What is aemet-mcp CLAUDE.md?

A project instruction file for an AEMET MCP server, which makes Spain's weather-agency data available to AI clients and agents. It describes the project's purpose, current published state, preferred simplicity, and technical context.

Use it when modifying the AEMET data server, choosing its tools, or explaining implementation decisions in the project's preferred technical context.

It helps an agent understand the project's domain and constraints before changing a server that already exists and is published.

How mmillan76/aemet-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mmillan76/aemet-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/mmillan76/aemet-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mmillan76/aemet-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mmillan76/aemet-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mmillan76/aemet-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mmillan76/aemet-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mmillan76/aemet-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mmillan76/aemet-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mmillan76/aemet-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,039 This file is loaded in full into every session.

When invoked 2,039 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	$0.02039	$0.02039
Opus 5	$0.01019	$0.01019
Sonnet 5	$0.00408	$0.00408
Haiku 4.5	$0.00204	$0.00204

Measured 8d ago against content hash dd8d6b857d2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aemet-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 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 · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AEMET MCP Server

Servidor MCP que expone datos de la AEMET (Agencia Estatal de Meteorología, España) a clientes de IA / agentes. Es el primer servidor MCP de una serie; su objetivo principal es didáctico: cerrar el ciclo completo build → publicar → descubrir.

Mantenlo simple. Prefiero 3 tools sólidas y bien tipadas a 10 a medias.

Estado actual (este repo YA está publicado — NO es greenfield)

La v1 está construida, publicada y funcionando en Claude Desktop (ver "Estado de publicación" más abajo para nombres y URLs reales). Implicaciones al trabajar aquí:

Las secciones "Orden de trabajo" y el "Checklist de publicación" son referencia histórica de cómo se levantó el repo, no tareas abiertas.
El trabajo futuro son iteraciones sobre algo vivo y ya publicado, no un montaje desde cero. Antes de cambiar algo, asume que ya existe y funciona.

Objetivo del proyecto

Producto público en npm + GitHub, licencia MIT.
Publicado en el registro oficial de MCP y en directorios (mcp.so, Smithery).
Código limpio que sirva de plantilla mental para los siguientes servidores.

Sobre mí (contexto para cómo explicarme las cosas)

Vengo de backend Java / Spring Boot. Mi TypeScript es básico. Quiero entender lo que se construye, no solo que compile:

Comenta las partes de async/await y los esquemas Zod cuando no sean obvias.
Si una decisión tiene alternativa razonable, dímela con el tradeoff en una línea.
No expliques lo trivial; asume que sé programar, no que sé el ecosistema Node.

Stack

Runtime: Node.js 20+, TypeScript.
SDK: @modelcontextprotocol/sdk (TypeScript).
Transporte: stdio para desarrollo local. (SSE/HTTP se valorará más adelante.)
HTTP: fetch nativo de Node.
Empaquetado: publicable vía npx -y <paquete>.

Estructura

aemet-mcp/
  src/
    index.ts          # arranque del servidor MCP + registro de tools (con shebang)
    aemet-client.ts   # wrapper sobre la API de AEMET (aísla el patrón de 2 pasos)
    tools/
      get-forecast.ts
      get-station-data.ts
      get-warnings.ts
  dist/               # salida de tsc — esto es lo que se publica, no src/
  package.json
  tsconfig.json
  server.json         # metadatos para el registro oficial de MCP
  .gitignore          # node_modules, dist, .env
  .env.example        # AEMET_API_KEY= (vacío)
  README.md
  LICENSE             # MIT

Read the full file on GitHub · 143 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 · 143 lines · 2,039 tokens per session scan A dd8d6b857d2f

Subscribe to this mod's changes

aemet-mcp CLAUDE.md is an instructions file published in the GitHub repository mmillan76/aemet-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,039 tokens to every session, about $0.0102 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

aemet-mcp: Instructions file for Claude Code