cursorrules

A set of Cursor rules and project notes for an MCP server that reads smart-city sensor data from MongoDB. MCP is a standard way for an AI agent to use external tools, while MongoDB is a database that stores the sensor records.

In plain words
What is it for?
It is for working on or using tools that list lighting devices, inspect telemetry, analyze energy and gas use, detect water leaks, and compare regional statistics.
Why use it?
It gives the agent project-specific context, structure, technologies, database details, and available operations instead of leaving those details implicit.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/wesleyribeirobarbosa/mcp-server/cursorrules
Clone the repo
git clone --depth 1 https://github.com/wesleyribeirobarbosa/mcp-server

Made for: Cursor.

Per session 569 This file is loaded in full into every session.
When invoked 569 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00569 $0.00569
Opus 5 $0.00284 $0.00284
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 2d ago against content hash 227aae8462ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Projeto: Servidor MCP para Smart Cities

Contexto do Projeto

Este é um servidor MCP (Model Context Protocol) que permite interação com dados IoT de cidades inteligentes.

Estrutura Principal

  • /src/server.ts - Servidor MCP principal
  • /src/tools/ - Ferramentas MCP disponíveis
  • /db-init/ - Scripts de inicialização do banco MongoDB
  • /dist/ - Arquivos TypeScript compilados
  • /.cursor/mcp.json - Configuração MCP para Cursor

Tecnologias Utilizadas

  • TypeScript
  • Node.js
  • MongoDB
  • MCP SDK (@modelcontextprotocol/sdk)
  • Zod para validação
  • Winston para logging

Banco de Dados

  • MongoDB local na porta 27017
  • Database: smart_city_iot
  • Usuário: cursor-mcp-client
  • Collections: lighting_devices, water_devices, gas_devices, *_telemetry

Ferramentas MCP Disponíveis

Ferramentas Básicas

  1. listLightingDevices - Lista dispositivos de iluminação
  2. getLightingTelemetry - Dados de telemetria
  3. analyzeEnergyConsumption - Análise de consumo de energia
  4. detectWaterLeaks - Detecção de vazamentos
  5. analyzeGasConsumption - Análise de consumo de gás

Ferramentas Avançadas

  1. getRegionalStatistics - Estatísticas regionais comparativas
  2. getDeviceHealthReport - Relatório de saúde dos dispositivos
  3. getCityDashboard - Dashboard completo da cidade
  4. predictMaintenance - Predição de manutenção
  5. getAnomalyDetection - Detecção de anomalias
  6. getEnergyEfficiencyReport - Relatório completo de eficiência energética
  7. getWaterQualityReport - Relatório de qualidade da água
  8. getCrossDeviceAnalysis - Análise correlacionada entre dispositivos

Comandos Importantes

  • npm run build - Compila TypeScript
  • npm start - Inicia servidor MCP
  • cd db-init && docker-compose up -d - Inicia MongoDB com dados

Convenções

  • Timestamps sempre em formato UNIX (segundos)
  • Logs salvos em arquivos (não console) devido ao protocolo MCP
  • Comunicação apenas via Stdio
  • IDs de dispositivos seguem padrão: LIGHT-000001, WATER-000001, etc.

Read the full file on GitHub · 61 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. 2d ago First seen · 61 lines · 569 tokens per session scan A 227aae8462ec

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository wesleyribeirobarbosa/mcp-server (1 stars, last pushed 1y ago), licensed MIT. It adds 569 tokens to every session, about $0.0028 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.