Forkmate

Official14 tools

by shawnazar

Free AI calorie & macro tracker: tell your AI what you ate and it logs it to your private food diary

MCP Server: ai.forkmate/forkmate

The MCP server ai.forkmate/forkmate provides an integration for logging what you eat by talking to an AI assistant. It is described as capturing calories and macros, and is listed with a total of 12 tools available for use.

🛠️ Key Features

Logs food intake via an AI assistant conversation
Records calories and macros
Exposes 12 tools

🚀 Use Cases

Track calories and macro nutrition from conversational inputs
Maintain food logs based on AI assistant interactions

⚡ Developer Benefits

Standard MCP tool surface for consuming nutrition logging functionality
Tool count is available (12) for integration planning

⚠️ Limitations

Only the “calories and macros” logging behavior is described; no additional capabilities are specified.

Topics

calorie-trackerfood-diarymcpmcp-servermodel-context-protocolnutritionai-assistantcalorie-counterchatgptclaudecursorfood-trackerhealthmacro-trackermyfitnesspal-alternativeremote-mcp

Captured live from the server via tools/list.

whoami

Diagnostic: confirms that this connection is signed in to a Forkmate account. Returns no account id, email or other identifier.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_day

Read the user's food diary for one day: its entries, each listed with its `id` and each food with its item_index, quantity and macros, and calorie/macro totals. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters1

local_date

string

optional

YYYY-MM-DD; defaults to today.

Raw schema

{
  "type": "object",
  "properties": {
    "local_date": {
      "type": "string",
      "description": "YYYY-MM-DD; defaults to today."
    }
  }
}

get_range

Read the user's food diary across a date range, with per-day calorie/macro totals and each entry listed with its `id`. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters2

start	string	required	YYYY-MM-DD (inclusive).
end	string	required	YYYY-MM-DD (inclusive).

Raw schema

{
  "type": "object",
  "properties": {
    "start": {
      "type": "string",
      "description": "YYYY-MM-DD (inclusive)."
    },
    "end": {
      "type": "string",
      "description": "YYYY-MM-DD (inclusive)."
    }
  },
  "required": [
    "start",
    "end"
  ]
}

get_preferences

Read the user's food profile: diet style, allergies (a structured list of the major US allergens), foods they like, foods they dislike, and a typical-portion note. Allergies are self-reported and not a safety guarantee; the response includes an allergy_disclaimer. Likes and dislikes are taste preferences, not allergies or restrictions.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

update_preferences

Edit the user's food profile: add or remove foods they like or dislike, add or remove allergies from the major US allergen list, or set their diet style. Only the fields sent change. A removal matches a saved name in any casing; a name that matches nothing is reported in `not_found` and nothing else is affected. Adding a food to likes takes it off dislikes, and the reverse. Lists hold up to 50 foods of up to 80 characters each. The reply is the whole updated profile. It saves what the user states about their own tastes and allergies, not inferences from the diary. Every call carries `user_approved: true`, meaning the user saw this exact change and said yes to it; a call without it changes nothing and returns the change for the user to approve. A user stating a preference (e.g. 'I dislike olives') has not approved saving it: approval is a later message agreeing to the change as proposed. The server cannot verify that a person gave the approval. Removals work without health-data consent and then return only what was removed. The user can see and edit the same profile in Forkmate's Settings.

Parameters8

add_likes	array	optional	Foods the user enjoys, e.g. 'salmon'.
remove_likes	array	optional	Foods to take off the likes list.
add_dislikes	array	optional	Foods the user dislikes, e.g. 'mushrooms'. A taste preference, not an allergy or a restriction.
remove_dislikes	array	optional	Foods to take off the dislikes list.
add_allergies	array	optional	Allergens to add, from the major US allergen list.
remove_allergies	array	optional	Allergens to remove.
diet_style	string	optional	The user's diet style; 'none' clears it.
user_approved	boolean	required	True only when the previous assistant message proposed this exact change and the user's latest message agreed to it. The user stating the preference itself is not approval.

Raw schema

{
  "type": "object",
  "properties": {
    "add_likes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Foods the user enjoys, e.g. 'salmon'."
    },
    "remove_likes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Foods to take off the likes list."
    },
    "add_dislikes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Foods the user dislikes, e.g. 'mushrooms'. A taste preference, not an allergy or a restriction."
    },
    "remove_dislikes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Foods to take off the dislikes list."
    },
    "add_allergies": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "milk",
          "eggs",
          "fish",
          "shellfish",
          "tree_nuts",
          "peanuts",
          "wheat",
          "soy",
          "sesame"
        ]
      },
      "description": "Allergens to add, from the major US allergen list."
    },
    "remove_allergies": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "milk",
          "eggs",
          "fish",
          "shellfish",
          "tree_nuts",
          "peanuts",
          "wheat",
          "soy",
          "sesame"
        ]
      },
      "description": "Allergens to remove."
    },
    "diet_style": {
      "type": "string",
      "enum": [
        "omnivore",
        "vegetarian",
        "vegan",
        "pescatarian",
        "keto",
        "none"
      ],
      "description": "The user's diet style; 'none' clears it."
    },
    "user_approved": {
      "type": "boolean",
      "description": "True only when the previous assistant message proposed this exact change and the user's latest message agreed to it. The user stating the preference itself is not approval."
    }
  },
  "required": [
    "user_approved"
  ],
  "additionalProperties": false
}

get_usual_foods

Read what the user usually and recently eats. `usual` lists their most-logged foods, most frequent first, each with how many times it was logged, the date last eaten, the meal it is usually logged under, and the portion and macros from the last time. `recent` lists each distinct food from the last seven days with the date last eaten, its meal and how many times. An optional `meal` narrows both lists to one meal. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters1

meal

string

optional

Only foods logged under this meal.

Raw schema

{
  "type": "object",
  "properties": {
    "meal": {
      "type": "string",
      "enum": [
        "breakfast",
        "lunch",
        "dinner",
        "snack",
        "other"
      ],
      "description": "Only foods logged under this meal."
    }
  },
  "additionalProperties": false
}

log_meal

Add a meal to the user's food diary: one or more food items, each with an optional quantity and macros, plus an optional meal label, date, note and provenance `source`. The reply names the new entry's `id` and `local_date`, which identify it for a later edit or deletion. A restaurant meal's numbers depend most on the restaurant, the specific menu item, its size and its add-ons (cheese, fries, sauce, dressing); a bare dish name is logged as a typical serving. When the user names one of their saved recipes ("my chicken and rice", "half my chili"), send their words as one item's name, with any amount in quantity; Forkmate logs the recipe's own foods and numbers in its place. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters7

items	array	required	The foods in this meal, one entry per food.
meal	string	optional	Which meal of the day this was.
at	string	optional	ISO-8601 instant the meal was eaten; defaults to now.
local_date	string	optional	YYYY-MM-DD diary date; defaults to the user's local date (from their timezone).
note	string	optional	Optional free-text note stored with the meal, e.g. 'post-run'.
source	string	optional	Optional provenance for these items: the `source` label of the food-database candidate they came from ('USDA', 'Open Food Facts', 'Forkmate' or 'product label'), or 'estimate'. Defaults to 'estimate'; unrecognized values are recorded as an estimate.
said	string	optional	Optional. The user's own words describing this meal, verbatim (e.g. 'a pint of IPA and wings at the bar'). Only the meal description — not other parts of the conversation.

Raw schema

{
  "type": "object",
  "properties": {
    "items": {
      "type": "array",
      "minItems": 1,
      "description": "The foods in this meal, one entry per food.",
      "items": {
        "type": "object",
        "required": [
          "name"
        ],
        "properties": {
          "name": {
            "type": "string",
            "description": "What the food is, e.g. 'scrambled eggs' or 'Greek yogurt, plain'."
          },
          "quantity": {
            "type": "string",
            "description": "Portion as a display label, e.g. '3', '1 cup' or '2 × 1 frank (96 g)'. Display only: the server stores macros exactly as sent and does not re-scale them."
          },
          "barcode": {
            "type": "string",
            "description": "The package's UPC/EAN barcode, when the food came from a barcode lookup."
          },
          "macros": {
            "type": "object",
            "description": "Estimated nutrition for the portion eaten. Omitted fields are looked up from the food databases.",
            "properties": {
              "kcal": {
                "type": "number",
                "description": "Energy for the whole portion eaten, in kilocalories (not per 100 g)."
              },
              "protein_g": {
                "type": "number",
                "description": "Protein for the whole portion eaten, in grams."
              },
              "carb_g": {
                "type": "number",
                "description": "Total carbohydrate for the whole portion eaten, in grams."
              },
              "fat_g": {
                "type": "number",
                "description": "Total fat for the whole portion eaten, in grams."
              }
            }
          },
          "caffeine_mg": {
            "type": "number",
            "description": "Optional caffeine content of this item, in milligrams (e.g. ~95 for a mug of brewed coffee)."
          },
          "fluid_ml": {
            "type": "number",
            "description": "Optional fluid/hydration volume of this item, in millilitres (e.g. 240 for an 8 oz cup)."
          }
        }
      }
    },
    "meal": {
      "type": "string",
      "enum": [
        "breakfast",
        "lunch",
        "dinner",
        "snack",
        "other"
      ],
      "description": "Which meal of the day this was."
    },
    "at": {
      "type": "string",
      "description": "ISO-8601 instant the meal was eaten; defaults to now."
    },
    "local_date": {
      "type": "string",
      "description": "YYYY-MM-DD diary date; defaults to the user's local date (from their timezone)."
    },
    "note": {
      "type": "string",
      "description": "Optional free-text note stored with the meal, e.g. 'post-run'."
    },
    "source": {
      "type": "string",
      "enum": [
        "USDA",
        "Open Food Facts",
        "Forkmate",
        "product label",
        "estimate"
      ],
      "description": "Optional provenance for these items: the `source` label of the food-database candidate they came from ('USDA', 'Open Food Facts', 'Forkmate' or 'product label'), or 'estimate'. Defaults to 'estimate'; unrecognized values are recorded as an estimate."
    },
    "said": {
      "type": "string",
      "maxLength": 300,
      "description": "Optional. The user's own words describing this meal, verbatim (e.g. 'a pint of IPA and wings at the bar'). Only the meal description — not other parts of the conversation."
    }
  },
  "required": [
    "items"
  ]
}

update_meal

Correct a food already in the user's diary — its name, quantity, macros, caffeine or fluid — or change an entry's meal label or note. The entry is identified by `id` and `local_date`, and a food by its `item_index`. Only the fields sent change; macros are merged onto the existing values and overwritten in place, with no history kept. A new `quantity` sent without `macros` rescales the food's macros, caffeine and fluid by the new amount ÷ the old one when both are the same kind of amount (a weight, a volume or a count), so '150 g' to '300 g' doubles them; otherwise the macros stay as they were and the reply says so. An entry cannot be moved to another day. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters11

id	string	required	The entry id, shown with each entry in the reply text when a meal is logged or a day or range is read.
local_date	string	required	YYYY-MM-DD diary date of the entry.
item_index	number	optional	Which food in the entry's items[] to edit (0-based). Required when changing a food's name/quantity/macros/caffeine/fluid; omit for an entry-level change (meal/note).
name	string	optional	Corrected name of the food.
quantity	string	optional	Portion as stated, e.g. '2' or '1 cup'.
macros	object	optional	Corrected macros. Only the components included are changed.
caffeine_mg	number	optional	Corrected caffeine content, in milligrams.
fluid_ml	number	optional	Corrected fluid/hydration volume, in millilitres.
meal	string	optional	Move the entry to a different meal label.
note	string	optional	Replacement note for the entry.
said	string	optional	Optional. The user's own words describing this meal, verbatim (e.g. 'a pint of IPA and wings at the bar'). Only the meal description — not other parts of the conversation.

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The entry id, shown with each entry in the reply text when a meal is logged or a day or range is read."
    },
    "local_date": {
      "type": "string",
      "description": "YYYY-MM-DD diary date of the entry."
    },
    "item_index": {
      "type": "number",
      "description": "Which food in the entry's items[] to edit (0-based). Required when changing a food's name/quantity/macros/caffeine/fluid; omit for an entry-level change (meal/note)."
    },
    "name": {
      "type": "string",
      "description": "Corrected name of the food."
    },
    "quantity": {
      "type": "string",
      "description": "Portion as stated, e.g. '2' or '1 cup'."
    },
    "macros": {
      "type": "object",
      "description": "Corrected macros. Only the components included are changed.",
      "properties": {
        "kcal": {
          "type": "number",
          "description": "Corrected energy for the whole portion, in kilocalories."
        },
        "protein_g": {
          "type": "number",
          "description": "Corrected protein for the whole portion, in grams."
        },
        "carb_g": {
          "type": "number",
          "description": "Corrected total carbohydrate for the whole portion, in grams."
        },
        "fat_g": {
          "type": "number",
          "description": "Corrected total fat for the whole portion, in grams."
        }
      }
    },
    "caffeine_mg": {
      "type": "number",
      "description": "Corrected caffeine content, in milligrams."
    },
    "fluid_ml": {
      "type": "number",
      "description": "Corrected fluid/hydration volume, in millilitres."
    },
    "meal": {
      "type": "string",
      "enum": [
        "breakfast",
        "lunch",
        "dinner",
        "snack",
        "other"
      ],
      "description": "Move the entry to a different meal label."
    },
    "note": {
      "type": "string",
      "description": "Replacement note for the entry."
    },
    "said": {
      "type": "string",
      "maxLength": 300,
      "description": "Optional. The user's own words describing this meal, verbatim (e.g. 'a pint of IPA and wings at the bar'). Only the meal description — not other parts of the conversation."
    }
  },
  "required": [
    "id",
    "local_date"
  ]
}

delete_meal

Delete one food from a diary entry (by `item_index`), or the whole entry (without it). The entry is identified by `id` and `local_date`. Deletion is permanent, with no undo; deleting the last food removes the entry, and an `id` that matches no entry on that date returns a not-found error and deletes nothing. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters3

id	string	required	The entry id, shown with each entry in the reply text when a meal is logged or a day or range is read.
local_date	string	required	YYYY-MM-DD diary date of the entry.
item_index	number	optional	Which food to remove (0-based). Omit to delete the whole entry.

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The entry id, shown with each entry in the reply text when a meal is logged or a day or range is read."
    },
    "local_date": {
      "type": "string",
      "description": "YYYY-MM-DD diary date of the entry."
    },
    "item_index": {
      "type": "number",
      "description": "Which food to remove (0-based). Omit to delete the whole entry."
    }
  },
  "required": [
    "id",
    "local_date"
  ]
}

give_consent

Records the user's consent to Forkmate storing and processing their health-related data, as summarised in the consent text that a refused log reply shows. Valid only as the user's own explicit agreement given in this conversation; an assistant agreeing on the user's behalf is not consent. Stores the consent version, the time, the connected app and the user's words, then logs any meal that was waiting for consent. Withdrawal is in Forkmate Settings.

Parameters2

user_statement	string	required	The user's own words agreeing, as they replied, e.g. 'yes, I agree'.
version	string	required	The consent version shown to the user.

Raw schema

{
  "type": "object",
  "properties": {
    "user_statement": {
      "type": "string",
      "maxLength": 280,
      "description": "The user's own words agreeing, as they replied, e.g. 'yes, I agree'."
    },
    "version": {
      "type": "string",
      "enum": [
        "health_ack_v4"
      ],
      "description": "The consent version shown to the user."
    }
  },
  "required": [
    "user_statement",
    "version"
  ],
  "additionalProperties": false
}

search_foods

Search USDA FoodData Central, Open Food Facts and Forkmate's curated restaurant menus for a named food. Returns up to 5 candidates, each with macros per 100 g, a `source` label ('USDA', 'Open Food Facts', 'Forkmate' or 'product label', a packaged product's published label read from a cited page and not yet checked by Forkmate), and, when known, `serving_grams`/`serving_label` for one household serving. Curated chain-menu candidates include a `provenance` object that may carry a portion caveat. A query names a food (at least 2 letters, no wildcards); there is no paging. For a bare generic dish ("a burger", "coffee"), the reply also lists `details_that_change_it`: the details that change that dish's numbers most, such as where it is from, which item, its size and add-ons. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters2

query	string	required	Food to search, e.g. 'greek yogurt' or 'Chipotle chicken'. At least 2 letters; wildcards are not supported.
limit	number	optional	Max candidates to return (default and maximum 5).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Food to search, e.g. 'greek yogurt' or 'Chipotle chicken'. At least 2 letters; wildcards are not supported."
    },
    "limit": {
      "type": "number",
      "description": "Max candidates to return (default and maximum 5)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

lookup_barcode

Look up a packaged food by its UPC/EAN barcode in Open Food Facts. Returns macros per 100 g, a `source` label ('Open Food Facts'), and, when known, `serving_grams`/`serving_label` for one household serving. All calorie and macro values, including carbohydrates, are estimates from USDA FoodData Central, Open Food Facts, the user's own entry or an AI assistant's estimate — approximate, not lab-measured or specific to a package or batch, and not suitable for insulin dosing (including carb counting for a meal bolus), blood-glucose prediction or any other medical decision.

Parameters1

upc

string

required

UPC/EAN barcode, digits only (8–14 digits).

Raw schema

{
  "type": "object",
  "properties": {
    "upc": {
      "type": "string",
      "description": "UPC/EAN barcode, digits only (8–14 digits)."
    }
  },
  "required": [
    "upc"
  ],
  "additionalProperties": false
}

send_feedback

Sends the user's feedback about Forkmate to the Forkmate team: a bug, a food or calorie figure that looked wrong, trouble connecting, or an idea. A person on the Forkmate team reads the note together with the user's account email. It changes nothing in the diary. The note is kept in the user's own account and deleted with it.

Parameters3

message	string	required	The feedback, in the user's words (at most 4000 characters).
rating	string	optional	The user's thumbs up or down on Forkmate, when they gave one.
about	string	optional	What the note is about: logging (saving or editing meals), accuracy (a food or number that looked wrong), connect (connecting this AI app), or other.

Raw schema

{
  "type": "object",
  "properties": {
    "message": {
      "type": "string",
      "maxLength": 4000,
      "description": "The feedback, in the user's words (at most 4000 characters)."
    },
    "rating": {
      "type": "string",
      "enum": [
        "up",
        "down"
      ],
      "description": "The user's thumbs up or down on Forkmate, when they gave one."
    },
    "about": {
      "type": "string",
      "enum": [
        "logging",
        "accuracy",
        "connect",
        "other"
      ],
      "description": "What the note is about: logging (saving or editing meals), accuracy (a food or number that looked wrong), connect (connecting this AI app), or other."
    }
  },
  "required": [
    "message"
  ],
  "additionalProperties": false
}

get_notifications

Reads the user's Forkmate notifications, newest first: notices that something the user reported was fixed, Forkmate release notes (what's new), and account messages. Each one has a kind, a title, a body, an optional link, the day it arrived and whether it is unread, and the reply includes the unread count. Read-only: reading marks nothing as read. Notifications older than 180 days are not kept.

Parameters2

unread_only	boolean	optional	Only unread notifications. Defaults to false.
limit	integer	optional	How many to return, newest first (1 to 20, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "unread_only": {
      "type": "boolean",
      "description": "Only unread notifications. Defaults to false."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "description": "How many to return, newest first (1 to 20, default 10)."
    }
  },
  "additionalProperties": false
}

README.md5 KBView on GitHub

Forkmate — free AI calorie tracker MCP server (Claude, ChatGPT, Cursor)

Forkmate (forkmate.ai) is a free AI calorie and macro tracker you talk to. Tell your AI assistant what you ate, and it logs the meal with its calories, protein, carbs and fat to your private food diary. See the day in the web diary at app.forkmate.ai.

It is a hosted, remote MCP server. There is nothing to install or run: add one URL to your client and sign in.


Server URL	`https://mcp.forkmate.ai/`
Transport	Streamable HTTP
Auth	OAuth 2.1 with PKCE and dynamic client registration. Your client opens the sign-in when it first calls a tool
Price	Free. No paid tier, no trial, no card, no ads
Registry name	`ai.forkmate/forkmate` (`server.json`)
Setup guide	forkmate.ai/connect

Connect your AI

Claude (claude.ai and Claude Desktop)

Settings → Connectors → Add custom connector → paste https://mcp.forkmate.ai/ → sign in.

Claude Code

claude mcp add --transport http forkmate https://mcp.forkmate.ai/

ChatGPT

On a plan that offers developer mode, turn it on in ChatGPT's settings, create a developer-mode app with the URL https://mcp.forkmate.ai/, choose OAuth, and sign in.

Cursor

Click Add to Cursor above, or add this to ~/.cursor/mcp.json:

json

{
  "mcpServers": {
    "forkmate": { "url": "https://mcp.forkmate.ai/" }
  }
}

VS Code (GitHub Copilot)

Click Install in VS Code above, or add this to .vscode/mcp.json:

json

{
  "servers": {
    "forkmate": { "type": "http", "url": "https://mcp.forkmate.ai/" }
  }
}

Windsurf

Add this to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "forkmate": { "serverUrl": "https://mcp.forkmate.ai/" }
  }
}

Cline

MCP Servers → Remote Servers → name forkmate, URL https://mcp.forkmate.ai/, transport Streamable HTTP. AI agents installing it can follow llms-install.md.

Gemini CLI

Add this to ~/.gemini/settings.json:

json

{
  "mcpServers": {
    "forkmate": { "httpUrl": "https://mcp.forkmate.ai/" }
  }
}

Any other MCP client

Add a remote HTTP MCP server with the URL https://mcp.forkmate.ai/ and complete the sign-in.

Then tell your assistant what you ate ("two eggs and toast for breakfast"), or ask "how many calories today?".

Tools

Tool	What it does
`log_meal`	Log what you ate to your diary
`update_meal`	Correct an entry already in your diary
`delete_meal`	Remove an entry from your diary
`get_day`	Read one day's diary with calorie and macro totals
`get_range`	Read a date range with per-day totals
`get_preferences`	Read your food profile: likes, dislikes, allergies and diet style
`update_preferences`	Add or remove likes, dislikes and allergies, or set your diet style
`get_usual_foods`	Read the foods you eat most often and the last week's foods
`search_foods`	Search USDA FoodData Central and Open Food Facts
`lookup_barcode`	Look up a packaged food by barcode (Open Food Facts)
`whoami`	Confirm which account is connected

Prompts

log-meal · log-photo · today-so-far · hit-protein · week-review · import-myfitnesspal

Your client shows these as ready-made starting points.

Coming from MyFitnessPal?

Export your MyFitnessPal data for free and bring your history across: forkmate.ai/migrate-from-myfitnesspal.

Privacy

Every call is scoped to your own signed-in account. Forkmate stores your food diary, which is health-related data. Read the privacy policy and the consumer health data policy. Export and account deletion are self-serve in the app.

Calorie and macro values are estimates. They are not suitable for insulin dosing or any other medical decision.

About this repository

This repository holds the public server manifest and setup instructions. The server itself is hosted at mcp.forkmate.ai; its source is not public.

Made by Shawn Azar. Support: hello@forkmate.ai.

Install

Tools (14)

whoamiget_dayget_rangeget_preferencesupdate_preferencesget_usual_foodslog_mealupdate_meal

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.forkmate.ai/

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "forkmate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.forkmate.ai/"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

MCP Server: ai.forkmate/forkmate

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

whoami

get_day

get_range

get_preferences

update_preferences

get_usual_foods

log_meal

update_meal

delete_meal

give_consent

search_foods

lookup_barcode

send_feedback

get_notifications

Forkmate — free AI calorie tracker MCP server (Claude, ChatGPT, Cursor)

Connect your AI

Claude (claude.ai and Claude Desktop)

Claude Code

ChatGPT

Cursor

VS Code (GitHub Copilot)

Windsurf

Cline

Gemini CLI

Any other MCP client

Tools

Prompts

Coming from MyFitnessPal?

Privacy

About this repository

Install

Remote endpoint

Related servers