Meteoswiss Llm Tools MCP Server

🌦️ MeteoSwiss LLM Tools

Swiss weather data for AI assistants — powered by MeteoSwiss Open Government Data (OGD), the same data behind the MeteoSwiss app and website. Free, no API key required.

meteoswiss-mcp.ars.is — try the hosted service instantly, no setup needed.

This repo is also a working answer to a design question: how should you give AI agents access to a public dataset? It implements the same MeteoSwiss data access twice — as an agent skill (markdown instructions plus bash scripts, no server) and as an MCP server (structured tools, fuzzy matching, caching, hosted). The two approaches are compared honestly in the skill vs. MCP case study.

A third piece, meteoswiss-forecast-evals, demonstrates eval-driven interface design: a promptfoo suite measuring how well 13 LLMs read the forecast JSON, which settled a real design decision — local-time timestamps beat UTC, with hour-level lookups scoring ~100% vs. ~0%.

What the tools provide:

• Multi-day forecasts for ~6000 Swiss locations (postal codes, stations, place names)
• Real-time measurements from ~300 stations (~160 full weather + ~140 precipitation-only), updated every 10 minutes
• Station discovery by name, canton, or GPS coordinates
• Pollen monitoring from ~15 stations across Switzerland
• Climate series from the National Basic Climatic Network (NBCN), going back decades
• MeteoSwiss website search and content retrieval

What this repo demonstrates

• An agent skill — teach an agent to fetch open data directly with curl/awk/jq: ~630 lines of markdown and bash, zero infrastructure. → packages/meteoswiss-skills
• An MCP server — the same data as structured, validated tools with fuzzy station matching, geocoding, TTL-tiered caching, a real test suite, Docker, and a hosted instance. → packages/meteoswiss-mcp
• Eval-driven interface design — treat tool output as an interface for a language model, and measure its legibility before shipping. → packages/meteoswiss-forecast-evals

Read the comparison: Skill vs. MCP Server: Two Ways to Give AI Agents the Same Data.

Choose your approach

Both approaches answer the same weather questions. Which to install depends on your agent:

Full comparison — parity matrix, engineering trade-offs, context cost, when to choose which: docs/skill-vs-mcp.md.

MCP server — quickstart

Use the hosted instance (no installation):

# Claude Code
claude mcp add meteoswiss https://meteoswiss-mcp.ars.is/mcp

For Cursor, install from the Cursor Directory or add manually via Settings → MCP.

Or self-host with Docker:

docker run -p 3000:3000 ghcr.io/eins78/meteoswiss-mcp:latest

See the meteoswiss-mcp README for Claude Desktop setup, environment variables, and full documentation.

Agent skill — quickstart

Install via the Claude Code plugin marketplace:

/plugin marketplace add eins78/meteoswiss-llm-tools
/plugin install meteoswiss-skills@meteoswiss-marketplace

Or with the Skills CLI:

pnpx skills add https://github.com/eins78/meteoswiss-llm-tools.git#packages/meteoswiss-skills --global --agent claude-code --all

See the meteoswiss-skills README for manual installation and details.

Available tools (MCP server)

Example questions

Works with both approaches — just ask in any of Switzerland's four languages:

• "What's the weather forecast for Zurich this week?"
• "Wie wird das Wetter in Bern morgen?"
• "Quelle est la météo à Genève?"
• "Che tempo fa a Lugano?"

Packages

Documentation

• Skill vs. MCP case study — the honest comparison of the two approaches
• Eval results: forecast JSON comprehension — the local-time-vs-UTC sweep
• MCP server user guide
• Documentation index

Development

git clone https://github.com/eins78/meteoswiss-llm-tools.git
cd meteoswiss-llm-tools
nvm use && pnpm install

See each package's README for package-specific commands. The repo uses changesets for versioning.

Manual, point-in-time test reports (e.g. live MCP tool test passes) live in docs/test-reports/.

Data source

All weather data comes from MeteoSwiss Open Government Data (OGD) — the official free data offering from Switzerland's Federal Office of Meteorology and Climatology. The same data powers the MeteoSwiss app and website.

License

CC0-1.0 — public domain