dailymeteo-mcp
Use it to query historical weather/climate data and manage DailyMeteo downloads for land locations worldwide.
Find place coordinates and area boundary polygons.
Get daily, monthly, or annual weather values for a location (temperature and precipitation), with summaries, trends, and CSV output.
Get 1961–1990 vs 1991–2020 climate normals and their change.
Check DailyMeteo account plan and remaining API/bulk credits.
Order a full daily point-history CSV by email using bulk credits.
Estimate and order clipped daily GeoTIFF area downloads (max 3,000 km²) using API credits.
Generate DailyMeteo app links for map, chart, and CSV/PDF export.
List and download MeteoEurope1km Zenodo raster archives, verify MD5 checksums, and optionally unzip.
Provides place-name to latitude/longitude lookup via OpenStreetMap, enabling weather queries for named locations.
Lists and downloads MeteoEurope1km gridded raster archives from Zenodo, covering Europe from 1961–2020 including sea-level pressure.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dailymeteo-mcp How much warmer are July days in Belgrade now than in 1961–1990?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dailymeteo-mcp
An MCP server for DailyMeteo. With it, an AI assistant (Claude, VS Code, Cursor and other MCP clients) can answer questions about historical weather and climate change for any land location. Data are 1 km grids from 1961 to the present.
How much warmer are July days in Belgrade now than in 1961–1990? Which was the wettest year in Lisbon since 1961? Download daily mean temperature grids for Europe for 2003.
Install
Easiest: ask your AI assistant (Claude Code, Cursor, Cline…): "Install the DailyMeteo MCP server from github.com/srpp011/dailymeteo-mcp". It will follow llms-install.md.
Claude Code plugin. The plugin connects to the hosted server at https://mcp.gilab.rs/mcp and adds a skill that tells Claude which tool to use. Nothing is installed locally. It asks for a DailyMeteo API key (Account → API Keys), which is optional and only needed for daily values:
claude plugin marketplace add srpp011/dailymeteo-mcp
claude plugin install dailymeteo@dailymeteoHosted server in any client. Add https://mcp.gilab.rs/mcp as a remote (streamable HTTP) MCP server. For daily values, send your API key in the X-DailyMeteo-Api-Key header, e.g. in Claude Code:
claude mcp add --transport http dailymeteo https://mcp.gilab.rs/mcp --header "X-DailyMeteo-Api-Key: YOUR_KEY"The hosted server has the tools that need no account on the server side: places and areas, values, normals, app links and the Zenodo archive list with download links. Account credits, point-history and area orders, and archive downloads to disk need the local server below.
Local server. All tools, including the account ones. It needs uv and runs with uvx --python 3.12 dailymeteo-mcp. See Configuration.
Related MCP server: Weather MCP Server
Tools
Everything the DailyMeteo app offers, for land areas worldwide, from 1961 to the present:
Tool | What it does | Cost |
| Place name → latitude/longitude (OpenStreetMap) | free |
| Area name → boundary polygon and size, for area downloads | free |
| Daily, monthly or annual values for a location; several variables at once; summary, yearly aggregates, trend, CSV | monthly/annual free; daily 1 credit per day and variable |
| Normals 1961–1990 and 1991–2020 and their change (year, months, or a calendar day) | free |
| Plan, API credits, bulk credits | free |
| Every variable, daily, for one location (whole record by default), CSV by email | 1 bulk credit |
| Cost of daily rasters clipped to an area (max 3,000 km²) | free |
| Daily GeoTIFF rasters clipped to an area, by email | API credits |
| Opens the location and series in the DailyMeteo app (map, chart, CSV/PDF export) | free |
| MeteoEurope1km raster archives on Zenodo (Europe, 1961–2020, incl. sea-level pressure) | free |
Variables are tmean, tmax and tmin in °C, and prcp in mm (monthly and annual values are totals).
As in the app, daily requests over 1,000 credits ask for the user's confirmation, and area downloads should be estimated before they are ordered. Repeating the same daily request is not charged again. Long series are not dumped into the conversation. They are summarised (per variable and per year) and saved as CSV.
Configuration
All environment variables are optional. Without any of them, monthly and annual values, normals, links and Zenodo grids work.
DAILYMETEO_EMAILandDAILYMETEO_PASSWORD: your DailyMeteo account. They enable daily values, credits, point history and area downloads. Sign up at https://app.dailymeteo.com/.DAILYMETEO_API_KEY: alternative for daily values only (Account → API Keys).DAILYMETEO_OUTPUT_DIR: where CSV files and downloads are saved (default~/dailymeteo).
Running the hosted mode yourself
DAILYMETEO_MCP_REMOTE=1 starts the server over streamable HTTP at /mcp (stateless, JSON responses), with /health and /files/<token>/<name>.csv for CSV links that expire after one hour. In this mode the account tools and disk downloads are left out, and daily values use only the API key the client sends in X-DailyMeteo-Api-Key (or Authorization: Bearer), never one from the server's environment.
DAILYMETEO_MCP_PUBLIC_URL: public base URL for CSV links (e.g.https://mcp.gilab.rs).DAILYMETEO_MCP_HOST,DAILYMETEO_MCP_PORT: listen address (default0.0.0.0:8000).DAILYMETEO_OUTPUT_DIR: where the CSV files are kept.
docker run -d -p 8000:8000 -e DAILYMETEO_MCP_REMOTE=1 -e DAILYMETEO_MCP_PUBLIC_URL=https://mcp.example.org dailymeteo-mcpRun it behind a reverse proxy with HTTPS. Requests to OpenStreetMap Nominatim are cached and sent at most one per second, as its usage policy asks.
Claude Code
claude mcp add dailymeteo -s user -e DAILYMETEO_EMAIL=you@example.com -e DAILYMETEO_PASSWORD=... -- uvx --python 3.12 dailymeteo-mcpClaude Desktop, Cursor, VS Code (mcpServers JSON)
{
"mcpServers": {
"dailymeteo": {
"command": "uvx",
"args": ["--python", "3.12", "dailymeteo-mcp"],
"env": { "DAILYMETEO_EMAIL": "you@example.com", "DAILYMETEO_PASSWORD": "..." }
}
}
}Docker (no local Python)
docker build -t dailymeteo-mcp .
claude mcp add-json dailymeteo -s user '{"type":"stdio","command":"docker","args":["run","-i","--rm","-e","DAILYMETEO_EMAIL","-e","DAILYMETEO_PASSWORD","-v","/path/to/output:/data","dailymeteo-mcp"]}'Data and citation
The values are interpolated grids, not station measurements. Results used in a publication should cite:
Sekulić, A., & Kilibarda, M. (2026). MeteoEurope1km (1961–2020): daily gridded meteorological dataset for Europe at a 1-km spatial resolution. Zenodo. https://doi.org/10.5281/zenodo.23264155
Built on the Python client dailymeteo. License: GPL-2.0-or-later.
Available Tools
11 toolsaccount_statusDailyMeteo account and creditsBRead-onlyInspect
Plan and remaining credits: API credits (daily point and area data) and bulk credits (point history).
Inputs: no named parameters.
app_linkOpen in the DailyMeteo appBRead-onlyInspect
Link that opens the location, variable and period on the DailyMeteo map with its chart and CSV export.
Inputs: lat (required), lon (required), end, start, +2 more. Returns: result
download_gridded_filesDownload MeteoEurope1km grid archivesAIdempotentInspect
Download MeteoEurope1km archives (1-3.5 GB per year of daily data), verify MD5, optionally unzip.
Interrupted downloads resume. Tell the user the total size (list_gridded_files) before large downloads.
Inputs: variable (required), unzip, years, period, +2 more.
estimate_area_downloadEstimate area download costBRead-onlyInspect
Credit cost of daily rasters clipped to an area (max 3,000 km²), and the account balance.
Inputs: end (required), start (required), variables (required), bbox, +1 more.
find_areaFind an area (polygon)ARead-onlyInspect
Boundary polygon (WKT) and size of a named area, for estimate_area_download / request_area_download.
Inputs: query (required).
find_locationFind a placeARead-onlyInspect
Latitude and longitude of a place (OpenStreetMap Nominatim). If several match, ask the user which one.
Inputs: query (required), limit. Returns: result
get_climate_normalsClimate normals 1961-1990 vs 1991-2020ARead-onlyInspect
Climate normals for 1961-1990 and 1991-2020 and the change (newer minus older). Free.
Without month, time_scale=mon returns all 12 months. Annual precipitation normals are yearly totals.
Inputs: lat (required), lon (required), day, month, +2 more.
get_weatherWeather values for a locationARead-onlyInspect
Daily, monthly or annual values for one location and one or more variables, 1961 to the present.
Monthly and annual values are free. Daily values cost 1 credit per day and variable and need the user's DailyMeteo API key or account (see the server instructions). Results include a summary per variable; series longer than 400 rows are not listed but summarised by year and saved as CSV.
Inputs: lat (required), lon (required), end, dates, +5 more.
list_gridded_filesList MeteoEurope1km grid archivesCRead-onlyInspect
MeteoEurope1km archives on Zenodo (Europe, 1 km, 1961-2020, Cloud-Optimized GeoTIFF), free.
Rasters are Equi7 Europe (EPSG:27704), Int16 in tenths of the unit (°C, mm, hPa), NoData -9999.
Inputs: variable (required), years, period, product.
request_area_downloadOrder area download (email)AInspect
Daily GeoTIFF rasters clipped to an area (max 3,000 km²), prepared on the server and emailed.
Spends API credits: run estimate_area_download first and get the user's agreement to the cost.
Inputs: end (required), start (required), variables (required), bbox, +1 more.
request_point_historyOrder full point history (email)AInspect
Every variable, daily, for one location — by default the whole record since 1961 — as CSV by email.
Costs one bulk credit (bulk credits are separate from API credits). Preparing the file takes minutes.
Inputs: lat (required), lon (required), end, start.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Most tools target a clearly distinct action/resource: find_location, find_area, list/download gridded files, account_status, estimate/request area downloads, and climate normals are well separated. The main overlap is between get_weather and request_point_history, since both can return daily point data, though their delivery format, scope, and credit model are described well enough to distinguish them.
The set mostly follows a readable verb_noun pattern: find_location, find_area, get_weather, estimate_area_download, request_area_download, list_gridded_files, download_gridded_files, get_climate_normals, and request_point_history. Two tools, app_link and account_status, are noun phrases rather than verb-led, which is a minor deviation but not confusing.
With 11 tools, the surface is well scoped for a weather-data service covering point data, area data, gridded archives, climate normals, account credits, geocoding, and a convenience app link. Each tool appears to serve a real workflow rather than duplicating the same operation.
The set covers the core lifecycle: locate a point or area, estimate cost, request or retrieve data, list/download gridded archives, check credits, and get climate normals. Minor gaps remain, such as no explicit variable-discovery tool and no obvious way to check the status of emailed area/point-history requests, but agents can likely work around these with server instructions or the provided descriptions.
Maintenance
Related MCP Connectors
Historical weather and climate: 100+ years of station data, normals, extremes, and trends.
Weather, climate, soil, terrain, fire and flood risk data for any point or polygon. Free tier.
Historical climate data, temperatures, precipitation, and normals
Global weather via Open-Meteo: forecast, historical, marine, air quality, geocoding, elevation.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes public weather and climate data through a standardized API, allowing AI agents to retrieve current conditions, 7-day forecasts, and historical data. It enables weather-aware automation and data enrichment for conversational agents and travel planning.-
- AlicenseNot gradedqualityDmaintenanceGlobal weather intelligence for AI assistants providing 10 weather tools — forecasts, historical data, air quality, marine, geocoding, elevation, and climate projections at 1km resolution with 80+ years of archive.1MIT
- AlicenseNot gradedqualityFmaintenanceProvides weather and climate intelligence for AI agents, including current conditions, forecasts, historical data, severe-weather alerts, agricultural outlook, and travel conditions via free and paid tools.1MIT
- FlicenseAqualityBmaintenanceEnables AI assistants to retrieve current weather conditions and forecasts for any location via natural language, with optional AI-generated summaries.1-