Skip to main content
Glama

taco-br-mcp

MCP server that lets an AI assistant answer with exact numbers from the TACO — Tabela Brasileira de Composição de Alimentos, 4ª ed. (NEPA/UNICAMP, 2011) — instead of guessing. 597 Brazilian foods, 26 nutrients, per 100 g of edible portion, plus household measures ("2 colheres de sopa", "1 unidade") from the IBGE POF.

Em português: servidor MCP com a Tabela Brasileira de Composição de Alimentos (TACO). Busca alimentos, devolve nutrientes, soma refeições e converte medidas caseiras em gramas. Toda resposta cita a fonte, e o que a tabela não traz vem como "sem dado", nunca como zero.

stdio by default, for Claude Desktop, Claude Code, Cursor and other local MCP clients. It also serves Streamable HTTP (--http), which is how ChatGPT connects: see Remote HTTP and ChatGPT.

Install

Requires Node.js 20 or newer.

Claude Code

claude mcp add taco-br -- npx -y taco-br-mcp

Claude Desktop (claude_desktop_config.json) and Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "taco-br": { "command": "npx", "args": ["-y", "taco-br-mcp"] }
  }
}

Then ask, for example: "Quantas kcal tem uma refeição de 4 colheres de sopa de arroz, 100 g de feijão carioca e 100 g de peito de frango grelhado?"

Related MCP server: indian-food-nutrition-mcp

Remote HTTP and ChatGPT

ChatGPT cannot reach a server running on your PC, so the same tools are available over Streamable HTTP:

npx -y taco-br-mcp --http   # http://127.0.0.1:3000/mcp

A public instance runs at https://taco-br-mcp.taco-br-mcp.workers.dev/mcp (open, no login, rate limited; best effort, no uptime promise). The repository also ships a Cloudflare Workers deployment (free plan, open access, per-IP rate limit). Step-by-step deploy and the ChatGPT connector setup (Settings → Apps & Connectors, developer mode, authentication "No authentication") are in docs/remote.md.

Tools

Tool

What it does

search_food

Find foods by Portuguese name (accent-insensitive, tolerates typos, knows regional names such as aipim/macaxeira/mandioquinha). Returns ids and kcal per 100 g.

get_nutrients

Full composition of one food by id, per 100 g or scaled to a number of grams. Trace (Tr) is {"trace":true} and a value the table does not publish is null, never 0.

get_fatty_acids

Fatty acid profile of one food (saturated, mono/polyunsaturated, omega-3 and -6, EPA, DHA, trans, individual acids). Only 423 of 597 foods are in that TACO table; for the others it says available: false, not zero.

get_amino_acids

Amino acid profile of one food (lysine, leucine, tryptophan...). TACO has it for only 26 foods; for any other it says so and lists the 26.

calc_meal

Sum nutrients over [{food_id, grams}] or [{food_id, household_measure, quantity}]. A total is flagged is_lower_bound (and the foods without data are named) when some item has no data for that nutrient.

compare_foods

2 to 10 foods side by side on chosen nutrients, per 100 g. Missing data stays null.

convert_household_measure

"2 colheres de sopa" of a food to grams, from the IBGE POF table through a hand-curated mapping (204 foods so far). Ambiguous food names return candidates; uncovered foods or measures are reported, never guessed.

ping

Health check.

All tools are read-only. Every response cites TACO 4ª ed. (NEPA/UNICAMP, 2011).

How it treats missing data

  • Tr (trace, below the quantification limit) is {"trace": true}, never 0.

  • A value the table does not publish is null and shown as "sem dado na TACO", never 0. The source marks these cells in three ways (NA, * for "analyses under re-evaluation", or blank); the processed CSV merges them, so the server does not tell them apart. Whole milk, for example, has no published energy or protein.

  • Fatty and amino acids come from separate TACO tables that cover only part of the foods (423 and 26 of 597). A food outside the table gets available: false, never a row of zeros. In the amino acid table the TACO prints 0,00 for amounts under 0.005 g/100 g; that is a published value (shown as 0 or a small number), not missing data.

  • calc_meal totals are lower bounds when an item lacks data for a nutrient: the response says which foods are missing.

  • Household weights are POF/IBGE averages, not your plate. Only foods and measures whose POF description matches the food were mapped; anything else is reported as not covered.

Mini-evaluation

15 questions about the TACO, answered by claude -p with and without the server, 3 repetitions each (90 runs per model, 30 October 2026), on three models. A numeric answer is correct when it is within 5% of the table value; for the two "honesty" questions it is correct only if it says the TACO does not publish the value (whole milk energy) or that the total is a minimum (fiber of a meal that includes chicken, which has no fiber value).

Category

Haiku 5.5 without / with

Sonnet 5.5 without / with

Opus 5.5 without / with

Direct lookup

12/18 / 18/18

16/18 / 18/18

18/18 / 18/18

Scaled grams

9/9 / 9/9

9/9 / 9/9

9/9 / 9/9

Comparison

3/3 / 3/3

3/3 / 3/3

3/3 / 3/3

Household units

3/6 / 6/6

1/6 / 6/6

3/6 / 6/6

Whole meal

3/3 / 3/3

0/3 / 3/3

3/3 / 3/3

Honesty

1/6 / 6/6

3/6 / 6/6

3/6 / 6/6

Total

31/45 / 45/45

32/45 / 45/45

39/45 / 45/45

Cost of 90 runs

US$ 0.22

US$ 3.10

US$ 5.78

Reading: with the server all three models got 45/45. Without it they score 31 to 39 out of 45, and the failures differ by model. Haiku gives remembered values that are wrong for single foods (vitamin C in banana prata, iron in cooked lentils), labels them as unverified, and does not flag the fiber total of the meal as a minimum. Sonnet mostly answers "no data" on household measures and meals. Opus remembers most single values and still guesses unit weights (2 boiled eggs). All three, in all 3 runs, answer 61 kcal for whole milk, a value the TACO does not publish. One side effect: Haiku with the server repeated the TACO citation in only 13 of 45 answers (the tool output always carries it); Sonnet and Opus did it in 45 of 45. Limits: 15 questions, 3 repetitions, rule-based scoring (the 5% tolerance accepted one no-MCP Sonnet answer with a wrong rice value that landed near the right sum). Questions, answer key and raw answers are in eval/ (one folder per model); to repeat: npm run build && node eval/run.mjs --model claude-haiku-5-5 && node eval/score.mjs --all --detail.

Development

npm install
npm run build
npm test
npm run inspect   # MCP Inspector against dist/server.js
npm run build:data -- --fetch   # regenerate data/ from the pinned upstream CSVs

Never write to stdout (console.log): it is the protocol channel. Use console.error. See AGENTS.md for the project rules.

Data & license

Code: MIT. Nutritional data: TACO 4ª ed., NEPA/UNICAMP (2011). Household-measure weights: Fonte: IBGE, POF 2008-2009, Tabela de Medidas Referidas para os Alimentos Consumidos no Brasil — the grams are IBGE's, unchanged; the mapping between TACO and POF foods was curated by this project, which is responsible for it. See NOTICE.md for sources, processing and pinned versions. If you use this in research, see CITATION.cff. Not medical or nutritional advice.

Available Tools

8 tools
calc_mealCalculate the nutrients of a mealA
Read-only

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.

Inputs: items (required), nutrients. Returns: items, notes, source, totals, +3 more

compare_foodsCompare foods side by sideA
Read-only

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.

Inputs: food_ids (required), nutrients. Returns: basis, foods, notes, source, +1 more

convert_household_measureConvert a household measure to gramsA
Read-only

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.

Inputs: measure (required), food_id, quantity, food_query. Returns: food, grams, notes, source, +7 more

get_amino_acidsGet amino acid profile of a foodA
Read-only

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).

Inputs: food_id (required), grams, nutrients. Returns: food, notes, scaled, source, +6 more

get_fatty_acidsGet fatty acid profile of a foodA
Read-only

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.

Inputs: food_id (required), grams, nutrients. Returns: food, notes, scaled, source, +6 more

get_nutrientsGet nutrients of a foodA
Read-only

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.

Inputs: food_id (required), grams, nutrients. Returns: food, notes, scaled, source, +4 more

pingPingA
Read-only

Health check for the taco-br server. Returns the server name, version and the data source citation.

Inputs: echo. Returns: ok, server, source, version

search_foodSearch foods in TACOA
Read-only

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.

Inputs: query (required), limit. Returns: query, source, results, total_matches

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 8 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables Claude to search and access detailed nutritional information from the USDA's FoodData Central database.
      11
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that lets you log meals through Claude (and soon ChatGPT) in plain language, using India's official food composition data (IFCT 2017) plus USDA, enabling accurate calorie and macro tracking for Indian dishes with household units and photo logging.
      75 npm
      2
      AGPL 3.0
    • A
      license
      B
      quality
      B
      maintenance
      A local-first nutrition MCP server for food search, barcode lookup, meal estimation, intake logging, hydration, and nutrition coaching workflows.
      46
      180 npm
      11
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for Japanese food nutrition data, enabling bilingual JP/EN lookups across konbini, restaurant chains, and grocery brands.
      6
      107 npm
      2
      MIT