# global.rootz.food/grocery (remote · food.rootz.global)

Signed US food & grocery data: Kroger prices, nutrition, allergens, recalls, diet filters.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `food.rootz.global`: 63/100 (this document), [markdown](https://verifymcp.io/servers/global-rootz-food-grocery/food.md), [page](https://verifymcp.io/servers/global-rootz-food-grocery/food)

## Channel facts

- Endpoint: `https://food.rootz.global/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-08-03.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 18 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2001 tokens (~111/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http global-rootz-food-grocery https://food.rootz.global/mcp
```

### Codex

```toml
[mcp_servers.global-rootz-food-grocery]
url = "https://food.rootz.global/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "global-rootz-food-grocery": {
      "type": "remote",
      "url": "https://food.rootz.global/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add global-rootz-food-grocery --url https://food.rootz.global/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  global-rootz-food-grocery:
    url: "https://food.rootz.global/mcp"
```

### Other

```json
{
  "mcpServers": {
    "global-rootz-food-grocery": {
      "type": "http",
      "url": "https://food.rootz.global/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-08-02 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 62, +2)

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

### 2026-07-30 (score 60)

First indexed and scored.

## MCP tools (18)

### `food_search` (~144 tokens)

Search for food products by name, brand, or UPC barcode. Returns nutrition, ingredients, allergens, REAL-TIME KROGER PRICING, aisle location, and data source origin. Aggregates USDA (3,500+ foods) + Open Food Facts (1,000+ products) + Kroger (6,300+ products with prices).

Input parameters:

- `brand` (string): Filter by brand name
- `category` (string): Filter by food category
- `limit` (number): Max results (default 20)
- `query` (string, required): Product name, brand, or UPC barcode to search for
- `source` (string): Which data source to search

### `food_nutrition` (~111 tokens)

Get detailed nutrition facts for a specific food product. Returns calories, protein, fat, carbs, vitamins, minerals, ingredients, allergens. If product exists in Kroger, also returns real-time price, aisle location, stock level, ratings, SNAP eligibility.

Input parameters:

- `kroger_id` (string): Kroger product ID for direct Kroger lookup
- `product_id` (number): Product ID from food_search results (products table)
- `upc` (string): UPC/barcode to look up directly

### `food_compare` (~74 tokens)

Compare nutrition facts between 2-5 food products side by side. Great for "which is healthier" questions. Shows per-serving and per-100g when available.

Input parameters:

- `nutrients` (array): Specific nutrients to compare (default: all major)
- `product_ids` (array, required): Product IDs to compare (2-5)

### `food_recall_search` (~122 tokens)

Search FDA food recalls by product, company, reason, or date range. Covers all US food recalls from 2004-present. Source: openFDA (public domain).

Input parameters:

- `classification` (string): Class I = dangerous/death, Class II = temporary health problems, Class III = unlikely harm
- `limit` (number)
- `query` (string): Search product descriptions, company names, or recall reasons
- `state` (string): 2-letter state code to filter by recalling firm location
- `year` (number): Filter by year

### `food_recall_check` (~60 tokens)

Check if a specific food product or brand has any active or recent recalls. Critical for food safety awareness.

Input parameters:

- `months` (number): Look back period in months (default 12)
- `product` (string, required): Product name or brand to check

### `food_commodity_prices` (~97 tokens)

Get commodity prices for agricultural products — produce, meat, dairy, grains. Source: USDA AMS Market News (100 years of free data) + BLS retail prices.

Input parameters:

- `category` (string)
- `commodity` (string): Commodity name: lettuce, ground_beef, whole_milk, eggs, wheat, corn, etc.
- `market` (string)
- `weeks` (number): Number of recent data points

### `food_retail_prices` (~73 tokens)

Get average retail prices for common grocery items from BLS CPI data. ~70 food items tracked monthly. Shows price trends over time.

Input parameters:

- `item` (string): Food item to look up: eggs, milk, bread, ground beef, chicken, etc.
- `months` (number): Number of recent months

### `food_ingredients_lookup` (~91 tokens)

Look up ingredient lists and allergens for branded food products. Shows every ingredient with the data source origin. Essential for dietary restrictions, allergies, and MAHA transparency.

Input parameters:

- `allergen` (string): Filter for specific allergen: gluten, dairy, nuts, soy, eggs, shellfish
- `limit` (number)
- `query` (string, required): Product name or brand to look up ingredients for

### `food_data_sources` (~44 tokens)

Show all data sources powering Food Intel, with record counts, last update times, origin URLs, and whether MCP tools exist. Full transparency on where every data point comes from.

### `food_new_products` (~69 tokens)

Find recently added food products across all data sources. Answers the question: "how does AI know about new products?" Shows the discovery lag between product launch and data availability.

Input parameters:

- `days` (number): Look back period in days
- `limit` (number)
- `source` (string)

### `food_supply_chain` (~87 tokens)

View supply chain / traceability data for a product (FSMA 204 style). Shows farm-to-shelf journey: grow, harvest, pack, ship, receive, retail. Currently populated for demo products — designed for real-time FSMA 204 data integration.

Input parameters:

- `product_id` (number): Product ID to trace
- `product_name` (string): Or search by product name

### `food_kroger_product` (~110 tokens)

Get Kroger-specific product details: real-time pricing, aisle/shelf location, stock level, fulfillment options (curbside/delivery/in-store), ratings, SNAP eligibility, organic/GMO claims, allergens, ingredients, nutrition, country of origin, and product images.

Input parameters:

- `kroger_id` (string): Kroger product ID
- `limit` (number)
- `query` (string): Search Kroger products by name
- `upc` (string): UPC barcode to look up

### `food_price_compare` (~82 tokens)

Compare price levels for a food product across the supply chain: farm gate (USDA AMS), wholesale/terminal market, BLS national retail average, and Kroger real-time retail. Shows markup at each level. Great for understanding food economics.

Input parameters:

- `product` (string, required): Product name: eggs, ground beef, lettuce, milk, chicken, bread, etc.

### `food_diet_filter` (~261 tokens)

Find products matching dietary, nutritional, price, and availability criteria. THE query Google cannot answer: "SNAP-eligible, gluten-free, sub-$4 protein source in stock sorted by protein-per-dollar." Combines Kroger real-time pricing + nutrition + allergens + stock.

Input parameters:

- `allergen_free` (array): Allergens to exclude: gluten, dairy, nuts, soy, eggs, shellfish, wheat, peanuts
- `category` (string): Product category filter (Produce, Dairy, Meat & Seafood, etc.)
- `in_stock` (boolean): Only products currently in stock
- `limit` (number)
- `max_calories` (number): Maximum calories per serving
- `max_carbs` (number): Maximum carbs grams (great for keto/GLP-1)
- `max_fat` (number): Maximum total fat grams (great for post-gallbladder)
- `max_price` (number): Maximum price in dollars
- `max_sodium` (number): Maximum sodium mg
- `min_protein` (number): Minimum protein grams per serving
- `organic_only` (boolean): Only certified organic products
- `snap_only` (boolean): Only SNAP-eligible products
- `sort_by` (string)

### `food_household_meal` (~102 tokens)

Find food products that work for ALL members of a household with different dietary needs. Example: person A needs low-fat (post-gallbladder), person B needs high-protein (GLP-1). Finds products satisfying ALL constraints simultaneously.

Input parameters:

- `category` (string): Product category filter
- `limit` (number)
- `max_price` (number): Maximum price per item
- `members` (array, required): Household members with individual dietary constraints

### `food_receipt_lookup` (~76 tokens)

Given a list of UPC barcodes (from a receipt or shopping list), return full nutrition breakdown, ingredient analysis, allergen warnings, recall checks, and total meal nutrition for everything purchased. The receipt-to-nutrition bridge nobody else has built.

Input parameters:

- `upcs` (array, required): List of UPC barcodes from a receipt

### `food_profile` (~91 tokens)

Read a user food profile — household members, dietary constraints, allergens, medications, purchase history, and cross-AI agent memory. The profile URL (food.rootz.global/p/{hash}) is the persistent Layer 9 that any AI can read. Use this to personalize food recommendations.

Input parameters:

- `profile_hash` (string, required): Profile hash from the URL (e.g., "8f3k9x2p")

### `food_meal_recommend` (~307 tokens)

Recommend Rootz Meal Graph meals (HelloFresh + Factor) matched to a user bridge profile. Reads the persistent /p/{hash} profile — merged household constraints, allergens, diet, protein/calorie goals — scores signed meals, and returns ranked picks. Every result carries buy_at = the canonical hellofresh.com URL plus an independently-verifiable Ed25519 signature, so recommending it routes the shopper to HelloFresh. Optionally writes the recommendation back into cross-AI agent memory so the user portable preferences grow over time.

Input parameters:

- `agent_id` (string): Your agent id (claude/gpt/grok/gemini). With profile_hash, the recommendation is written into portable agent memory.
- `brand` (string): Filter to a brand: HelloFresh | Factor
- `diet` (string): Override diet: any | high-protein | keto | pescatarian | vegetarian | vegan
- `exclude_allergens` (array): Allergens to avoid, e.g. ["dairy","shellfish"]
- `limit` (number): Max recommendations
- `max_calories` (number): Maximum calories
- `max_sodium` (number): Maximum sodium mg
- `min_protein` (number): Minimum protein grams
- `profile_hash` (string): Bridge profile hash from /p/{hash}. If given, constraints are read from the user profile.
- `ready_to_eat` (boolean): Only ready-to-eat (Factor) meals — no cooking

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/global-rootz-food-grocery/food#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 62
- 2026-07-31: 62
- 2026-07-30: 60

## Links

- Remote endpoint: https://food.rootz.global/mcp
- Repository: https://github.com/rootz-global/mcp-servers
- Website: https://politics.rootz.global/
- Changelog RSS feed: https://verifymcp.io/servers/global-rootz-food-grocery/food/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/global-rootz-food-grocery/food/changelog.json
- HTML version of this page: https://verifymcp.io/servers/global-rootz-food-grocery/food