open-meteo-mcp: Instructions file for Codex

AGENTS.md

open-meteo-mcp AGENTS.md is an instructions file for Codex, OpenCode from cmer81/open-meteo-mcp. It costs 976 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on an Open-Meteo MCP server. MCP, or Model Context Protocol, lets an AI client call tools; this server connects those tools to weather, air-quality, marine, flood, and climate APIs.

In plain words
What is it for?
Use it when modifying, testing, or reviewing this server and its 17 API tools, including their schemas, transports, caching, authentication, and release rules.
Why use it?
It gives agents the repository's architecture, transport options, tool definitions, data validation, security rules, and required project checks before they make changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions AGENTS.md.

This is cmer81/open-meteo-mcp's own configuration. It tells Codex and OpenCode how to work on open-meteo-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 open-meteo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cmer81/open-meteo-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/cmer81/open-meteo-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cmer81/open-meteo-mcp

Made for: Codex, OpenCode.

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 open-meteo-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cmer81/open-meteo-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/cmer81/open-meteo-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cmer81/open-meteo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cmer81/open-meteo-mcp/agents-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 open-meteo-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cmer81/open-meteo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cmer81/open-meteo-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 976 This file is loaded in full into every session.
When invoked 976 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 $0.00976 $0.00976
Opus 5.5 $0.00390 $0.00390
Sonnet 5.5 $0.00195 $0.00195
Haiku 4.5 $0.00098 $0.00098

Measured 24d ago against content hash d0fd720eefc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

open-meteo-mcp AGENTS.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 24d 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.

AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Open-Meteo MCP (Model Context Protocol) server: gives LLMs access to Open-Meteo's forecast, historical, air quality, marine, flood, seasonal and climate projection APIs.

Instructions for coding agents. Detailed, area-specific guidance lives in .claude/rules/ (see Area rules) and the release procedure in .claude/skills/release/SKILL.md.

Architecture

  • src/index.ts - MCP server (@modelcontextprotocol/sdk), tool registration, both transports
  • src/client.ts - OpenMeteoClient: one Axios instance per Open-Meteo service, LRU response cache
  • src/tools.ts - Tool metadata (name, title, description, annotations); input schemas come from types.ts
  • src/instructions.ts - Server instructions sent at initialize (lands in the client's system prompt): which tool answers which question. A test fails if a tool is not mentioned
  • src/types.ts - Zod schemas for all API parameters and responses
  • src/truncation.ts - Caps oversized responses and serializes them for the client
  • src/security.ts - Auth, origin validation, rate limiting, trusted-proxy IP extraction (HTTP transport only)

Transports

Selected by the TRANSPORT env var:

  • stdio (default) - for local MCP clients. Never write logs to stdout here — it would corrupt the protocol stream; log() writes to stderr.
  • Streamable HTTP (TRANSPORT=http) - stateless Express server on /mcp, bound to 127.0.0.1 by default.

Tools (17)

  • Core: weather_forecast, weather_archive, air_quality, marine_weather, elevation, geocoding
  • Model-specific (same schema, different endpoint): dwd_icon_forecast, gfs_forecast, meteofrance_forecast, ecmwf_forecast, jma_forecast, metno_forecast, gem_forecast
  • Advanced: flood_forecast, seasonal_forecast, climate_projection, ensemble_forecast

Commands

npm run dev        # auto-reload
npm run build      # TypeScript -> dist/
npm start          # run the built server
npm test
npm run typecheck
npm run lint
npm run smoke      # every tool against the live API (needs a prior build)

Read the full file on GitHub · 69 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. 24d ago First seen · 69 lines · 976 tokens per session scan A d0fd720eefc7

Subscribe to this mod's changes

open-meteo-mcp AGENTS.md is an instructions file published in the GitHub repository cmer81/open-meteo-mcp (72 stars, last pushed today), licensed MIT. It adds 976 tokens to every session, about $0.0039 per session on Opus 5.5. 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 2026-10-04.

Related

Other instructions, from other repositories