taco-br-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pingA | Health check for the taco-br server. Returns the server name, version and the data source citation. |
| search_foodA | Find foods in the Brazilian TACO table (597 items, per 100 g) by name in Portuguese. Accent-insensitive; tolerates typos; knows regional names (aipim, macaxeira, pão de sal, mandioquinha). Returns ids to use with get_nutrients. Restaurant dishes and brands are mostly absent. |
| get_nutrientsA | Full composition of one TACO food by id (from search_food), per 100 g or scaled to a quantity in grams. Missing data is reported as null (not analyzed) or {"trace":true}, never as 0. |
| calc_mealA | Sum nutrients over a list of TACO foods (ids from search_food). Each item has either grams or a household_measure with quantity (e.g. "colher de sopa" x 2, covered foods only; see convert_household_measure). Totals are lower bounds when an item has no data for a nutrient: the response says which. Defaults to energy, protein, fat, carbohydrate, fiber and sodium. |
| compare_foodsA | Compare 2 to 10 TACO foods (ids from search_food) on chosen nutrients, per 100 g of edible portion. Missing data stays null or {"trace":true}; do not rank a food with null as having less. |
| convert_household_measureA | Convert a Brazilian household measure (e.g. 2 colheres de sopa, 1 unidade, 1 fatia) of a TACO food to grams, using the IBGE POF table through a hand-curated mapping. Only some foods are covered; it never guesses: on ambiguity it returns candidates, and for uncovered foods or measures it says so. Pass food_id (from search_food) or food_query. |
| get_fatty_acidsA | Fatty acid profile (saturated, mono/polyunsaturated, omega-3/6, EPA, DHA, trans, and individual acids) of one TACO food by id, per 100 g or scaled to grams. Only 423 of 597 foods have it; others return available:false (not zero). Tr is {"trace":true}, missing is null. |
| get_amino_acidsA | Amino acid profile (lysine, leucine, tryptophan, etc.) of one TACO food by id, per 100 g or scaled to grams. TACO only has it for 26 foods; others return available:false with the list of foods that do (not zero). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool has a clearly separate role: search, single-food composition, meal summation, comparison, unit conversion, fatty acids, amino acids, and health check. The only mild overlap is between get_nutrients ('full composition') and the specialized get_fatty_acids/get_amino_acids tools, but descriptions clarify that the specialized ones expose individual acids and coverage limits.
Names are consistently snake_case and mostly verb_noun (search_food, get_nutrients, calc_meal, compare_foods, convert_household_measure, get_fatty_acids, get_amino_acids). The lone outlier is 'ping', which is a conventional health-check name but breaks the verb_noun pattern.
Eight tools is well-scoped for a food-composition server: lookup, detail, aggregation, comparison, conversion, two specialized nutrient profiles, and a health check. Every tool earns its place with no obvious filler.
The core lifecycle (search → inspect → convert measure → sum/compare) is fully covered, and the specialized profiles plus explicit missing-data semantics are thoughtful. Minor gaps exist: no way to browse/list all foods or categories, and no nutrient-metadata or multi-food bulk export operation.