# TACO Brasil (npm · taco-br-mcp)

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

- Trust score: 81/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- npm · `taco-br-mcp`: 81/100 (this document), [markdown](https://verifymcp.io/servers/ianhudsonai-taco-br/taco-br-mcp.md), [page](https://verifymcp.io/servers/ianhudsonai-taco-br/taco-br-mcp)

## Channel facts

- Registry: `npm`
- Package: `taco-br-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to ianhudsonai/taco-br-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 740 tokens (~123/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the TACO Brasil MCP server?

TACO Brasil runs locally as an npm package, launched with npx -y taco-br-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

```json
{
  "servers": {
    "ianhudsonai-taco-br": {
      "command": "npx",
      "args": [
        "-y",
        "taco-br-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ianhudsonai-taco-br -- npx -y taco-br-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ianhudsonai-taco-br": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "taco-br-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ianhudsonai-taco-br --command npx --arg -y --arg taco-br-mcp
```

### Hermes

```yaml
mcp_servers:
  ianhudsonai-taco-br:
    command: "npx"
    args: ["-y", "taco-br-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ianhudsonai-taco-br": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "taco-br-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ianhudsonai-taco-br -t stdio -c npx -a -y taco-br-mcp
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-30 (score 81)

First indexed and scored.

## MCP tools (6)

### `ping` (~42 tokens)

Ping

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

Input parameters:

- `echo` (string): Optional text to echo back in the message.

Output parameters:

- `ok` (boolean): Always true when the server is alive.
- `server` (string): Server name.
- `source` (string): Citation for the data this server exposes.
- `version` (string): Server version.

### `search_food` (~112 tokens)

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.

Input parameters:

- `limit` (integer): Maximum number of results (default 10).
- `query` (string, required): Food name in Portuguese, e.g. "feijão carioca cozido" or "pao de queijo".

Output parameters:

- `query` (string): The query as received.
- `results` (array): Best matches first.
- `source` (string): Citation for the data.
- `total_matches` (integer): How many foods in the table match the query.

### `get_nutrients` (~132 tokens)

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.

Input parameters:

- `food_id` (integer, required): TACO food number, as returned by search_food.
- `grams` (number): Quantity in grams of edible portion. Omit for the table basis of 100 g.
- `nutrients` (array): Nutrient keys to return (e.g. "energy_kcal", "protein_g", "iron_mg"). Omit for all.

Output parameters:

- `basis_grams` (number): Quantity the amounts refer to, in grams of edible portion.
- `food` (object)
- `not_analyzed_nutrients` (array): Keys with no value in the TACO table; not zero.
- `notes` (array): Caveats about this food or this answer.
- `nutrients` (array): Requested nutrients, in table order.
- `scaled` (boolean): True when amounts were computed from the per-100 g table values for another quantity.
- `source` (string): Citation for the data.
- `trace_nutrients` (array): Keys reported as trace (Tr).

### `calc_meal` (~140 tokens)

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.

Input parameters:

- `items` (array, required): Foods in the meal. The same food may appear more than once.
- `nutrients` (array): Nutrient keys to total. Omit for energy, protein, fat, carbohydrate, fiber and sodium.

Output parameters:

- `complete` (boolean): True when every requested nutrient has data for every item (no total is a lower bound).
- `household_source` (string): Citation for the household measure weights; set when any item used one.
- `items` (array): The meal items in the order received.
- `notes` (array): Caveats about this answer.
- `source` (string): Citation for the data.
- `total_grams` (number): Sum of the item quantities.
- `totals` (array): One entry per requested nutrient, in table order.

### `compare_foods` (~104 tokens)

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.

Input parameters:

- `food_ids` (array, required): TACO food numbers to compare, as returned by search_food.
- `nutrients` (array): Nutrient keys to compare. Omit for energy, protein, fat, carbohydrate, fiber and sodium.

Output parameters:

- `basis` (string): Quantity all values refer to.
- `foods` (array): The foods compared, in the order received.
- `notes` (array): Caveats about this answer.
- `nutrients` (array): One row per requested nutrient, in table order.
- `source` (string): Citation for the data.

### `convert_household_measure` (~210 tokens)

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.

Input parameters:

- `food_id` (integer): TACO food number, as returned by search_food. Preferred over food_query.
- `food_query` (string): Food name in Portuguese, used only when food_id is not given; must match exactly one food.
- `measure` (string, required): Household measure in Portuguese, e.g. "colher de sopa", "unidade", "fatia", "concha", "copo americano".
- `quantity` (number): How many of the measure (default 1; may be fractional, e.g. 0.5).

Output parameters:

- `available_measures` (array): Measures known for this food (status unknown_measure).
- `candidates` (array): Foods matching the query (status ambiguous_food), best first.
- `food` (object): The resolved food (not set for ambiguous_food / no_food_match).
- `grams` (number): quantity x grams_per_measure (status ok).
- `grams_per_measure` (number): Weight of one measure in grams (status ok).
- `household_source` (string): Citation for the household measure weights.
- `measure` (object): The matched household measure (status ok).
- `notes` (array): Caveats and next steps.
- `quantity` (number): How many of the measure (status ok).
- `source` (string): Citation for the nutrient table.
- `status` (string): ok: grams computed. ambiguous_food: the query matched several foods, pick an id from candidates. no_food_match: no food found. no_household_data: this food has no curated household measures, ask for…

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ianhudsonai-taco-br/taco-br-mcp#diagnostics

## Score history

- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 81
- 2026-10-31: 81
- 2026-10-30: 81

## Common questions

### What is the TACO Brasil MCP server?

TACO Brasil is an MCP server listed in the public MCP registry as io.github.ianhudsonai/taco-br. Tabela Brasileira de Composição de Alimentos (TACO): 597 foods, nutrients and household measures. This page covers its npm package (taco-br-mcp).

### Is the TACO Brasil MCP server safe to use?

TACO Brasil scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TACO Brasil MCP server expose?

TACO Brasil exposes 6 tools: ping, search_food, get_nutrients, calc_meal, compare_foods, convert_household_measure. Their descriptions and schemas cost roughly 740 tokens of context every time the server is loaded.

### Is the TACO Brasil MCP server still maintained?

TACO Brasil is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the TACO Brasil MCP server under?

TACO Brasil declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/taco-br-mcp
- Socket report: https://socket.dev/npm/package/taco-br-mcp
- Repository: https://github.com/ianhudsonai/taco-br-mcp
- Changelog RSS feed: https://verifymcp.io/servers/ianhudsonai-taco-br/taco-br-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ianhudsonai-taco-br/taco-br-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ianhudsonai-taco-br/taco-br-mcp