ForkMate MCP server

Add a food to the user's pantry, or replace its details if a food with the same name (any casing) is already there. Only `name` is required; macros for one serving, a serving label, a `source` and a note are optional. An unrecognized `source` is recorded as 'client' (the user's own estimate). Does not log a 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.

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.

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.

Read the user's pantry: the staple foods they keep on hand, separate from their diary. Each item has a name and, when saved, macros for one serving, a serving label, a `source` and a short note. A `source` is the user's own claim about where the macros came from, not a server-verified guarantee. 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.

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.

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.

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.

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. 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.

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.

Remove a food from the user's pantry by name. Affects the pantry only, not the food diary; removing a food that is not there succeeds as a no-op.

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' or '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. 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.

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.

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.

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