139-tool MCP server for real-time global intelligence from free public APIs: markets, SEC filings, conflict, military, aircraft-cohort early warning, refugee and migration flows, cyber, climate, news, and 30+ domains. Cited AI situation briefs, geofences with change detection, live SSE dashboard. MIT, no paid API keys.

What's in it

Data offered llm-inferred: earthquakes (USGS) · wildfire hotspots (NASA FIRMS) · disaster alerts (GDACS) and environmental events (NASA EONET) · conflict events (ACLED, UCDP) · refugee and IDP displacement (UNHCR) · FX rates (ECB) · macro and economic indicators (FRED, World Bank, EIA) · internet outages and cloud service status (Cloudflare Radar, cloud status) · severe weather alerts (NWS, Meteoalarm) · tropical cyclones (NHC, JTWC) · volcano activity (Smithsonian GVP) · news feeds and trending keywords (RSS, GDELT)
Coverage docs-verified: Global
Update frequency docs-verified: Default 5-minute interval when the collector runs as a daemon; per-tool refresh rates not stated
Formats llm-inferred: MCP stdio · PDF · HTML · markdown · SSE (live dashboard)
Access docs-verified: Free public APIs with no paid subscription; MIT licence. Several tools need free API credentials set as env vars (ACLED_ACCESS_TOKEN, CLOUDFLARE_API_TOKEN, EIA_API_KEY, FRED_API_KEY, NASA_FIRMS_API_KEY, OPENSKY_CLIENT_ID, OPENSKY_CLIENT_SECRET)

Useful for

Use cases llm-inferred: Hazard screening for a client site: recent earthquakes, wildfire hotspots and GDACS disaster alerts for context in an environmental or civils risk note · Severe weather context for a project briefing using NWS and Meteoalarm alerts where the site falls in US or EU coverage · Macro and cost-escalation inputs for civils and infrastructure budgets using FRED, World Bank and EIA energy price series
Audience llm-inferred: environmental consultants · civils and infrastructure risk analysts · planners · GIS analysts · AI agent developers

Limitations

Constraints llm-inferred: Global geopolitical, market and security focus; no UK hydrology, flood, rainfall or ground-model datasets are listed in DOCS · Severe weather coverage is limited to US (NWS) and EU (Meteoalarm); UK coverage is not listed in DOCS · Requires local install of a Python package (pip install -e .) and Python 3.11+; not a hosted service · PDF reports need native dependencies, e.g. pango on macOS · A source that fails three times in a row is paused for 5 minutes by its circuit breaker · Several tools need API credentials; per-source rate limits and free-tier quotas are not stated in DOCS · Source maintenance risk: the server aggregates 30+ third-party public APIs that can change or disappear

climate gis

Globalhealthy

mcp

80/100Currency A

geo-mcp-servers ↗

A curated, tracked list of Model Context Protocol (MCP) servers for geospatial, GIS, mapping, and earth-observation work — geocoding, routing, PostGIS, STAC/imagery, QGIS/ArcGIS, weather, and the commercial location platforms.

What's in it

Data offered docs-verified: catalogue of geospatial MCP servers covering geocoding, routing, PostGIS, STAC/imagery, QGIS/ArcGIS, weather, and commercial location platforms
Formats llm-inferred: Markdown (README tables) · YAML (servers.yaml source)
Access docs-verified: Catalogue licensed MIT (ENTRY metadata). Listed servers range from open to paywalled: open, free, commercial, or paywalled, per the docs legend.

Useful for

Use cases llm-inferred: Find a geocoding or reverse-geocoding MCP server to convert site addresses to coordinates for a planning appraisal · Identify a PostGIS or STAC/imagery MCP server to query spatial datasets for catchment or land-use analysis · Locate a weather MCP server to pull rainfall or climate context for a drainage strategy desk study
Audience llm-inferred: GIS analysts · hydrologists · drainage engineers · flood consultants · planners · developers building MCP-based geospatial tooling

Limitations

Constraints llm-inferred: Lists servers rather than providing data itself · Server health varies: 18 stale and 2 pending at the time of the health check · Health status reflects only repository push activity within 12 months · Some entries have URLs still to be confirmed · Access tiers differ by server, and many are commercial or paywalled

climate gis

Globalhealthy

skill

77/100Currency A

ai-science-toolkit ↗

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

What's in it

Data offered docs-verified: Literature search and synthesis from Zotero, arxiv, bioRxiv, Google Scholar and Consensus (lit-review) · Publication-readiness audit of scientific figures (figure-review) · Senior-engineer repo review with parallel sub-reviews (ai-review) · Stress-testing of claims, results and manuscript sections (reviewer-2) · Listing of running Claude/Codex CLI sessions with resume commands (ai-sessions) · Scaffolding of new repos with a standard structure (repo-init)
Formats docs-verified: Claude Code skills (slash commands, SKILL.md) · Shell scripts (.sh) · Markdown reviewer agents
Access docs-verified: MIT licence. No credentials documented for most of the toolkit; Zotero write access, the Notion work journal and session-name generation need configuration.

Useful for

Use cases llm-inferred: Literature review to support a flood-risk or drainage design assumption using /lit-review · Publication-style audit of model or monitoring charts before they go into a client report using /figure-review · Stress-testing a flood or water-quality modelling claim for baseline and uncertainty using /reviewer-2 · Senior-engineer review of an in-house analysis repo before handover using /ai-review
Audience llm-inferred: Researchers using Claude Code for scientific computing · Climate and atmospheric scientists · Scientific software developers · Analysts building AI-assisted analysis workflows

Limitations

Constraints docs-verified: Developed on macOS and Linux; on Windows the shell layer does not run, so skills with shell preambles (handoff, pickup, figure-review, repo-init) fail · Session auto-naming hook works only with iTerm2 or VS Code · Zotero write, Notion work journal and session-name generation need extra configuration · No datasets, gauge feeds or data APIs are described; the toolkit offers skills, reviewer agents and shell utilities only · No UK water, civils or environmental content is described

climate

Globalhealthy

mcp

76/100Currency A

data360-mcp ↗

Model Context Protocol (MCP) server that gives LLM agents and chatbots direct access to the World Bank's Data360 Platform. Search, validate, and retrieve development indicators—from GDP and poverty to gender equality and climate—with structured metadata and time-series data, without hallucinating values.

What's in it

Data offered docs-verified: development indicators (e.g. GDP, poverty, gender equality, climate) · indicator time-series data · indicator metadata (methodology, definitions, limitations, statistical concepts) · codelists (REF_AREA, SEX, AGE, etc.) · country coverage check per indicator
Coverage llm-inferred: Global (ENTRY regions field; not stated in DOCS)
Formats docs-verified: MCP (http transport, default) · MCP (sse transport) · Python package (PyPI: data360-mcp)
Access docs-verified: Open source: MIT licence together with World Bank IGO Rider (ENTRY licence field: 'Other'). No credentials documented in ENTRY. Pricing not stated in DOCS.

Useful for

Use cases llm-inferred: Country-level socio-economic baseline indicators (GDP, poverty) for international ESIA or socio-economic chapters · Climate-related indicator context for overseas water or civils options appraisal · Agent-assisted indicator search with country coverage check before drafting a report · Retrieve indicator time series with metadata for methodology notes in technical appendices
Audience llm-inferred: AI and chatbot developers building agents on World Bank data · environmental consultants (socio-economic baselines, ESIA) · water and civils consultants working on international projects · GIS analysts

Limitations

Constraints llm-inferred: Indicator data only; no UK-specific, gauge-level or site-scale data indicated · No spatial or temporal resolution or update cadence documented · Requires a local Python install and MCP client; default endpoint is localhost · Depends on upstream Data360 API availability; stale metadata may be reused during degradation · Licence field is 'Other' (MIT plus IGO Rider); review before redistribution · Documented API calls are read-only retrievals; no write or analysis tools listed

climate gis

Globalhealthy

mcp

76/100Currency A

foehn ↗

Download MeteoSwiss Open Government Data — weather stations, radar, hail, forecasts and climate series — via Python API, CLI, or MCP server, as DataFrames, Parquet, xarray Datasets or Zarr stores

What's in it

Data offered docs-verified: weather station data (CSV/TXT converted to Parquet) · radar composites (ODIM/HDF5) · hail maps · forecasts (GRIB2, ICON-CH1/CH2, KENDA) · climate grids, normals and scenarios (NetCDF)
Coverage docs-verified: Switzerland (MeteoSwiss Open Data)
Formats docs-verified: Polars DataFrame · Parquet · xarray Dataset · Zarr · CSV/TXT (input) · NetCDF · GRIB2 · HDF5/ODIM
Access docs-verified: Free/open: software is MIT-licensed; underlying data is MeteoSwiss open data; no credentials documented

Useful for

Use cases llm-inferred: Swiss station rainfall and temperature series for a project-site climate baseline · Radar precipitation composites for storm event reconstruction in Swiss catchments · NetCDF climate scenario grids for future rainfall sensitivity checks on Swiss projects · GRIB2 forecast fields for short-term weather context on Swiss site works
Audience llm-inferred: hydrologists · flood consultants · drainage engineers · GIS analysts · climate data analysts

Limitations

Constraints llm-inferred: Covers MeteoSwiss (Switzerland) data only; no UK coverage · Requires Python 3.11 or later · Gridded data (xarray/Zarr) needs the optional grids extra · Spark/Databricks ingestion is optional and not needed for local use · MCP tool names are not listed in the provided docs · Source data update frequency is not stated

climate gis

Switzerlandhealthy

mcp

75/100Currency A

mcp-swiss ↗

Swiss open data MCP server — transport, weather, geodata, companies, etc,. Zero API keys.

What's in it

Data offered docs-verified: public transport: stations, connections, live departures and arrivals (SBB, PostBus, trams) · MeteoSwiss current weather and historical weather · BAFU river and lake levels and temperature · swisstopo geocoding, reverse geocoding, solar potential and geographic layers · ZEFIX company registry search · public and school holidays by canton · federal and cantonal parliament data (OpenParlData.ch) · SLF avalanche bulletins and snow data · NABEL air quality stations and Swiss legal limits · Swiss Post postcode lookup and parcel tracking URLs · ElCom electricity tariffs · BFS population and statistics · SNB CHF exchange rates · Zurich waste collection calendar · SRF news headlines and search · Swiss popular vote results · federal dam registry · Swiss trail closures and hiking alerts · BFS property prices and rent index · ASTRA traffic counting stations · Swiss earthquake records (SED/ETH Zürich) · MeteoSwiss pollen concentrations
Coverage docs-verified: Switzerland
Formats docs-verified: MCP stdio
Access docs-verified: Free, open access: no API key, no registration, no server to run (MIT licence per ENTRY)

Useful for

Use cases llm-inferred: Swiss river baseline screening: nearby BAFU hydro stations and current water levels/temperature for a site (get_water_level, list_hydro_stations) · Swiss weather inputs for a project: MeteoSwiss station list and historical weather for a site period (list_weather_stations, get_weather_history) · Swiss site constraints screening: dam registry lookup by canton for a Swiss site (get_dams_by_canton) · Swiss air quality baseline: NABEL station data and LRV limits near a site (list_air_quality_stations, get_air_quality)
Audience llm-inferred: hydrologists · flood consultants · environmental consultants · GIS analysts · planners

Limitations

Constraints llm-inferred: Covers Switzerland only; no UK data, so not relevant to UK sites · Historical weather data is limited to a window of up to 32 days per request · Data is served from third-party Swiss agencies (BAFU, MeteoSwiss, swisstopo, etc.), so availability depends on those sources · Runs as a community npm/Docker package; maintenance risk sits with a single upstream repository · Loads 79 tools by default, which costs tokens; module filtering is needed for efficiency

climate gis

Switzerlandhealthy

mcp

75/100Currency A

ocean-mcp ↗

MCP servers for coastal oceanography

What's in it

Data offered docs-verified: NOAA CO-OPS tides, water levels, currents, meteorological data · ERDDAP dataset access across 80+ public servers · NHC storm tracks, advisories, HURDAT2 best track data · Hurricane reconnaissance HDOB, Vortex Data Messages, ATCF fixes · STOFS storm surge forecasts and observation validation · OFS regional ocean model forecasts (water level, temperature, salinity) · RTOFS global ocean forecasts (SST, salinity, currents, SSH) · WW3 GFS-Wave forecasts and NDBC buoy wave observations · NDBC buoy observations (waves, SST, wind, pressure) · NWS ASOS/AWOS surface wind observations · USGS streamflow, NWS/NWPS flood status, peak events · GOES-18/19 satellite imagery (visible, infrared, water vapor) · ADCIRC and SCHISM model setup debugging and config validation (tooling, not data)
Coverage llm-inferred: United States coastal and ocean waters (NOAA sources); RTOFS is global
Formats docs-verified: markdown · JSON · GeoJSON · image
Access docs-verified: Free and open; no API key for the data servers; MIT licence. hpc-system-mcp and ufs-runner-mcp need NOAA RDHPCS cluster access

Useful for

Use cases llm-inferred: US coastal flood-risk screening: CO-OPS water levels and flood statistics at a nearby tide station · Storm surge forecast comparison against tide-gauge observations for coastal flood assessment · Stream flow and NWS flood status checks near a US site via USGS Water Services · Wave and wind climate context from NDBC buoy observations for marine or coastal design
Audience llm-inferred: coastal engineers · hydrologists · oceanographers · GIS analysts · environmental consultants working on US projects

Limitations

Constraints llm-inferred: Coverage is US/NOAA-focused; no UK or European data sources are described · Several servers are not on PyPI and must be installed from source (vdatum-mcp, hpc-system-mcp, ufs-runner-mcp, alert-mcp) · hpc-system-mcp and ufs-runner-mcp require NOAA RDHPCS cluster access; ufs-runner-mcp submits real Slurm jobs · nos-workflow-mcp is experimental and not ready for general use · Data servers depend on upstream public NOAA, USGS and ERDDAP endpoints, so availability is outside the project's control · Monorepo has 13 published servers in the table, so each must be installed and configured separately

climate environment hydrology

Some details auto-extracted · unverified

United Stateshealthy

mcp

74/100Currency A

Open-Meteo MCP ↗

A comprehensive MCP server providing access to Open-Meteo weather APIs for Large Language Models

What's in it

Data offered docs-verified: weather forecast up to 16 days · ERA5 historical weather from 1940 · air quality (PM2.5, PM10, ozone, NO2, pollen, European and US AQI, UV index) · marine waves, swell and sea surface temperature · ensemble forecasts · seasonal outlook from a few weeks to about 7 months · CMIP6 climate projections 1950 to 2050 · river discharge via GloFAS (flood_forecast) · geocoding · elevation
Coverage llm-inferred: Not stated for the server as a whole. GFS is global, DWD ICON focuses on Europe and MET Norway on Nordic countries. UK is not named. · 1940 to yesterday (ERA5 archive); CMIP6 projections 1950 to 2050
Resolution llm-inferred: Temporal: hourly, daily and 15-minute series. Spatial resolution not stated.
Formats llm-inferred: JSON · MCP stdio · MCP streamable HTTP
Access docs-verified: Free for non-commercial use; no API key needed for the Open-Meteo APIs. Server licence MIT. API_KEY applies only to the server's own HTTP transport.

Useful for

Use cases llm-inferred: ERA5 rainfall and temperature history (weather_archive) for FRA or drainage baseline climatology · Forecast rainfall and wind for construction-phase site planning · GloFAS river discharge screening (flood_forecast) at site coordinates before gauge data review · CMIP6 climate projections (climate_projection) for climate-change allowances in drainage strategy
Audience llm-inferred: flood consultants · drainage engineers · hydrologists · planners · GIS analysts

Limitations

Constraints llm-inferred: Docs cover free use for non-commercial purposes only; commercial consultancy use must be checked against Open-Meteo terms · ENTRY auth lists API_KEY, but the docs say no key is needed for Open-Meteo; API_KEY only protects HTTP mode · Model-specific tools are regional (ICON for Germany/Europe, MET Norway for Nordic countries); UK coverage is not named · GloFAS flood discharge is modelled, not gauge observations · Responses over 25,000 characters are truncated; narrow the date range or variables to get full data · Response cache is in-memory only and not persistent · Archive ranges ending within the last 5 days are still being backfilled by Open-Meteo · Tool argument names in example_tool_calls are inferred from Open-Meteo API conventions, not from DOCS · Docs give no maintenance or release-status information

climate gis hydrology

Globalhealthy

dataset

73/100Currency A

World Bank Climate Change Knowledge Portal ↗

country climate projections

climate

Globalrestricted

mcp

73/100Currency B

mcp-canada ↗

MCP server for Canadian government data — 266 bilingual tools across 9 federal, 7 provincial & 2 municipal open-data APIs (Bank of Canada, StatCan, weather, recalls, drugs, immigration, BC/Alberta/Saskatchewan/Manitoba/Quebec/Ontario + more)

What's in it

Data offered docs-verified: exchange rates · interest rates · commodity prices · inflation · conditions · climate · air quality · hydrology (water levels, flow, flood risk) · marine · radar · product recalls · drug products and schedules · statistics time series · open datasets (CKAN catalogues) · provincial and municipal open data (ArcGIS Hub, WFS, Socrata)
Coverage docs-verified: Canada
Formats llm-inferred: JSON · MCP stdio (default) · MCP SSE/HTTP
Access docs-verified: Free and open source under MIT licence; no credentials documented in README

Useful for

Use cases llm-inferred: Canadian hydrometric flow and flood-risk context for a flood risk assessment on a Canadian site · Canadian climate and rainfall normals as inputs to drainage design on Canadian projects · Discovering Canadian open geospatial datasets (CKAN, ArcGIS Hub, WFS) for desk-based site baselines · Canadian exchange-rate or commodity price inputs for project costing
Audience llm-inferred: hydrologists · flood consultants · GIS analysts · environmental consultants working on Canadian projects

Limitations

Constraints llm-inferred: Canada-only data; no UK coverage, so of limited use for terramcp.earth's UK-focused work · Entry description states 266 tools, but DOCS state 295 tools · Depends on many upstream government APIs whose availability and rate limits are outside the server's control · Requires Python 3.12+ and uvx to run · No spatial or temporal resolution or update frequency documented

climate gis

Canadahealthy

mcp

73/100Currency B

mcp_weather_server ↗

A Model Context Protocol (MCP) server that provides weather information using the Open-Meteo API.

What's in it

Data offered docs-verified: current weather (temperature, humidity, dew point, wind, gusts, precipitation, pressure, cloud cover, UV index, visibility, feels-like) · hourly weather for a date range with daily sunrise/sunset · air quality pollutants (PM2.5, PM10, ozone, NO2, CO, SO2, ammonia, dust, aerosol optical depth) with health advisories · current date/time and timezone info · timezone conversion
Coverage llm-inferred: Global
Resolution docs-verified: Hourly for get_weather_by_datetime_range; city-name lookup (no coordinate input documented)
Formats docs-verified: MCP stdio · MCP SSE · MCP streamable HTTP · JSON (get_weather_details, get_air_quality_details)
Access docs-verified: Free/open, no API key required (Open-Meteo backend); Apache-2.0 licence

Useful for

Use cases llm-inferred: Air quality baseline (PM2.5, PM10, NO2) for an EIA or planning air-quality section · Rainfall, wind and temperature history over a date range to support site monitoring or construction-weather reporting · Current weather context for a site visit or field-survey log · Timezone-correct timestamp conversion for consultancy field records
Audience llm-inferred: environmental consultants · air quality specialists · drainage engineers · civils engineers · planners

Limitations

Constraints llm-inferred: Location is a city name in English only; no coordinate or site-level input is documented · Data is city-level, not site-specific, so not suitable for site-scale design inputs without validation · Depends on the third-party Open-Meteo API being available · SSE mode is described as legacy; streamable HTTP is the modern option · Not UK-focused in metadata (regions: Global); no UK-specific data sources or stated accuracy · No stated beta status, rate limits or SLA

climate

Globalhealthy

mcp

73/100Currency A

sailing-mcp ↗

Remote MCP server for sailing navigation — wind/wave forecasts, tides, currents, marinas, bridge schedules and live AIS. Stateless, multi-tenant (users bring their own API keys).

What's in it

Data offered docs-verified: wind forecasts · wave forecasts · tides (HW/LW, observed, forecast, surge) · tidal currents · marina, harbour and anchorage POIs · scheduled bridge openings · Notices to Skippers · fairway depths and bridge air-draft clearance · locks · METAR/TAF aviation weather · sunrise, sunset, twilight and moon phase · live AIS vessel snapshot · global tide predictions (key required) · multi-source tidal/ocean currents (key required)
Coverage docs-verified: Dutch / North Sea waters (strong focus); some tools are global
Formats docs-verified: MCP streamable HTTP
Access docs-verified: Public-data tools need no key. Windy, WorldTides, Stormglass and AISStream need the user's own API key passed in the URL; all except Windy have a free tier. Server licence MIT (per ENTRY metadata, not DOCS).

Useful for

Use cases llm-inferred: Tide and surge levels at Dutch coastal sites for marine works or outfall boundary checks (tides_nl) · Wind and wave forecast windows for coastal survey or dredging campaign planning · Bridge clearance and fairway depth checks for barge or crane access routes (fairway_nl)
Audience llm-inferred: coastal and marine engineers · hydrologists · civils and BIM engineers planning marine logistics · GIS analysts

Limitations

Constraints llm-inferred: Built and documented for recreational sailing, not engineering or regulatory use · Official charts, almanacs and notices must be checked before relying on outputs · Windy, WorldTides, Stormglass and AISStream need user-supplied API keys; keyed tools only appear when the key is present · AISStream is community-fed and sparse mid-ocean · Some bridges may show '(name unknown)' where OSM has no nearby named bridge · All tool times are UTC · Depends on third-party public endpoints (RWS, NDW, OSM/Overpass, aviationweather.gov, Open-Meteo) with no stated SLA · No public hosted endpoint is documented; the user must run or host an instance (docs use a 'your-host' placeholder) · ENTRY metadata lists OAuth, but DOCS describe API-key URL parameters and state 'No OAuth required' for Claude.ai · Likely single-maintainer personal project ('Built by @ai_kulikov'), so maintenance risk

climate environment hydrology civils-bim

Some details auto-extracted · unverified

Globalhealthy

Browse all 204 sources →