.com/davidmosiah/garmin-mcp) |\n| Strava | [`strava-mcp-unofficial`](https://www.npmjs.com/package/strava-mcp-unofficial) | [strava-mcp](https://github.com/davidmosiah/strava-mcp) |\n| Fitbit | [`fitbit-mcp-unofficial`](https://www.npmjs.com/package/fitbit-mcp-unofficial) | [fitbitmcp](https://github.com/davidmosiah/fitbitmcp) |\n| Google Health | [`google-health-mcp-unofficial`](https://www.npmjs.com/package/google-health-mcp-unofficial) | [google-health-mcp](https://github.com/davidmosiah/google-health-mcp) |\n| Withings | [`withings-mcp-unofficial`](https://www.npmjs.com/package/withings-mcp-unofficial) | [withingsmcp](https://github.com/davidmosiah/withingsmcp) |\n| Apple Health | [`apple-health-mcp-unofficial`](https://www.npmjs.com/package/apple-health-mcp-unofficial) | [apple-health-mcp](https://github.com/davidmosiah/apple-health-mcp) |\n| Samsung Health | [`samsung-health-mcp-unofficial`](https://www.npmjs.com/package/samsung-health-mcp-unofficial) | [samsung-health-mcp](https://github.com/davidmosiah/samsung-health-mcp) |\n| Polar | [`polar-mcp-unofficial`](https://www.npmjs.com/package/polar-mcp-unofficial) | [polarmcp](https://github.com/davidmosiah/polarmcp) |\n| Nourish (nutrition) | [`wellness-nourish`](https://www.npmjs.com/package/wellness-nourish) | [wellness-nourish](https://github.com/davidmosiah/wellness-nourish) |\n\n**One-command setup for Hermes** โ€” preconfigures every connector above plus wellness skills + onboarding: [`delx-wellness-hermes`](https://github.com/davidmosiah/delx-wellness-hermes).\n\n\n\n---\n\n## Not medical advice\n\nNutrition 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.\n\n**Unofficial.** Not affiliated with, endorsed by, or sponsored by USDA, Open Food Facts, or any third party. All trademarks belong to their respective owners.\n\n## ๐Ÿ“ง Contact & Support\n\n- ๐Ÿ“จ **support@delx.ai** โ€” general questions, integration help, partnerships\n- ๐Ÿค **Code of Conduct** โ€” [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)\n- ๐Ÿ› **Bug reports / feature requests** โ€” [GitHub Issues](https://github.com/davidmosiah/wellness-nourish/issues)\n- ๐Ÿฆ **Updates** โ€” [@delx369](https://x.com/delx369) on X\n- ๐ŸŒ **Site** โ€” [wellness.delx.ai](https://wellness.delx.ai)\n\n**First meal in 2 minutes:** [docs/first-meal-2-minutes.md](docs/first-meal-2-minutes.md)\n\n**Wearable context fields (no invention):** [docs/wearable-context-schema.md](docs/wearable-context-schema.md)\n\n## Skill or MCP\n\nSame package, two doors. MCP registers tools on stdio/HTTP. The [skill](skill/SKILL.md) can drive the **same** tools through the CLI when the client has no MCP:\n\n```bash\nnpx -y wellness-nourish call nourish_connection_status --json '{}'\n```\n\nCopy `skill/SKILL.md` into your agent skills dir.\n", "bytes": 14788, "sha": "dc9198b7bf4e2507ee1ec9c088e15036e96f5c0cd6ac63f860b023208e1c23d6", "repo_slug": "davidmosiah/wellness-nourish", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_davidmosiah_wellness_nourish_165977a0/readme" }