Nutrition Skill

Overview

Nutrition works by matching your search term to the best generic food in the USDA FoodData Central SR Legacy database and returning its per-100-gram nutrition panel, layered with derived intelligence the raw USDA data does not carry - calories per gram, the percentage of calories from protein, fat and carbohydrate, and protein per 100 calories. Paid plans unlock the full micronutrient panel (sodium, potassium, cholesterol, the individual fats, minerals and vitamins), the percent Daily Value each nutrient supplies the way a Nutrition Facts label reads, plain-language dietary flags like high protein and low sodium, and can scale the whole panel to any serving weight in grams. Data comes from the public-domain USDA food composition dataset.

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as NutritionSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

{
  "name": "NutritionSkill",
  "arguments": {
    "food": "banana"
  }
}

You do not name the tool yourself; the model picks it. Asking about banana in the terms this skill covers is enough for it to reach for NutritionSkill on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}

https://api.vervekit.com/v1/mcp

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

{
  "status": "ok",
  "error": null,
  "data": {
    "food": "Bananas, raw",
    "fdcId": 173944,
    "category": "Fruits and Fruit Juices",
    "basis": "per 100g",
    "servingSizes": [
      {
        "label": "1 NLEA serving",
        "grams": 126
      },
      {
        "label": "1 extra large (9\" or longer)",
        "grams": 152
      },
      {
        "label": "1 large (8\" to 8-7/8\" long)",
        "grams": 136
      }
    ],
    "nutrition": {
      "calories": 89,
      "protein": 1.09,
      "totalFat": 0.33,
      "carbohydrates": 22.8,
      "fiber": 2.6,
      "sugars": 12.2
    },
    "micronutrients": {
      "sodium": 1,
      "potassium": 358,
      "cholesterol": 0,
      "saturatedFat": 0.112,
      "transFat": 0,
      "monounsaturatedFat": 0.032,
      "polyunsaturatedFat": 0.073,
      "calcium": 5,
      "iron": 0.26,
      "magnesium": 27,
      "phosphorus": 22,
      "zinc": 0.15,
      "vitaminC": 8.7,
      "vitaminA": 3,
      "vitaminD": 0,
      "vitaminE": 0.1,
      "vitaminK": 0.5,
      "thiamin": 0.031,
      "riboflavin": 0.073,
      "niacin": 0.665,
      "vitaminB6": 0.367,
      "folate": 20,
      "vitaminB12": 0,
      "water": 74.9
    },
    "analytics": {
      "caloriesPerGram": 0.89,
      "proteinCaloriePercent": 4.4,
      "fatCaloriePercent": 3,
      "carbCaloriePercent": 92.6,
      "proteinPer100Calories": 1.22
    },
    "dailyValues": {
      "protein": 2.2,
      "totalFat": 0.4,
      "saturatedFat": 0.6,
      "cholesterol": 0,
      "sodium": 0,
      "carbohydrates": 8.3,
      "fiber": 9.3,
      "potassium": 7.6,
      "calcium": 0.4,
      "iron": 1.4,
      "magnesium": 6.4,
      "phosphorus": 1.8,
      "zinc": 1.4,
      "vitaminC": 9.7,
      "vitaminA": 0.3,
      "vitaminD": 0,
      "vitaminE": 0.7,
      "vitaminK": 0.4,
      "thiamin": 2.6,
      "riboflavin": 5.6,
      "niacin": 4.2,
      "vitaminB6": 21.6,
      "folate": 5,
      "vitaminB12": 0
    },
    "dietaryFlags": {
      "highProtein": false,
      "goodSourceOfProtein": false,
      "highFiber": false,
      "goodSourceOfFiber": false,
      "lowSodium": true,
      "lowFat": true,
      "lowSaturatedFat": true,
      "lowCholesterol": true,
      "lowCalorie": false
    }
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Other ways to use Nutrition Skill

Set up Nutrition Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Related

More in Food: