# io.github.davidmosiah/wellness-nourish (npm · wellness-nourish)

Local-first nutrition MCP for AI agents: food, barcode, photo, intake, hydration, goals.

- Trust score: 64/100 (medium)
- Change this week: +40
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `wellness-nourish`: 64/100 (this document), [markdown](https://verifymcp.io/servers/davidmosiah-wellness-nourish/wellness-nourish.md), [page](https://verifymcp.io/servers/davidmosiah-wellness-nourish/wellness-nourish)

## Channel facts

- Registry: `npm`
- Package: `wellness-nourish`
- Version: `0.7.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Supply Chain Security**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects sharp 0.34.5, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (129 of 130), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5256 tokens (~103/item across 51 items; 46 tools + 5 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 28% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### Claude

```bash
claude mcp add davidmosiah-wellness-nourish -- npx -y wellness-nourish
```

### Codex

```bash
codex mcp add davidmosiah-wellness-nourish -- npx -y wellness-nourish
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "davidmosiah-wellness-nourish": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "wellness-nourish"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add davidmosiah-wellness-nourish --command npx --arg -y --arg wellness-nourish
```

### Hermes

```yaml
mcp_servers:
  davidmosiah-wellness-nourish:
    command: "npx"
    args: ["-y", "wellness-nourish"]
```

### Other

```json
{
  "mcpServers": {
    "davidmosiah-wellness-nourish": {
      "command": "npx",
      "args": [
        "-y",
        "wellness-nourish"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 64, +5)

- [security regression] CVE-2026-69207 affects this package: high
- [functional improvement] Stability: unverified → 0.30

### 2026-08-03 (score 59, +38)

- [security regression] GHSA-f88m-g3jw-g9cj affects this package: high
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → good
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Capabilities: pass
- [functional] Licence: MIT

### 2026-08-02 (score 21, −3)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-08-01 (score 24, +18)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 6, −43)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-30 (score 49, +25)

- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 28
- [functional] First check of Schema quality: unverified
- [functional] First check of Schema quality: fail

### 2026-07-27 (score 24)

First indexed and scored.

## MCP tools (46)

### `nourish_agent_manifest` (~38 tokens)

Nourish agent manifest

Return agent-facing install, safety, resource, and first-call guidance.

Input parameters:

- `client` (string)
- `response_format` (string)

### `nourish_capabilities` (~29 tokens)

Nourish capabilities

Describe supported nutrition workflows, providers, and recommended first tools.

Input parameters:

- `response_format` (string)

### `nourish_connection_status` (~34 tokens)

Nourish connection status

Report local storage, fixture, USDA, and Open Food Facts readiness without returning secrets.

Input parameters:

- `response_format` (string)

### `nourish_quickstart` (~63 tokens)

Nourish quickstart

Personalized 3-step setup walkthrough for the human user. Adapts to current state (USDA key set? OFF enabled? local-dir writable?). Call this first when the user asks 'how do I use this?'

Input parameters:

- `response_format` (string)

### `nourish_demo` (~46 tokens)

Nourish demo

Returns realistic example payloads of nourish_search_food, nourish_estimate_meal, and nourish_daily_summary so agents see the contract before any real call.

Input parameters:

- `response_format` (string)

### `nourish_privacy_audit` (~33 tokens)

Nourish privacy audit

Describe local storage, secret handling, source licensing, and safety boundaries.

Input parameters:

- `response_format` (string)

### `nourish_profile_get` (~64 tokens)

Nourish profile get

Returns the shared Delx Wellness profile (~/.delx-wellness/profile.json). Read-only. Surfaces calorie/macro targets, dietary preferences, restrictions/allergies, and goals so nourish coach/suggest tools can personalize meals.

Input parameters:

- `response_format` (string)

### `nourish_profile_update` (~128 tokens)

Nourish profile update

Persist a partial patch to the shared Delx Wellness profile. Requires explicit_user_intent: true. Rejects any field containing oauth/token/secret/password/cookie/refresh/api_key/session — the profile is for non-secret wellness context only.

Input parameters:

- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `patch` (object, required): Partial WellnessProfileDocument patch. Top-level keys: profile, goals, devices, training, nutrition, preferences, safety, notes.
- `response_format` (string)

### `nourish_onboarding` (~83 tokens)

Nourish onboarding

Returns the 11-question onboarding flow for the shared Delx Wellness profile. Read-only. The agent should ask these questions next so wellness-nourish (and the rest of the wellness stack) can personalize responses — non-secret data only, stored at ~/.delx-wellness/profile.json.

Input parameters:

- `locale` (string)
- `response_format` (string)

### `nourish_search_food` (~70 tokens)

Search foods

Search food providers by query. Use taco or br_local for Brazilian staples, open_food_facts for packaged products, usda for generic foods, or all.

Input parameters:

- `limit` (integer)
- `provider` (string)
- `query` (string, required)
- `response_format` (string)

### `nourish_lookup_barcode` (~46 tokens)

Lookup barcode

Lookup a packaged food barcode in Open Food Facts.

Input parameters:

- `barcode` (string, required): Numeric packaged-food barcode with 6 to 18 digits.
- `response_format` (string)

### `nourish_decode_barcode_image` (~74 tokens)

Decode barcode image

Decode a barcode from an image path, base64 image, or data URI without logging intake.

Input parameters:

- `image_base64` (string)
- `image_data_uri` (string)
- `image_mime_type` (string)
- `image_path` (string)
- `response_format` (string)

### `nourish_lookup_barcode_image` (~71 tokens)

Lookup barcode image

Decode a packaged-food barcode image, then lookup the product in Open Food Facts.

Input parameters:

- `image_base64` (string)
- `image_data_uri` (string)
- `image_mime_type` (string)
- `image_path` (string)
- `response_format` (string)

### `nourish_get_food` (~59 tokens)

Get food

Fetch a USDA food by source_id, an Open Food Facts food by barcode source_id, or a TACO food by source_id.

Input parameters:

- `response_format` (string)
- `source` (string, required)
- `source_id` (string, required)

### `nourish_estimate_meal` (~102 tokens)

Estimate meal

Estimate nutrition for a short meal text using local deterministic defaults. Accepts text or meal_text; preserve unresolved and confidence.

Input parameters:

- `locale` (string)
- `meal_text` (string): Alias for text for agents that naturally call this parameter meal_text.
- `meal_type` (string)
- `response_format` (string)
- `text` (string): Meal text to estimate, for example 'pão de queijo, café preto, banana'.

### `nourish_estimate_meal_photo` (~69 tokens)

Estimate meal photo

Estimate meal nutrition from an agent-provided photo observation; always requires user confirmation before logging.

Input parameters:

- `detected_items` (array)
- `image_description` (string, required)
- `locale` (string)
- `meal_type` (string)
- `response_format` (string)

### `nourish_analyze_food_image` (~114 tokens)

Analyze food image

Route agent-provided food image observations across barcode, nutrition label OCR, or meal-photo estimation without logging.

Input parameters:

- `barcode` (string)
- `barcode_observation` (string)
- `detected_barcodes` (array)
- `detected_items` (array)
- `image_description` (string)
- `locale` (string)
- `meal_type` (string)
- `nutrition_label_text` (string)
- `product_name` (string)
- `response_format` (string)

### `nourish_log_intake` (~217 tokens)

Log intake

Log an intake entry only after explicit user intent. Pass explicit_user_intent: true after the user asks to save/log/register; accepts text or meal_text plus structured food data.

Input parameters:

- `confidence` (number)
- `custom_food` (object)
- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `food`
- `food_ref` (object)
- `grams_estimate` (number)
- `meal_text` (string): Alias for text; use when the agent planned a meal_text argument.
- `meal_type` (string)
- `notes` (string)
- `nutrients` (object)
- `quantity` (number)
- `response_format` (string)
- `tags` (array)
- `text` (string): Meal text to estimate and log after confirmation.
- `timestamp` (string)
- `unit` (string)
- `wellness_context_refs` (array)

### `nourish_daily_coach` (~167 tokens)

Daily nutrition coach

Summarize today, goal gaps, wearable context, and a safe next action for Telegram-style coaching.

Input parameters:

- `auto_wearable` (boolean): If true and no wearable_context is passed inline, try to read the most recent shared wellness_context from ~/.delx-wellness/ (written by a wearable connector). The coach reports whether a context was…
- `date` (string)
- `focus` (string)
- `locale` (string)
- `meal_type` (string)
- `recent_intake_id` (string)
- `response_format` (string)
- `wearable_context` (object)
- `workout_context` (string)

### `nourish_suggest_next_meal` (~166 tokens)

Suggest next meal

Suggest a next meal from today's intake, goals, personal memory, and optional wearable context.

Input parameters:

- `auto_wearable` (boolean): If true and no wearable_context is passed inline, try to read the most recent shared wellness_context from ~/.delx-wellness/ (written by a wearable connector). The coach reports whether a context was…
- `date` (string)
- `focus` (string)
- `locale` (string)
- `meal_type` (string)
- `recent_intake_id` (string)
- `response_format` (string)
- `wearable_context` (object)
- `workout_context` (string)

### `nourish_after_log_review` (~164 tokens)

After-log review

Review the day after a meal log and explain what changed plus the next correction or action.

Input parameters:

- `auto_wearable` (boolean): If true and no wearable_context is passed inline, try to read the most recent shared wellness_context from ~/.delx-wellness/ (written by a wearable connector). The coach reports whether a context was…
- `date` (string)
- `focus` (string)
- `locale` (string)
- `meal_type` (string)
- `recent_intake_id` (string)
- `response_format` (string)
- `wearable_context` (object)
- `workout_context` (string)

### `nourish_pre_workout_nutrition` (~170 tokens)

Pre-workout nutrition

Suggest light pre-workout nutrition using goals, current intake, and optional WHOOP/Garmin context.

Input parameters:

- `auto_wearable` (boolean): If true and no wearable_context is passed inline, try to read the most recent shared wellness_context from ~/.delx-wellness/ (written by a wearable connector). The coach reports whether a context was…
- `date` (string)
- `focus` (string)
- `locale` (string)
- `meal_type` (string)
- `recent_intake_id` (string)
- `response_format` (string)
- `wearable_context` (object)
- `workout_context` (string)

### `nourish_evening_checkin` (~165 tokens)

Evening check-in

Check late-day protein, calories, and hydration gaps with a compact Telegram-friendly next step.

Input parameters:

- `auto_wearable` (boolean): If true and no wearable_context is passed inline, try to read the most recent shared wellness_context from ~/.delx-wellness/ (written by a wearable connector). The coach reports whether a context was…
- `date` (string)
- `focus` (string)
- `locale` (string)
- `meal_type` (string)
- `recent_intake_id` (string)
- `response_format` (string)
- `wearable_context` (object)
- `workout_context` (string)

### `nourish_pull_wearable_context` (~138 tokens)

Pull wearable context

Read the most recent shared wellness_context (delx-wellness-context/v1) written by a wearable connector to ~/.delx-wellness/, so coach tools can be recovery/strain-aware without the agent passing it inline. Read-only; never fabricates wearable data. If no connector has persisted a context yet, returns available:false with the expected path. The returned context can be passed straight into nourish_daily_coach / nourish_suggest_next_meal / nourish_pre_workout_nutrition as wearable_context (or set auto_wearable:true on those tools to pull it automatically).

Input parameters:

- `response_format` (string)

### `nourish_remember_meal` (~146 tokens)

Remember meal

Save a personal meal shortcut locally after explicit user intent, for example 'meu cafe normal' -> '2 ovos e banana'.

Input parameters:

- `aliases` (array)
- `default_meal_type` (string)
- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `label` (string, required): Personal shortcut, for example 'meu cafe normal'.
- `meal_text` (string, required): Canonical meal text that Nourish should estimate when this shortcut is used.
- `notes` (string)
- `response_format` (string)
- `tags` (array)

### `nourish_list_memory` (~29 tokens)

List personal nutrition memory

Read local remembered meals and nutrition preferences for personal Telegram shortcuts.

Input parameters:

- `response_format` (string)

### `nourish_forget_memory` (~72 tokens)

Forget personal nutrition memory

Delete a local remembered meal by id or label after explicit user intent.

Input parameters:

- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `id_or_label` (string, required)
- `response_format` (string)

### `nourish_update_intake` (~115 tokens)

Update intake

Update a local intake entry by id. Quantity or grams_estimate changes rescale nutrients to keep summaries consistent. Gated: requires explicit user intent — agents must not call this autonomously.

Input parameters:

- `grams_estimate` (number)
- `id` (string, required)
- `meal_type` (string)
- `notes` (string)
- `quantity` (number)
- `response_format` (string)
- `tags` (array)
- `timestamp` (string)
- `unit` (string)

### `nourish_list_intake` (~204 tokens)

List intake

List local intake entries with optional filters: date OR since/until range, meal_type, tag, source_trace, min_confidence, limit. All filters AND together. Returns most-recent-first.

Input parameters:

- `date` (string): Single-day filter. Mutually exclusive with since/until.
- `limit` (integer): Max entries to return (most recent first). Defaults to all matching.
- `meal_type` (string): Filter to a single meal type.
- `min_confidence` (number): Only return entries whose confidence is >= this value (e.g. 0.7).
- `response_format` (string)
- `since` (string): Start of date range (inclusive). Use with `until` for multi-day queries.
- `source_trace` (string): Filter by how the entry was created.
- `tag` (string): Filter to entries that have this tag (case-sensitive).
- `until` (string): End of date range (inclusive).

### `nourish_delete_intake` (~49 tokens)

Delete intake

Delete a local intake entry by id. Gated: requires explicit user intent — agents must not call this autonomously.

Input parameters:

- `id` (string, required)
- `response_format` (string)

### `nourish_clear_day` (~93 tokens)

Clear day

Delete all local intake entries for a date after explicit user intent.

Input parameters:

- `date` (string, required)
- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `include_hydration` (boolean): If true, also clear all hydration entries for the date in addition to intake.
- `response_format` (string)

### `nourish_delete_water` (~80 tokens)

Delete water entry

Delete a single local hydration entry by id after explicit user intent.

Input parameters:

- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `id` (string, required): Hydration entry id (e.g. water_<uuid>).
- `response_format` (string)

### `nourish_clear_hydration_day` (~97 tokens)

Clear hydration day

Delete all local hydration entries for a date after explicit user intent. Does not touch intake — pair with nourish_clear_day or use nourish_clear_day { include_hydration: true } for both.

Input parameters:

- `date` (string, required)
- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `response_format` (string)

### `nourish_carbon_summary` (~204 tokens)

Carbon footprint summary

Estimate the carbon footprint (kg CO2-equivalent) of a meal, plus optional lower-carbon swap suggestions. Pass `items: [{name, grams}, ...]` for an arbitrary meal, OR `date: YYYY-MM-DD` to compute carbon over that day's logged intake. Data: Agribalyse 3.1 (Etalab Open License) + Our World in Data / Poore & Nemecek 2018 (CC-BY 4.0). Read-only; never mutates state.

Input parameters:

- `date` (string): Compute carbon for all logged intake entries on this date (defaults to today in the active timezone).
- `include_swap_suggestions` (boolean): If true, return up to 3 lower-carbon swap suggestions for the highest-emission items in the meal.
- `items` (array): Compute carbon for an explicit list of meal items. Wins over `date` when both are present.
- `response_format` (string)

### `nourish_undo_last` (~165 tokens)

Undo last entry

Undo the most recently logged intake or hydration entry. The most common Telegram/agent recovery move ('I logged the wrong thing'). Returns what was undone so the agent can confirm. Requires explicit_user_intent. Pass kind: 'intake' | 'hydration' | 'any' (default 'any') to scope the undo.

Input parameters:

- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `kind` (string): Which most-recent entry to undo: 'intake' = last logged meal, 'hydration' = last logged water, 'any' = whichever was most recent across both stores. Defaults to 'any'.
- `response_format` (string)

### `nourish_log_water` (~118 tokens)

Log water

Log local hydration in milliliters after explicit user intent. Pass explicit_user_intent: true after the user asks to save/log water.

Input parameters:

- `amount_ml` (number, required): Water amount in milliliters. Must be greater than 0.
- `date` (string)
- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `notes` (string)
- `response_format` (string)
- `timestamp` (string)

### `nourish_hydration_summary` (~35 tokens)

Hydration summary

Summarize local hydration for a date.

Input parameters:

- `date` (string)
- `response_format` (string)

### `nourish_get_goals` (~28 tokens)

Get goals

Read local calorie, macro, and hydration goals.

Input parameters:

- `response_format` (string)

### `nourish_set_goals` (~225 tokens)

Set goals

Set local calorie, macro, and hydration goals after explicit user intent. Use daily: {...} or flat shortcuts like calories_kcal/protein_g; pass explicit_user_intent: true after confirmation.

Input parameters:

- `calories_kcal` (number): Flat shortcut for daily.calories_kcal.
- `carbohydrates_g` (number): Flat shortcut for daily.carbohydrates_g.
- `daily` (object): Nested daily nutrient goals, for example { calories_kcal, protein_g, carbohydrates_g, fat_g }.
- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `fat_g` (number): Flat shortcut for daily.fat_g.
- `fiber_g` (number): Flat shortcut for daily.fiber_g.
- `hydration_ml` (number): Daily hydration target in milliliters.
- `protein_g` (number): Flat shortcut for daily.protein_g.
- `response_format` (string)
- `sugar_g` (number): Flat shortcut for daily.sugar_g.

### `nourish_goal_progress` (~148 tokens)

Goal progress

Compute per-day progress vs configured goals (kcal, protein, carbs, fat, water) for today / yesterday / last_7_days / last_30_days. Returns per-day breakdown (consumed, goal, pct, delta_to_goal), period totals, multi-day averages, days_on_target count, and locale-aware next-action recommendations (pt-BR if profile language is Portuguese, otherwise en). Read-only: no logging side effects, no explicit_user_intent required.

Input parameters:

- `period` (string): Window to evaluate: today (default), yesterday, last_7_days, or last_30_days. All bucketed in the active timezone.
- `response_format` (string)

### `nourish_daily_summary` (~152 tokens)

Daily summary

Summarize local intake totals, confidence, and source coverage for a date. Pass `compare_to: 'yesterday'` or `compare_to: '7d_avg'` to add a `comparison` block with per-nutrient deltas — useful for trend coaching ('your protein is low again — third day in a row').

Input parameters:

- `compare_to` (string): Optional baseline to add a `comparison` block: 'yesterday' = previous day, '7d_avg' = average of the prior 7 days. 'none' (default) skips the comparison.
- `date` (string): Date to summarize (defaults to today in active timezone).
- `response_format` (string)

### `nourish_compare_days` (~109 tokens)

Compare two days

Compute a per-nutrient diff between two days' summaries. Returns deltas (date_b - date_a) for calories, protein, carbs, fat, fiber, sugar, sodium plus what changed by meal type. Useful for 'how was today vs yesterday?' coaching.

Input parameters:

- `date_a` (string, required): First date (the 'baseline' to compare against).
- `date_b` (string, required): Second date (the 'newer' / comparison date).
- `response_format` (string)

### `nourish_bulk_log_intake` (~170 tokens)

Bulk log intake

Log multiple intake entries in a single call. Each item is processed through the same text-estimator pipeline as `nourish_log_intake`, but the entire batch shares one explicit_user_intent flag — perfect for Telegram users who say 'log everything I ate today: breakfast was X, lunch was Y, dinner was Z'. Returns per-item success/failure so a partial failure doesn't lose the rest.

Input parameters:

- `explicit_user_intent` (boolean): Pass true only after the user explicitly asked to save, log, set, or delete this personal nutrition data.
- `items` (array, required): Array of meals to log atomically (1-20). Each item gets its own intake entry. The `explicit_user_intent` flag covers the entire batch.
- `response_format` (string)

### `nourish_weekly_summary` (~40 tokens)

Weekly summary

Summarize seven days of local intake totals from a start date.

Input parameters:

- `response_format` (string)
- `start_date` (string)

### `nourish_export_data` (~218 tokens)

Export intake data

Export local intake data as JSONL or CSV without provider secrets or tokens. Defaults to the 500 most-recent rows; pass since/until to scope by date or max_rows to widen/narrow. Omitted rows are reported so you can refine instead of dumping months of history into chat (use the `wellness-nourish export` CLI for a full unbounded dump).

Input parameters:

- `export_format` (string)
- `max_rows` (integer): Max data rows to return in the response (most recent first). Defaults to 500. Omitted rows are reported as a count so the agent can refine by date or fall back to the `wellness-nourish export` CLI fo…
- `response_format` (string)
- `since` (string): Only include entries on or after this date (inclusive, YYYY-MM-DD). Use to keep the response small instead of dumping months of history into chat.
- `until` (string): Only include entries on or before this date (inclusive, YYYY-MM-DD).

### `nourish_chatgpt_dashboard` (~89 tokens)

Open Nourish dashboard

Open an interactive ChatGPT/MCP Apps dashboard for today's nutrition summary, safe meal estimation, and next-meal coaching. Read-only; logging still requires explicit user confirmation through existing tools.

Input parameters:

- `date` (string): Local date to summarize as YYYY-MM-DD. Defaults to today.
- `focus` (string)
- `locale` (string)
- `response_format` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/davidmosiah-wellness-nourish/wellness-nourish#diagnostics

## Score history

- 2026-08-04: 64
- 2026-08-03: 59
- 2026-08-02: 21
- 2026-08-01: 24
- 2026-07-31: 6
- 2026-07-30: 49
- 2026-07-28: 24
- 2026-07-27: 24

## Links

- npm package: https://www.npmjs.com/package/wellness-nourish
- Socket report: https://socket.dev/npm/package/wellness-nourish
- Repository: https://github.com/davidmosiah/wellness-nourish
- Website: https://wellness.delx.ai/nutrition
- Changelog RSS feed: https://verifymcp.io/servers/davidmosiah-wellness-nourish/wellness-nourish/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/davidmosiah-wellness-nourish/wellness-nourish/changelog.json
- HTML version of this page: https://verifymcp.io/servers/davidmosiah-wellness-nourish/wellness-nourish