mcp-stm-montevideo: Instructions file for Claude Code

CLAUDE.md

mcp-stm-montevideo CLAUDE.md is an instructions file for Claude Code from chaba11/mcp-stm-montevideo. It costs 511 tokens per session, scanned A, original, MIT.

Development instructions for an MCP server that provides Montevideo, Uruguay’s public-bus data to language models. MCP is a standard way for an AI assistant to use external tools and data.

In plain words
What is it for?
Use it when developing or maintaining the STM Montevideo server, including its TypeScript code, Vitest tests, CKAN data lookups, coordinate conversion, and bus-schedule responses.
Why use it?
It gives contributors the project context, approved data sources, technology choices, testing rules, caching requirements, and error-handling expectations in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is chaba11/mcp-stm-montevideo's own configuration. It tells Claude Code how to work on mcp-stm-montevideo 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 mcp-stm-montevideo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chaba11/mcp-stm-montevideo. 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/chaba11/mcp-stm-montevideo/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chaba11/mcp-stm-montevideo

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 mcp-stm-montevideo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chaba11/mcp-stm-montevideo/claude-md/github.svg)](https://agentmods.dev/instructions/chaba11/mcp-stm-montevideo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chaba11/mcp-stm-montevideo/claude-md"><img src="https://agentmods.dev/badge/instructions/chaba11/mcp-stm-montevideo/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 mcp-stm-montevideo CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chaba11/mcp-stm-montevideo/claude-md"><img src="https://agentmods.dev/badge/instructions/chaba11/mcp-stm-montevideo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 511 This file is loaded in full into every session.
When invoked 511 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 $0.00511 $0.00511
Opus 5 $0.00255 $0.00255
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 9d ago against content hash 482d105b9fa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-stm-montevideo 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 9d 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 · 48 lines

What it actually says

MCP STM Montevideo

Qué es este proyecto

Un MCP server en TypeScript que expone datos del Sistema de Transporte Metropolitano (STM) de Montevideo, Uruguay. Permite que LLMs respondan preguntas como "¿cuándo pasa el próximo 181 por Bv España y Libertad?"

Stack

  • Runtime: Node.js 20+ con TypeScript
  • MCP SDK: @modelcontextprotocol/sdk
  • Build: tsup
  • Test: vitest
  • Geo: geolib
  • Package name: mcp-stm-montevideo

Fuentes de datos

  • CKAN Montevideo: https://ckan.montevideo.gub.uy/api/3/action/
  • Dataset horarios por parada: horarios-de-omnibus-urbanos-por-parada-stm
  • Dataset paradas: buscar en CKAN el que tenga ubicación de paradas con coordenadas
  • Dataset recorridos: buscar en CKAN
  • Las coordenadas pueden estar en EPSG:32721 (UTM 21S) — convertir a WGS84
  • Timezone: America/Montevideo para todos los cálculos

Reglas de desarrollo

  • Todo el código en src/
  • Tests en tests/ con vitest
  • Nunca hardcodear URLs de recursos CKAN (los resource_id cambian). Usar package_show para resolver dinámicamente.
  • Cache en memoria con TTL: 1h para horarios, 24h para paradas estáticas
  • Manejo de errores robusto: si CKAN no responde, devolver mensaje claro al usuario
  • Código y comments en inglés, README bilingüe (es/en)
  • Cada tool del MCP debe tener inputSchema completo con descriptions en español

Cómo verificar

npm run build && npm run test && npm run lint

Filosofía de testing

  • Los test loops buscan edge cases activamente: datos vacíos, encoding, timezone, errores de red, tipos incorrectos
  • Si un test descubre un bug → ARREGLAR el código en el mismo loop, no skipear el test
  • Cada bug arreglado por un test → agregar un test de regresión al unit test correspondiente
  • Target: 120+ tests al final del proyecto
  • Tests de performance para routing: < 2s con red completa, < 5s con 500 paradas
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. 9d ago First seen · 48 lines · 511 tokens per session scan A 482d105b9fa7

Subscribe to this mod's changes

mcp-stm-montevideo CLAUDE.md is an instructions file published in the GitHub repository chaba11/mcp-stm-montevideo (1 stars, last pushed 6mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens