What is ab-ibge-mcp-server CLAUDE.md?

Instructions for developing and publishing an MCP server that gives AI agents access to Brazil's IBGE public data APIs. IBGE is Brazil's government institute for statistics and geography, and MCP is a standard way for AI tools to call external services.

Use it when developing the server, building its TypeScript code, running it locally, checking its available data tools, and publishing versioned updates to the npm package registry.

It puts the project's development, build, local testing, and release commands in one place so contributors can work consistently.

How ab-orbit/ab-ibge-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ab-orbit/ab-ibge-mcp-server. 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/ab-orbit/ab-ibge-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ab-orbit/ab-ibge-mcp-server

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/ab-orbit/ab-ibge-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/ab-orbit/ab-ibge-mcp-server/claude-md)

Your own site

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

Per session 1,816 This file is loaded in full into every session.

When invoked 1,816 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	$0.01816	$0.01816
Opus 5	$0.00908	$0.00908
Sonnet 5	$0.00363	$0.00363
Haiku 4.5	$0.00182	$0.00182

Measured 8d ago against content hash 202c18fd8086, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ab-ibge-mcp-server 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 8d 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 · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 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 Overview

This is an MCP (Model Context Protocol) server that provides AI agents access to Brazil's IBGE (Instituto Brasileiro de Geografia e Estatística) public APIs. The server exposes 22+ tools covering demographic, economic, and geographic data through a standardized MCP interface.

Published as: ab-ibge-mcp-server on npm registry.

Essential Commands

# Development
npm run dev          # Run server with ts-node (for testing)
npm run build        # Compile TypeScript to dist/
npm start            # Run compiled server from dist/

# Testing the server locally
node dist/index.js   # Should output: "✅ IBGE MCP Server iniciado — 22+ ferramentas disponíveis"

# Publishing updates
npm run build && npm version patch && npm publish  # Bug fixes (1.0.0 → 1.0.1)
npm run build && npm version minor && npm publish  # New features (1.0.0 → 1.1.0)
npm run build && npm version major && npm publish  # Breaking changes (1.0.0 → 2.0.0)

Architecture

Core Structure

src/
├── index.ts              # MCP server initialization and tool registration
├── types.ts              # TypeScript interfaces for IBGE API responses
├── services/
│   └── ibge-client.ts    # Centralized HTTP client with error handling
└── tools/                # MCP tool implementations (one file per domain)
    ├── localidades.ts    # Regions, states, municipalities (143 lines)
    ├── sidra.ts          # SIDRA system - statistical tables (582 lines)
    ├── censo.ts          # Census 2022 data (165 lines)
    ├── indicadores.ts    # Economic indicators (88 lines)
    ├── malha-noticias.ts # Geographic mesh & news (188 lines)
    └── cnae.ts           # Economic activity classification (385 lines)

Key Design Patterns

1. Tool Registration Pattern

Each tool file exports a register*Tools(server: McpServer) function
All tools are registered in src/index.ts during server initialization
Tools use Zod schemas for input validation
All tools return ToolResponse with consistent error handling

Read the full file on GitHub · 180 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.

8d ago First seen · 180 lines · 1,816 tokens per session scan A 202c18fd8086

Subscribe to this mod's changes

ab-ibge-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ab-orbit/ab-ibge-mcp-server (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,816 tokens to every session, about $0.0091 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.

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

ab-ibge-mcp-server: Instructions file for Claude Code