ibge-br-mcp: Instructions file for Claude Code

CLAUDE.md

ibge-br-mcp CLAUDE.md is an instructions file for Claude Code from SidneyBissoli/ibge-br-mcp. It costs 4,027 tokens per session, scanned A, original, MIT.

A project instruction document for ibge-br-mcp, an MCP server that exposes Brazilian public data from IBGE through tools for coding assistants.

In plain words
What is it for?
Use it when developing or maintaining this TypeScript server, its data tools, tests, configuration, and command-line workflow.
Why use it?
It explains how the server works and gives contributors the commands and rules needed to build, test, lint, and modify it.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is SidneyBissoli/ibge-br-mcp's own configuration. It tells Claude Code how to work on ibge-br-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ibge-br-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SidneyBissoli/ibge-br-mcp. 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/SidneyBissoli/ibge-br-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SidneyBissoli/ibge-br-mcp

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.

agentmods badge for ibge-br-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sidneybissoli/ibge-br-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/sidneybissoli/ibge-br-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sidneybissoli/ibge-br-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sidneybissoli/ibge-br-mcp/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.

agentmods 80×15 button for ibge-br-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sidneybissoli/ibge-br-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sidneybissoli/ibge-br-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,027 This file is loaded in full into every session.
When invoked 4,027 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04027 $0.04027
Opus 5 $0.02014 $0.02014
Sonnet 5 $0.00805 $0.00805
Haiku 4.5 $0.00403 $0.00403

Measured 6d ago against content hash d35af42881f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ibge-br-mcp 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 6d 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 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.

What this is

An MCP (Model Context Protocol) server, published to npm as ibge-br-mcp, that exposes Brazilian public data from the IBGE APIs as ~23 tools over STDIO (health data, including some DataSUS-origin stats, is read via IBGE's SIDRA — the server only ever calls IBGE endpoints). Pure TypeScript, ESM, no runtime framework — just @modelcontextprotocol/server (MCP SDK v2) + zod 4. There is no database and no local state beyond an in-memory cache; every tool is a thin async function that fetches from a public REST API and formats the result as Markdown text.

Commands

npm run build          # tsc → dist/ (required before start/inspector; bin points at dist/index.js)
npm run dev            # build + run
npm run watch          # tsc --watch
npm test               # vitest run (all tests)
npm run test:watch     # vitest watch
npm run test:coverage  # coverage report
npm run lint           # eslint src/  (must be zero warnings)
npm run lint:fix
npm run format         # prettier --write src/
npm run inspector      # @modelcontextprotocol/inspector against dist/index.js — manual tool testing
node scripts/smoke-mcp.mjs           # smoke against the hosted Worker (initialize/tools/list/calls incl. estatisticas)
node scripts/smoke-mcp.mjs --stdio   # same smoke over local STDIO (requires npm run build)

Run a single test file or test by name:

npx vitest run tests/validation.test.ts
npx vitest run -t "ibgeEstados"

Node >= 20 (SDK v2 requirement; uses the global fetch). Tests mock global.fetch — they never hit the network.

The Cloudflare Worker (worker/, not published to npm) is an instance of the portfolio's Fase 0 hosting template (mcp-br-commons/templates/cloudflare-worker) and has its own scripts, run from inside worker/:

cd worker && npm run dev        # wrangler dev — local HTTP transport
cd worker && npm run deploy     # wrangler deploy
cd worker && npm run typecheck  # tsc --noEmit
cd worker && npm test           # vitest — auth, rate limit, usage, status, surface

Read the full file on GitHub · 106 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.

  1. 6d ago Changed · +12 lines · +470 tokens per session d35af42881f5
  2. 10d ago First seen · 94 lines · 3,557 tokens per session scan A 0a1f4c1e329b

Subscribe to this mod's changes

ibge-br-mcp CLAUDE.md is an instructions file published in the GitHub repository SidneyBissoli/ibge-br-mcp (9 stars, last pushed today), licensed MIT. It adds 4,027 tokens to every session, about $0.0201 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.

Related

Other instructions, from other repositories