What is mcp-mercado-bitcoin CLAUDE.md?

Repository-specific instructions for an AI coding assistant working on an MCP server that connects language models to Mercado Bitcoin, a Brazilian cryptocurrency exchange. They describe the project, commands, architecture, and three-layer security model.

Building, testing, and changing the Mercado Bitcoin MCP server, including its API client, OAuth authentication, security checks, and tools for market data, accounts, and orders.

They give the assistant the context needed to work consistently in this codebase and reduce mistakes around commands, structure, authentication, and trading safety.

How RodrigoFlorencio86/mcp-mercado-bitcoin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RodrigoFlorencio86/mcp-mercado-bitcoin. 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/RodrigoFlorencio86/mcp-mercado-bitcoin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RodrigoFlorencio86/mcp-mercado-bitcoin

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/rodrigoflorencio86/mcp-mercado-bitcoin/claude-md/github.svg)](https://agentmods.dev/instructions/rodrigoflorencio86/mcp-mercado-bitcoin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rodrigoflorencio86/mcp-mercado-bitcoin/claude-md"><img src="https://agentmods.dev/badge/instructions/rodrigoflorencio86/mcp-mercado-bitcoin/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/rodrigoflorencio86/mcp-mercado-bitcoin/claude-md"><img src="https://agentmods.dev/badge/instructions/rodrigoflorencio86/mcp-mercado-bitcoin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 613 This file is loaded in full into every session.

When invoked 613 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	$0.00613	$0.00613
Opus 5	$0.00307	$0.00307
Sonnet 5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 10d ago against content hash 924599b1f973, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-mercado-bitcoin 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 10d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

MCP Server for Mercado Bitcoin (Brazilian crypto exchange). Exposes the full MB API v4 as 31 MCP tools for use by LLMs and AI agents.

Commands

npm run build — compile TypeScript to build/
npm run dev — watch mode (rebuild on changes)
npm start — run the compiled server
npx @modelcontextprotocol/inspector node build/index.js — test with MCP Inspector

Architecture

src/
├── index.ts          Entry point: creates McpServer, registers tools, starts stdio transport
├── config.ts         Environment variable loading → Config object
├── auth.ts           OAuth2 token lifecycle (auto-refresh, concurrency-safe)
├── client.ts         HTTP client wrapping MB API v4 (public + authenticated requests)
├── guards.ts         Security: operation mode gates, spending tracker, confirmation previews
└── tools/
    ├── public.ts     7 tools — orderbook, trades, symbols, tickers, candles, fees, networks
    ├── account.ts    6 tools — accounts, balances, tier, positions, fees, internal transfer
    ├── trading.ts    6 tools — place/cancel/list orders (with confirmation flow)
    └── wallet.ts     11 tools — deposits, withdrawals, addresses, bank accounts, sub-accounts

Security model (3 layers)

Operation mode (MB_OPERATION_MODE): controls which tool groups are registered at startup. readonly < trading < full.
Confirmation flow: dangerous tools require confirm=true parameter. Default call returns a preview; user must approve before execution.
Spending guards: MB_MAX_ORDER_BRL (per-order), MB_DAILY_LIMIT_BRL (daily), MB_DRY_RUN (simulate). Tracked in SpendingTracker.

Key patterns

All tools return { content: [{ type: "text", text: JSON.stringify(data) }] }.
Auth token is cached and auto-refreshed 60s before expiry. Concurrent refresh requests are coalesced.
Guard checks (requireAuth, requireMode) run at tool invocation, returning error content if denied.
console.error() for all logging (never stdout — it's the MCP transport).

Read the full file on GitHub · 51 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.

10d ago First seen · 51 lines · 613 tokens per session scan A 924599b1f973

Subscribe to this mod's changes

mcp-mercado-bitcoin CLAUDE.md is an instructions file published in the GitHub repository RodrigoFlorencio86/mcp-mercado-bitcoin (1 stars, last pushed 5mo ago), licensed MIT. It adds 613 tokens to every session, about $0.0031 per session on Opus 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.

Finance and fintech

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-mercado-bitcoin: Instructions file for Claude Code