What is mercadopago-tool CLAUDE.md?

Project instructions for an open-source Mercado Pago connector, a tool for creating payment links, managing payments, and issuing refunds through AI agents, Telegram, or WhatsApp. They document its Node.js and TypeScript setup, commands, tests, and architecture.

Use them when developing or maintaining the connector, running its test and build commands, starting its bots or servers, checking types, or working with its core and channel modules.

They give an agent the project context needed to work safely and consistently. The instructions also identify how to build, test, type-check, run, and containerize the project.

How dan1d/mercadopago-tool configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dan1d/mercadopago-tool. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dan1d/mercadopago-tool/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dan1d/mercadopago-tool

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dan1d/mercadopago-tool/claude-md/github.svg)](https://agentmods.dev/instructions/dan1d/mercadopago-tool/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dan1d/mercadopago-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/dan1d/mercadopago-tool/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dan1d/mercadopago-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/dan1d/mercadopago-tool/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 783 This file is loaded in full into every session.

When invoked 783 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00783	$0.00783
Opus 5.5	$0.00313	$0.00313
Sonnet 5.5	$0.00157	$0.00157
Haiku 4.5	$0.00078	$0.00078

Measured 2mo ago against content hash 485199de7822, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mercadopago-tool CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mercadopago-tool

Project overview

Open-source Mercado Pago tool connector for AI agents and chat interfaces. Enables payment link generation, payment management, and refunds from multiple channels (AI agents, Telegram, WhatsApp).

Tech stack

Runtime: Node.js 18+ (native fetch, no axios/node-fetch)
Language: TypeScript strict mode
Module system: Node16 (ESM with .js extensions in imports)
Tests: vitest (124 tests across 11 suites)
No web framework — uses Web Standard Request/Response API

Key commands

npm test              # Run all tests (vitest)
npm run build         # Compile TypeScript → dist/
npm run bot           # Start Telegram bot
npm run whatsapp      # Start WhatsApp webhook server
npm start             # Start unified server (src/server.ts)
npm run dev:server    # Start server in dev mode (tsx watch)
npm run integration   # Run integration test against real MP API
npx tsc --noEmit      # Type-check without building
docker compose up -d  # Run via Docker

Architecture

The project has a flat core + channel modules pattern:

Core (src/client.ts, src/actions.ts, src/schemas.ts, src/errors.ts) — Mercado Pago API client and 5 actions
Webhook (src/webhook.ts) — IPN handler with HMAC-SHA256 validation
MCP Server (src/mcp-server.ts) — Model Context Protocol server for AI agents
Telegram (src/telegram-bot.ts) — Telegram bot using node-telegram-bot-api
WhatsApp (src/whatsapp/) — WhatsApp Business Cloud API module (4 files)
Unified Server (src/server.ts) — Single HTTP entry point mounting all webhooks + health endpoint
Index (src/index.ts) — Re-exports everything, provides createMercadoPagoTools() registry

Code conventions

All imports use .js extension (Node16 module resolution)
Errors are typed via MercadoPagoError class with .isUnauthorized, .isNotFound, .isRateLimited
Actions take (client, params) pattern — client is injected, not global
Tests mock fetch globally with vi.stubGlobal("fetch", mockFetch) — no real API calls
Bot/channel messages are in Spanish (LATAM merchants target audience)
Webhook handlers are framework-agnostic: (Request) => Promise<Response>

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 72 lines · 783 tokens per session scan A 485199de7822

Subscribe to this mod's changes

mercadopago-tool CLAUDE.md is an instructions file published in the GitHub repository dan1d/mercadopago-tool (3 stars, last pushed 8mo ago), licensed MIT. It adds 783 tokens to every session, about $0.0031 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

E-commerce Finance and fintech

mercadopago-tool CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mercadopago-tool CLAUDE.mddan1d/mercadopago-tool	Instructions file	3	8mo ago	MIT	A	783	Claude Code
vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetags	Instructions file	25	today	MIT	A	553	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

mercadopago-tool: Instructions file for Claude Code