---
title: Nutrition MCP for AI Agents: Nourish Setup and Safe Meal Logging
description: Food lookup, barcode photo lookup, meal photo estimates, intake logs, hydration, goals, carbon summaries and nutrition trends for agents.
canonical: https://wellness.delx.ai/nutrition
content_signal: ai-train=no, search=yes, ai-input=yes
---

# Nutrition MCP for AI agents

Nourish is the Delx Wellness nutrition layer. It is a local-first MCP server for calories, macros, TACO/BR food search, barcode image decoding, meal photo previews, carbon context and nutrition trends, built to sit beside wearable connectors instead of pretending to be another device provider.

## Direct answer

Nourish MCP 0.8.2 gives AI agents local nutrition context through a preview-confirm-log contract. Inspect readiness and verified synthetic shapes first, preserve confidence and provenance, and never write a meal without explicit user intent. This is nutrition context, not medical advice.

## Install

```bash
npx -y wellness-nourish@0.8.2 setup --client claude
npx -y wellness-nourish doctor
```

## First meal in two minutes

1. Call `nourish_connection_status` to check providers and the local store.
2. Call `nourish_demo` to inspect verified synthetic response shapes without personal data.
3. Call `nourish_estimate_meal` and show calories, macros, confidence, warnings and unresolved items.
4. Ask the user to confirm. Only then call `nourish_log_intake` with `explicit_user_intent: true`.
5. Call `nourish_daily_summary` with `privacy_mode: "summary"` unless item-level detail is necessary.

The read-only ChatGPT dashboard can show daily nutrition, hydration, profile gaps and a preview-only estimate. Mutating tools still require explicit user intent through the MCP contract.

## Agent client config

```json
{
  "mcpServers": {
    "nourish": {
      "command": "npx",
      "args": ["-y", "wellness-nourish@0.8.2"],
      "env": {
        "FDC_API_KEY": "${FDC_API_KEY}",
        "NOURISH_OFF_ENABLED": "1"
      }
    }
  }
}
```

## Hermes Telegram personal setup

```bash
npx -y wellness-nourish setup --client hermes --profile personal --local-dir /root/.hermes/nourish/personal
npx -y wellness-nourish doctor --client hermes --json
hermes mcp test nourish
```

This installs the Hermes skill at `~/.hermes/skills/nourish-mcp/SKILL.md` so Telegram meal messages, barcode photos and meal photo previews use confirmation-before-log by default.

## Workflows

- Inspect nourish_agent_manifest or nourish_capabilities before building a client against the tool set.
- Use nourish_demo for verified synthetic response shapes before reading or writing personal data.
- Preview a meal estimate before writing to the local log.
- Install Hermes personal mode for Telegram with setup --client hermes.
- Search TACO/BR local food data for Brazilian staples before falling back to USDA.
- Search USDA FoodData Central before estimating generic foods.
- Lookup packaged foods through Open Food Facts with ODbL attribution.
- Compare days, inspect trends, undo the last entry, or bulk-log a Telegram food recap.
- Summarize meal carbon footprint when food names have kg CO2e matches.
- Decode barcode photos from image paths, base64 images or data URIs before Open Food Facts lookup.
- Use agent vision observations for meal photo previews, then confirm portions before logging.
- Use daily coaching and remembered meal shortcuts only with clear user context and explicit save intent.
- Read summaries with privacy_mode=summary unless the user explicitly needs item-level detail.
- Summarize calories, macros, hydration and goals in agent-friendly markdown.
- Export local intake data as JSONL or CSV.

## MCP tools

- `nourish_agent_manifest`
- `nourish_capabilities`
- `nourish_quickstart`
- `nourish_demo`
- `nourish_profile_get`
- `nourish_profile_update`
- `nourish_onboarding`
- `nourish_connection_status`
- `nourish_search_food`
- `nourish_lookup_barcode`
- `nourish_decode_barcode_image`
- `nourish_lookup_barcode_image`
- `nourish_estimate_meal`
- `nourish_estimate_meal_photo`
- `nourish_analyze_food_image`
- `nourish_log_intake`
- `nourish_daily_coach`
- `nourish_suggest_next_meal`
- `nourish_remember_meal`
- `nourish_list_memory`
- `nourish_bulk_log_intake`
- `nourish_undo_last`
- `nourish_compare_days`
- `nourish_carbon_summary`
- `nourish_daily_summary`
- `nourish_weekly_summary`
- `nourish_log_water`
- `nourish_hydration_summary`
- `nourish_set_goals`
- `nourish_goal_progress`
- `nourish_export_data`

## Resources

- `nourish://agent-manifest`
- `nourish://capabilities`
- `nourish://privacy-audit`
- `nourish://usage-guide`

## Privacy

- Food logs, hydration and goals stay under ~/.wellness-nourish unless NOURISH_LOCAL_DIR is set.
- Profile and goals persist locally to ~/.delx-wellness/profile.json (mode 0600); shared with all 14 Delx Wellness connectors and never uploaded.
- No hosted account is required.
- Agents must preserve source attribution, confidence and safety warnings.
- Mutating MCP tools require explicit user intent.

## Known limits

- Nutrition estimates are approximate.
- Meal photo estimates depend on the agent vision layer and always require user confirmation before logging.
- No hosted sync or clinical guidance.
- Open Food Facts data carries attribution and share-alike obligations.
- TACO values ship as an attributed curated subset while redistribution-license confirmation remains a 1.0 gate.

## Links

- GitHub: https://github.com/davidmosiah/wellness-nourish
- npm: https://www.npmjs.com/package/wellness-nourish