TACO Brasil

io.github.ianhudsonaiPublished by GitHub account ianhudsonaiv0.1.1Updated Oct 30, 2026

Tabela Brasileira de Composição de Alimentos (TACO): 597 foods, nutrients and household measures

VerifiedSTDIODesktop onlyLocation & LifestyleData & Analytics

Overview

AI-generated overview

Local MCP server that gives an assistant exact TACO Brazilian food composition data: search 597 foods, read nutrients, sum meals and convert household measures.

What you can do
  • Search foods by Portuguese name, accent-insensitive and tolerant of regional synonyms, returning ids and kcal per 100 g
  • Read full nutrient composition of one food by id, per 100 g or scaled to grams, with trace and unpublished values flagged rather than zeroed
  • Sum nutrients across a list of foods given in grams or household measures, flagging totals as lower bounds when data is missing
  • Compare 2 to 10 foods side by side on chosen nutrients per 100 g
  • Convert Brazilian household measures such as spoons, units and slices to grams, reporting candidates or non-coverage instead of guessing
  • Health check that returns the server name, version and data source citation
When to use it
Useful when an assistant should answer nutrition questions about Brazilian foods with table values instead of recalled estimates: single-food lookups, scaled portions, meal totals and food comparisons. Also helps when household measures like spoons or slices must be turned into grams.
Requirements
Runs locally over stdio via npx, requiring Node.js 20 or newer; configured in Claude Desktop, Claude Code, Cursor or similar clients. No accounts, API keys or environment variables are declared. An optional HTTP mode exists for clients that cannot reach a local process.
Before you install
All tools are read-only and no credentials are requested. Values the table does not publish come back as null or as a trace marker, and meal totals can be lower bounds, so results should not be read as complete. Household weights are population averages, not measurements of a specific plate, and only part of the foods are covered for fatty acids, amino acids and household measures.

Installation

In SourceWeft

  1. Open TACO Brasil in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

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

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

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?"

Remote HTTP and ChatGPT

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

bash
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

ToolWhat it does
search_foodFind foods by Portuguese name (accent-insensitive, tolerates typos, knows regional names such as aipim/macaxeira/mandioquinha). Returns ids and kcal per 100 g.
get_nutrientsFull 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_acidsFatty 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_acidsAmino 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_mealSum 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_foods2 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.
pingHealth 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).

CategoryHaiku 5.5 without / withSonnet 5.5 without / withOpus 5.5 without / with
Direct lookup12/18 / 18/1816/18 / 18/1818/18 / 18/18
Scaled grams9/9 / 9/99/9 / 9/99/9 / 9/9
Comparison3/3 / 3/33/3 / 3/33/3 / 3/3
Household units3/6 / 6/61/6 / 6/63/6 / 6/6
Whole meal3/3 / 3/30/3 / 3/33/3 / 3/3
Honesty1/6 / 6/63/6 / 6/63/6 / 6/6
Total31/45 / 45/4532/45 / 45/4539/45 / 45/45
Cost of 90 runsUS$ 0.22US$ 3.10US$ 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

bash
npm installnpm run buildnpm testnpm run inspect   # MCP Inspector against dist/server.jsnpm 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.

Source: README.md at commit 46c7295

Tools

6

ping

Ping

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

Parametersecho

search_food

Search foods in TACO

Find foods in the Brazilian TACO table (597 items, per 100 g) by name in Portuguese. Accent-insensitive; knows a few synonyms (aipim, macaxeira, pão de sal). Returns ids to use with get_nutrients. Restaurant dishes and brands are mostly absent.

Parameterslimitqueryrequired

get_nutrients

Get nutrients of a food

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.

Parametersgramsfood_idrequirednutrients

calc_meal

Calculate the nutrients of a meal

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.

Parametersitemsrequirednutrients

compare_foods

Compare foods side by side

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.

Parametersfood_idsrequirednutrients

convert_household_measure

Convert a household measure to grams

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.

Parametersfood_idmeasurerequiredquantityfood_query

Version history

1
  1. v0.1.1LatestOct 30, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts