About
A MCP server for the Met Éireann API
README
An MCP (Model Context Protocol) server that exposes Irish weather forecasts to AI assistants via the official Met Éireann Open Access Forecast API.
http://openaccess.pf.api.met.ie/metno-wdb2ts/locationforecast
No API key required. All data is public open data from Met Éireann.
Data Source
Official API: http://openaccess.pf.api.met.ie/metno-wdb2ts/locationforecast
Query parameters:
| Parameter | Type | Description |
|---|---|---|
lat |
float | Latitude (−90 to 90) |
long |
float | Longitude (−180 to 180) |
Example:
http://openaccess.pf.api.met.ie/metno-wdb2ts/locationforecast?lat=53.3498&long=-6.2603
The API returns XML in the Met.no locationforecast 1.9 format. This server parses the XML and converts it to LLM-friendly plain text.
Licence: Met Éireann open data is published under the Met Éireann Open Data Licence.
MCP Tools
| Tool | Description |
|---|---|
get_weather(lat, lon) |
24-hour forecast for any coordinate |
get_dublin_weather() |
Forecast for Dublin (53.3498, −6.2603) |
get_forecast_by_city(city) |
Forecast for a named Irish city or county |
get_weather_alerts() |
Guidance on where to find active warnings |
api_status() |
Check API connectivity |
Supported locations for get_forecast_by_city
All 26 counties plus major towns: Dublin, Cork, Galway, Limerick, Waterford, Kilkenny, Sligo, Wexford, Drogheda, Dundalk, Tralee, Ennis, Athlone, Letterkenny, Mullingar, Belmullet, Malin Head, Shannon, Rosslare, Valentia, and all county names.
Setup
Requirements
- Python 3.11+
- pip
Install
git clone https://github.com/Sitric1/Met-Eireann-MCP-Server.git
cd Met-Eireann-MCP-Server
pip install -e ".[dev]"
Run
python main.py
Claude Desktop config
Add to claude_desktop_config.json:
{
"mcpServers": {
"met-eireann": {
"command": "python",
"args": ["/absolute/path/to/Met-Eireann-MCP-Server/main.py"]
}
}
}
Development
Run tests
pytest
pytest --cov=src
Project structure
Met-Eireann-MCP-Server/
├── main.py # MCP server entry point
├── pyproject.toml
├── src/
│ ├── clients/
│ │ └── met_eireann.py # HTTP client (retries, rate limiting, XML fetch)
│ ├── services/
│ │ └── forecast_service.py # XML parsing, caching, formatting
│ └── tools/
│ └── weather_tools.py # MCP tool registrations
└── tests/
├── test_client.py
├── test_service.py
└── test_tools.py
Reliability features
- Timeout: 20s per request
- Retries: up to 3 attempts with exponential backoff (1s, 2s)
- Rate limiting: minimum 1s between outgoing requests
- Caching: 10-minute TTL per coordinate (up to 256 entries)
- User-Agent: identifies requests to Met Éireann
- Graceful errors: all tool failures return a readable string, never raise
Limitations
- The point forecast API covers Ireland and nearby waters only.
- Weather alerts are not included in the point forecast API — see
get_weather_alerts()for the official warnings page. - Forecast resolution is hourly for the first 48 hours, then 6-hourly.
Licence
MIT — see LICENCE.
Install Met Eireann in Claude Desktop, Claude Code & Cursor
unyly install met-eireannInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add met-eireann -- uvx --from git+https://github.com/Sitric1/Met-Eireann-MCP-Server met-eireann-mcp-serverStep-by-step: how to install Met Eireann
FAQ
Is Met Eireann MCP free?
Yes, Met Eireann MCP is free — one-click install via Unyly at no cost.
Does Met Eireann need an API key?
No, Met Eireann runs without API keys or environment variables.
Is Met Eireann hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Met Eireann in Claude Desktop, Claude Code or Cursor?
Open Met Eireann on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
mkinf
An Open Source registry of hosted MCP Servers to accelerate AI agent workflows.
Compare Met Eireann with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
