Skip to main content
Glama

Crear o leer BR Code Pix (copia e cola)

br-pix-brcode
Read-onlyIdempotent

Construye un BR Code Pix «copia e cola» (TLV EMVCo con GUI br.gov.bcb.pix, llave o URL dinámica, monto, txid y CRC16) o lee y revisa uno, según los manuales del Banco Central do Brasil. Solo formato; nunca afirma un pago. Cuándo: un cálculo de dinero, impuestos o matemática financiera tiene que ser exacto y reproducible (redondeo, centavos, tasas). No para: leer un payload QR EMVCo de comercio (emvco-qr-parse). Efectos secundarios: ninguno (solo lectura, sin red, sin estado guardado). Determinista: la misma entrada da la misma salida. Límites: entrada JSON de hasta 64 KB, 1 s por llamada, resultado de hasta 1 MB.

EN: Builds a Pix "copia e cola" BR Code (EMVCo TLV with GUI br.gov.bcb.pix, key or dynamic URL, amount, txid, CRC16-CCITT) or parses and checks one, following the Banco Central do Brasil manuals. Format only; it never claims a payment. When: a money, tax or financial-math result has to be exact and reproducible (rounding, cents, rates). [EN completo / full EN: inputSchema.description]

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "key": "123e4567-e12b-12d1-a456-426655440000",
      "merchant_city": "BRASILIA",
      "merchant_name": "Fulano de Tal"
    },
    "name": "br-pix-brcode"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoPix key (CPF, CNPJ, +55 phone, e-mail or random UUID key) (string; optional; up to 77 chars).
mccNoMerchant category code (string; optional; default "0000"; up to 4 chars; pattern ^\d{4}$).0000
urlNoDynamic location URL without https:// (instead of key) (string; optional; up to 77 chars).
txidNoTransaction id (letters and digits, max 25; "***" when none) (string; optional; default "***"; up to 25 chars; pattern ^(\*\*\*|[A-Za-z0-9]{1,25})$).***
actionNobuild a payload or parse one (optional; one of: build, parse; default "build").build
amountNoAmount in BRL (omit to let the payer type it) (number; optional; min 0.01; max 9999999999.99).
payloadNoBR Code to parse (string; optional; up to 512 chars).
single_useNoPoint of initiation 12 (single use) (boolean; optional; default false).
descriptionNoFree text for the payer (26-02) (string; optional; up to 72 chars).
postal_codeNoCEP (ID 61) (string; optional; up to 9 chars; pattern ^[0-9-]{1,9}$).
merchant_cityNoReceiver city (max 15 ASCII characters) (string; optional; up to 40 chars).
merchant_nameNoReceiver name (max 25 ASCII characters; accents are removed) (string; optional; up to 60 chars).

Output Schema

NameRequiredDescriptionDefault
crcNo
keyNo
urlNo
kindNo
noteNo
txidNo
validNo
amountNo
errorsNo
lengthNo
payloadNo
key_typeNo
merchantNo
warningsNo
single_useNo
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "key": "123e4567-e12b-12d1-a456-426655440000",
      +    "merchant_city": "BRASILIA",
      +    "merchant_name": "Fulano de Tal"
      +  }
      +]
  2. Added

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, yet the description adds real context beyond them: no network, no stored state, deterministic output, 'never claims a payment', and hard limits (64 KB input, 1 s per call, 1 MB result). The side-effect and determinism sentences partly restate the annotations, and it doesn't say what a failed parse returns, which keeps it off a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is front-loaded and tight, but the definition is bilingual (Spanish then the same content repeated in EN) which roughly doubles the length, and the 'Cuándo: … redondeo, centavos, tasas' boilerplate is irrelevant to this tool. Both cost real estate without adding information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 12 all-optional parameters, an output schema that covers return values, and rich annotations, the description supplies what's missing behaviourally: offline determinism, size/time limits, format-only scope, and a disambiguation pointer. The main hole is that the dual build/parse nature is only described narratively, with no note on what a parse produces or which fields matter per mode.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every one of the 12 parameters is already documented with types, patterns, defaults and constraints. The description mentions the domain concepts (key or dynamic URL, amount, txid, CRC16) but contributes no field-level meaning beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb+artifact: builds a Pix 'copia e cola' BR Code (EMVCo TLV with GUI br.gov.bcb.pix, key or dynamic URL, amount, txid, CRC16) or parses and checks one. It also draws a hard line against the neighbouring emvco-qr-parse tool, so an agent can pick correctly without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The negative guidance is explicit and useful ('No para: leer un payload QR EMVCo de comercio (emvco-qr-parse)'), but the positive 'Cuándo' clause is generic template boilerplate about money/tax/financial math being exact and reproducible — it doesn't describe when to build versus parse a BR Code. Nothing prevents an agent from calling it for a generic rounding task, and there's no guidance on which of the build/parse modes to select.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources