Catchment hydrology

Useful for

Use cases llm-inferred

Nearest-gauge river level and flow context for FRA baseline · Check live flood warnings and alerts for a site's catchment · Pull recent level and flow readings for hydrological baseline review · Locate monitoring stations within a set radius of a project site

Audience llm-inferred

flood consultants · hydrologists · drainage engineers

Limitations

Constraints docs-verified

No service level guarantee; not suitable for safety-critical applications · Upstream Environment Agency API is Beta · Responses may be cached for short periods · List tools capped at 500 items (default 50; readings default 100), 60 KB truncation; use limit/offset to paginate · Coverage conflict: docs say UK, ENTRY metadata says England

Useful for

Use cases llm-inferred

FRA baseline flows from nearest gauge: find sites by bbox, then pull daily mean discharge (00060) for the baseline period · Current conditions check at gauges during a flood or drought review, using percentile ranking as indicative only · Groundwater depth baseline from monitoring wells via parameter 72019 · Monitoring site inventory for a catchment by HUC code, filtered to sites with instantaneous data

Audience llm-inferred

hydrologists · flood risk consultants · drainage engineers · GIS analysts · ecologists (groundwater and surface water baselines)

Limitations

Constraints llm-inferred

Covers US and territories only; no UK data · Percentile ranking is approximate and is not a flood-stage or drought determination · Readings return up to 100 sites per call, with at most 100 series and the 10 most recent records per series · Series inline output is capped at 500 records; larger results need CANVAS_PROVIDER_TYPE=duckdb · Dataframe tools and spillover require CANVAS_PROVIDER_TYPE=duckdb; table drop is opt-in via WATER_DATAFRAME_DROP_ENABLED · Pre-1.0 release (v0.3.0), so the interface may change · Relies on the USGS NWIS service being available; upstream failures are returned as retryable errors · Public hosted endpoint is not operated by USGS and has no stated uptime guarantee

Useful for

Use cases llm-inferred

Hydrology baseline from nearest Swiss gauging station (levels, flows) for water-resource projects · Air quality baseline check against Swiss LRV and WHO 2021 limits for EIA screening · Aircraft noise screening of planning sites using LV95 coordinates · Natural hazard screening (flood, avalanche, wildfire) in site due diligence

Audience llm-inferred

hydrologists · environmental consultants · planners · GIS analysts

Limitations

Constraints docs-verified

Swiss data only; not applicable to UK sites · Hydro station search has no canton filter; flood warnings are nationwide with no canton filter · env_hydro_history returns latest value plus an access path for real-time series, not full series · Aircraft noise contours are isolines: results are a dB bracket/upper bound, orientation aid only, not legally binding · Coordinates must be LV95 (EPSG:2056); WGS84 input is rejected · Hazard overview/regions tools are routers only; the naturgefahren.ch aggregate API was discontinued · Per-query caps apply and each API call times out after 30 seconds · Subject to upstream terms of service (BAFU, hydrodaten.admin.ch, naturgefahren.ch, waldbrandgefahr.ch) · Requires Python 3.11+ for local install · Tool budget is declared exhausted (21 tools); metadata lists tools as empty

Useful for

Use cases llm-inferred

Discover candidate NASA satellite precipitation or elevation datasets for supplementary catchment context · Check granule availability over a site and date range before scoping a remote sensing data request · Find OPeNDAP or WMS access endpoints for environmental baseline layers · Locate citable publications and DOIs for a dataset used in a technical report

Audience llm-inferred

GIS analysts · hydrologists · environmental consultants · remote sensing specialists

Limitations

Constraints llm-inferred

Global NASA datasets, with no UK-specific coverage stated; coverage must be verified per region · Collections can declare global coverage despite data gaps, so granule checks are needed · The discover_data tool and its ingestion pipeline are legacy and being deprecated · Clients should allow a 60000 ms timeout for complex spatial or temporal queries · Downloads require the earthaccess library and its authentication · No rate limits or service-level commitments are documented

Useful for

Use cases llm-inferred

Catchment land cover and forest cover percentage for flood risk assessment inputs · Flood extent area from imagery using threshold_area for post-event mapping · NDVI/NDWI change between periods via multi_period_analysis for ecological baselines · Zonal statistics of DEM or land cover over a catchment for morphometry

Audience llm-inferred

GIS analysts · hydrologists · flood consultants · ecologists · environmental consultants using AI-assisted workflows

Limitations

Constraints docs-verified

Requires Google Earth Engine authentication and a GEE project ID · AI code-generation tools need an LLM provider API key · Local install required (Poetry, clone repo); Python 3.11 to 3.14 · Catalogue auth field lists only LLM keys and omits GEE credentials · AI-generated GEE code and factuality outputs need expert verification · No rate limits, SLA or maintenance status stated in docs

Useful for

Use cases llm-inferred

Historical daily PRCP and TMAX/TMIN series from the nearest GHCND station for a US project climate baseline · Storm Events flood and hail records for a US state and year as hazard evidence in a risk assessment · Billion-Dollar Disaster cost and frequency context for resilience or adaptation reporting · Screen station data-coverage dates before fetching observations for a US hydrology or drainage study

Audience llm-inferred

hydrologists · climate risk analysts · civils engineers on US projects · GIS analysts · planners

Limitations

Constraints llm-inferred

Data is US-focused (ENTRY regions: United States; docs reference US states and NCEI corpora), so it has limited use for UK projects · Requires a free NOAA CDO token for CDO tools · CDO fetch_data span caps: 1 year for GHCND and PRECIP/NEXRAD/NORMAL daily-hourly datasets, 10 years for GSOM, GSOY, NORMAL_MLY, NORMAL_ANN · GHCND values are raw tenths-of-unit integers unless units is set to metric or standard · Storm Events limited to one year per query, and fails for years NCEI does not publish · Billion-Dollar Disasters coverage ends at the last year NCEI has finished assessing · Public hosted endpoint is third-party and not guaranteed; self-hosting adds maintenance · No CDO rate limits stated in docs

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

Useful for

Use cases llm-inferred

Find Sentinel-2 or Landsat scenes over a UK catchment bbox for pre- and post-flood imagery · Estimate download size of satellite tiles before pulling data for a BNG habitat baseline · Locate DEM or land-cover STAC collections for drainage strategy catchment analysis, where the target catalog hosts them

Audience llm-inferred

GIS analysts · flood consultants · hydrologists · ecologists · drainage engineers

Limitations

Constraints llm-inferred

Results depend entirely on the STAC catalog queried; no catalog is bundled · get_queryables returns an empty set if the catalog does not implement the endpoint · get_aggregations returns a message rather than data if the catalog does not support aggregation · sign_assets only applies to Microsoft Planetary Computer catalogs · estimate_data_size depends on odc.stac and XArray and falls back to estimates when odc.stac fails · Install URL in DOCS (wayfinder-foundry/stac-mcp) differs from ENTRY url (BnJam/stac-mcp); confirm the source repository before use · DOCS refer to a planned FastMCP integration (issues #69, #78) that is not yet delivered · No authentication is documented, so private or authenticated STAC APIs are not covered

Useful for

Use cases llm-inferred

Automate loading site, catchment and boundary layers, checking CRS and zooming to extents for flood or drainage report figures · Run zonal statistics and raster sampling on DEM or rainfall rasters to prepare drainage strategy inputs · Apply styled, labelled layers and layouts to produce BNG habitat baseline maps

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · ecologists · planners

Limitations

Constraints docs-verified

Needs a running QGIS desktop session with the plugin's server started; it is not a standalone data source · Plugin (inside QGIS) and MCP server (outside QGIS) must be kept in version sync · uvx caches the server archive, so updates need a forced refresh; auto-update requires network at launch

Useful for

Use cases llm-inferred

Nearest river-level and flow gauge lookup for FRA baseline flow context · Historic level and flow readings via startdate/enddate for hydrological model calibration · Flood warning and flood area screening within a radius of a site (lat/long/dist filter) · Latest rainfall and level readings as a context check for drainage strategy studies

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · GIS analysts · civils engineers

Limitations

Constraints docs-verified

Labelled a trial/beta service; feedback requested · No service-level guarantee; should not be relied on for safety-critical applications · Does not replace the Agency's official channels for notifying the public of floods · Responses may be redirected at high load or in future versions; clients must follow standard HTTP redirects · Responses may be cached briefly; custom filtering reduces cache hits · Readings are sometimes updated in batches, so a complete history needs the since filter · Some endpoints impose a length limit by default; check the metadata limit and offset values · No rate limit documented; the docs recommend one call every 15 minutes (data/readings?latest) rather than crawling every station

Useful for

Use cases llm-inferred

FRA baseline flows and levels from nearest gauge · Rainfall and river level context for flood event review · Groundwater level baseline for site investigation or geotechnical assessment · Water quality baseline (dissolved oxygen, turbidity, nitrate) for ecological or pollution assessment

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · ecologists · geotechnical engineers · GIS analysts

Limitations

Constraints docs-verified

Hard limit of 2,000,000 rows per call that cannot be overridden; soft limit of 100,000 rows per call (overridable with _limit) · Hard limit is subject to review and may be reduced if the service is overloaded · Bulk downloads should use the batch API; otherwise keep to one non-batch request in flight at a time · Concurrency limits may be enforced per IP address, and excessive demand may lead to blocking · Logged groundwater sub-daily values may mix 15-min and hourly intervals · Station identifiers are not always unique; some stations need a composite key with a wiskiID · HTML views are intended for debugging and development, not for presentation to consumers

Useful for

Use cases llm-inferred

Baseline river flow and gauge record review for FRA inputs from nearest USGS gauge (US sites only) · Flood event analysis from continuous sensor records at gauged catchments · Water quality baseline sampling review for environmental assessment (US sites only) · Gauge camera imagery for site visit verification and condition checks

Audience llm-inferred

flood consultants · hydrologists · GIS analysts · environmental scientists · water quality specialists

Limitations

Constraints llm-inferred

Covers United States monitoring locations only; not applicable to UK sites · Rate limits apply without an API key · Licence not specified in catalogue metadata · Multiple API families (OGC, STAC, legacy Water Services, NIMS) may require different query patterns · NIMS imagery requires constructing full image URLs from camera base paths and returned filenames

Useful for

Use cases llm-inferred

Catchment terrain and slope analysis for an FRA study area from a bbox DEM · Topographic levels for drainage strategy and earthworks setting-out inputs · Terrain base layer for GIS site analysis

Audience llm-inferred

GIS analysts · hydrologists · drainage engineers · civils engineers

Limitations

Constraints llm-inferred

Licence varies by dataset · API key required · No docs retrieved, so capabilities and coverage are unverified

Useful for

Use cases llm-inferred

Flood screening for a site in a transboundary or large catchment · Regional context for an FRA desk study · Checking global flood awareness signals alongside local gauge data

Audience llm-inferred

flood consultants · hydrologists

Limitations

Constraints llm-inferred

No DOCS retrieved, so capabilities, resolution, formats and update cadence are unverified · Copernicus licence terms need checking before reuse in client deliverables

Useful for

Use cases llm-inferred

Calibrate a hydrological model against observed river discharge for a catchment · Validate remote sensing or model outputs with in-situ flow records · Regional or global catchment flow statistics for water resources assessment · Catchment boundary and basin context from GRDC basin layers

Audience llm-inferred

hydrologists · water resources engineers · flood consultants · GIS analysts · researchers

Limitations

Constraints llm-inferred

Access subject to station/data terms; licence not stated in catalogue · No API or MCP tools listed in catalogue · Station coverage and record length vary; UK-specific coverage not stated · Data is discharge-focused; other water quality or groundwater variables not indicated

Useful for

Use cases llm-inferred

FRA catchment context: delineate contributing catchment boundaries from HydroSHEDS basins · Drainage strategy: river network and lake layers for receiving-watercourse context · Ecology/BNG baseline: river and lake network mapping for habitat context

Audience llm-inferred

hydrologists · flood consultants · drainage engineers · GIS analysts · ecologists

Limitations

Constraints docs-verified

HydroSHEDS v2 is released for the Americas; the global v2 (TanDEM-X based) is still in development · Specific resolutions, update cadence and licence terms are not stated in DOCS

Useful for

Use cases llm-inferred

Flood risk assessment: ground-level inputs for hydraulic model topography · Drainage strategy: surface levels for catchment and overland flow delineation · Civils design: existing ground model for earthworks and levels

Audience llm-inferred

flood consultants · drainage engineers · hydrologists · GIS analysts · civils engineers

Limitations

Constraints llm-inferred

No docs retrieved, so coverage, formats, resolution and access terms are unverified · Auth and licence not recorded in entry

Useful for

Use cases llm-inferred

Gauge-based streamflow baseline and flow signatures for a catchment · Watershed delineation and morphometry for catchment characterisation · TWI and Curve Number grids as inputs to runoff screening · Basin-averaged climate forcing extraction for hydrological model inputs

Audience llm-inferred

hydrologists · flood consultants · GIS analysts · researchers

Limitations

Constraints llm-inferred

Named data sources are US federal (USGS NWIS, NHDPlus, GridMET, 3DEP, NLCD, POLARIS, CAMELS-US); no UK data sources documented · ENTRY regions say 'Global' but DOCS describe US-only sources · Requires a Python install and the aihydro-mcp server; not a hosted service · ENTRY tools list (quality_flags, aihydro.tools, ...) does not match the tool names in DOCS · DOCS are truncated; full tool parameter schemas are not visible · Depends on external services (USGS NWIS, NLDI, GridMET); availability not guaranteed

Useful for

Use cases llm-inferred

Pull 7-day stream flow and gage height for a gauged US river reach as hydrology inputs · Locate USGS monitoring stations within a project bounding box for baseline data review · Check currently flooding reference points as context for US flood-impact comparisons

Audience llm-inferred

hydrologists · flood consultants · GIS analysts · environmental scientists

Limitations

Constraints llm-inferred

US-only data (USGS network and US state codes); not applicable to UK catchments · USGS API has usage limits; avoid rapid repeated requests · Some sites may have no data for the requested period or parameters · Requires local Python install (pip install -e . or httpx and mcp) and Claude Desktop config · current_water_levels.py is a deprecated legacy file

Useful for

Use cases llm-inferred

Screen rivers, watersheds, dams and impaired waters for a non-UK project site as a desk-based context map · Locate USGS gauges or water quality stations near a site for baseline data discovery · Pull weather or CORS station locations to scope rainfall or GNSS monitoring for an environmental assessment

Audience llm-inferred

GIS analysts · hydrologists · flood consultants · environmental consultants

Limitations

Constraints llm-inferred

Docs do not state UK coverage; the listed sources (USGS gages, RAWS) are US-based, so UK use needs checking · Requires a local install: pip install fastmcp requests, and Node.js for the optional frontend · Resolution, update frequency and Living Atlas data licence are not documented · Auth is null in ENTRY and the access model for the underlying Esri services is not documented · Maintenance status and version are not stated

Useful for

Use cases llm-inferred

FRA baseline weather and river-level context for a GB site, using Environment Agency gauge levels against typical range · Historical weather review back to 1940 for drainage or flood event investigations · Forecast, lightning and alert checks to support site visit and fieldwork planning · Air quality and pollen checks for ecological or construction site work in Europe

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · environmental consultants

Limitations

Constraints docs-verified

Some tools are US-only · Free public APIs come with fair-use rate limits · Minutely precipitation nowcast only in North America and Central Europe

Useful for

Use cases llm-inferred

Active-travel and walking route options along rivers and green corridors for a site access assessment · Indicative public-access path mapping to nearby parks and waterways for planning-stage site context · Sketching GPX/GeoJSON walking routes for site walkover or public-consultation material

Audience llm-inferred

planners · GIS analysts · ecologists

Limitations

Constraints llm-inferred

Walking route tool only; provides no river level, flow or other hydrological data despite the hydrology category · Requires self-hosting with Docker (about 8 GB disk and 4 GB RAM); not a hosted service · First setup takes roughly 20–60 minutes to import OSM data and build tiles · Default region is Greater London; other areas need OSM_REGIONS reconfiguration · Scenic weighting is a soft preference and cannot guarantee routes pass through scenic areas · Public deployment needs extra setup (nginx API key or Cloudflare Tunnel); default ports bind to localhost

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

Useful for

Use cases llm-inferred

FRA screening: modelled GloFAS river discharge baseline at site coordinates (no gauge data) · Climate change context for drainage design: CMIP6 daily projections for 2050 horizons · Site terrain screening: Copernicus DEM elevation at point coordinates for earthworks and drainage routing · Open-coast scheme inputs: wave height and swell conditions

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · civils engineers · climate resilience consultants · GIS analysts

Limitations

Constraints llm-inferred

Global dataset; DOCS describe no UK-specific sources or validation · Air quality is modelled grid data, not station measurements · Pollen is modelled for Europe only, and only in pollen season · River discharge comes from the largest modelled river within 5 km, not always the nearest; null outside GloFAS coverage · cerra covers Europe only; regional models queried outside coverage fail · ERA5-family historical data runs about 5 days behind; ecmwf_ifs has no delay · Marine: sheltered water returns near-zero waves; land points return nulls · Climate projections are daily-only · Elevation is a ~90 m DEM, not survey-grade · Upstream rate limits fail as rate_limited · Large results spill to a DuckDB canvas only when CANVAS_PROVIDER_TYPE=duckdb · Auth mode unverified in DOCS

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

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

Useful for

Use cases llm-inferred

Catchment area and centroid calculation from boundary files (read_file_gpd, get_area, get_centroid) for FRA or drainage baselines · Reproject site boundaries and survey points to British National Grid (EPSG:27700) before overlay (project_geometry, reproject_raster) · Zonal statistics of DEM or rainfall rasters within catchment polygons (zonal_statistics) for drainage or flood-risk inputs · Clip and overlay habitat or constraint layers with site boundaries (clip_vector, overlay_gpd) for BNG baseline mapping

Audience llm-inferred

GIS analysts · hydrologists · flood consultants · drainage engineers · ecologists

Limitations

Constraints llm-inferred

Version 0.15.0 is beta, so the API may change · Requires Python 3.10 or higher · Google Cloud Storage backend needs the gis-mcp[gcp] extra plus credentials and IAM setup · Docs do not describe per-tool inputs, outputs, or CRS and resolution behaviour · Catalogue tool list has 59 tools with none for climate, ecology, movement or boundary data, although the docs claim 92+ tools that include those categories; confirm which tools ship · No UK-specific datasets (e.g. EA gauges, OS, DEFRA) are listed; coverage is generic GIS tooling · Data-gathering categories depend on external sources whose availability and rate limits are not documented

Useful for

Use cases llm-inferred

Inspect and repair invalid layers in an existing flood risk or drainage QGIS project, then improve cartography · Build a print layout of a site or catchment study area and visually review the rendered map before issue · Run Processing steps such as clipping or reprojection on consultancy GIS data within the open QGIS session

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · civils and BIM engineers

Limitations

Constraints llm-inferred

Requires a live QGIS Desktop session; it does not operate on data without QGIS running · Aesthetic map review needs a vision-capable AI client · Plugin recommendations exclude deprecated plugins and treat experimental plugins as opt-in · Validated on QGIS LTR 3.44.12 and QGIS 4.2 only, per the docs

Useful for

Use cases llm-inferred

Reproject a site or survey raster to a UK projected CRS (e.g. EPSG:27700) with a recorded CRS justification before flood or drainage modelling · Clip and buffer vector site boundaries and study areas for a desk study or planning constraints check · Compute raster statistics on DEM or elevation tiles for catchment or drainage screening · Batch convert and simplify GIS layers into consistent formats for client handover

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · hydrologists · ecologists · planners

Limitations

Constraints docs-verified

Reflection middleware: tools whose methodology matters (e.g. raster_reproject, CRS choice, resampling) raise ToolError until a structured justification is supplied · Path access is restricted to GDAL_MCP_WORKSPACES; if unset, all paths are allowed and a warning is logged · Raster and vector tool sets are optional via RASTER and VECTOR environment flags · Input and output path parameters are not shown in DOCS; full parameters are in TOOLS.md, which was not supplied

Useful for

Use cases llm-inferred

NDVI or land-cover change over a site boundary for a BNG habitat baseline · Sentinel-2 cloud-filtered imagery review for a pre-development site condition survey · Zonal statistics of land use within a catchment as input to a flood risk or drainage desk study · Water-body extent change over time from Landsat for environmental permit or monitoring context

Audience llm-inferred

GIS analysts · ecologists · hydrologists · planners · environmental consultants

Limitations

Constraints docs-verified

Chrome Web Store version does not support local connections (MCP Server or Ollama); MCP requires the Developer Version from GitHub · Agent can only see code in temp/new scripts in the Google Earth Engine Code Editor, so scripts must be saved first · Z.AI models do not support screenshot analysis · Ask Mode is read-only and cannot insert, modify or execute code; Do Mode is required for execution

Useful for

Use cases llm-inferred

Cloud-free dry-season NDVI/NDWI baseline for an ecology or BNG habitat assessment · Land-cover training polygons from ESA WorldCover for a site-scale classification · Area-wide vegetation and water-index statistics for a catchment or planning screening report

Audience llm-inferred

GIS analysts · ecologists · hydrologists · planners

Limitations

Constraints llm-inferred

Requires Python 3.10+, a Google Earth Engine account and a Google Cloud project with the Earth Engine API enabled · Earth Engine access is free for research and non-commercial use; commercial consultancy use needs checking against Google's terms, which DOCS do not address · execute_code runs arbitrary Python on the local machine with the user's Earth Engine login; do not expose the server to untrusted clients · Initial earthengine authenticate step opens a browser · Roadmap features not yet available: Dynamic World and Hansen training labels, consensus logic, shapefile/KML/GPX/CSV import, local GeoTIFF backend, OpenStreetMap ingest, STAC backend, change-detection helpers · Land-cover classification workflow needs the optional lulc-engine package · No UK-specific datasets (e.g. river gauges, LiDAR DEM) are documented; these would need to be found in the Earth Engine catalog or added via execute_code · Spatial and temporal resolution and update frequency are not stated · Maintenance status and version history are not documented

Useful for

Use cases llm-inferred

Flood risk context: GloFAS/EFAS river discharge series as catchment baseline inputs · Climate allowance inputs: ERA5 reanalysis extracts for drainage or flood risk climate-change baselines · Coastal studies: CMEMS wave and sea-level subsets as context for coastal flood or outfall design

Audience llm-inferred

hydrologists · flood risk consultants · drainage engineers · coastal engineers · GIS analysts

Limitations

Constraints docs-verified

Catalogue snapshots may lag the live Copernicus catalogues · CDS-family downloads depend on upstream queue availability; large requests may take minutes to hours · Size estimates are approximate and must not be used for quotas, billing or disk provisioning · Hierarchical routing is pattern-based; misroutes on ambiguous queries are possible · Requires Copernicus credentials and one-off dataset licence acceptance for some CDS datasets · Download location is fixed at server startup · CDSE, Sentinel Hub and WEkEO are planned but not yet supported · Requires Python 3.11+

Useful for

Use cases llm-inferred

Flood extent and onset from Sentinel-1 SAR after a storm event (sar_flood, sar_water) for flood risk assessment evidence · Upstream river flow context versus period mean at a site (river_discharge) for FRA baseline flows · Vegetation and water change detection across two dates at a site (eo_compare, eo_index) for pre- and post-works comparison · Long-run temperature and precipitation trend for a site (climate_history) for drainage design climate context

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · GIS analysts · ecologists · planners

Limitations

Constraints llm-inferred

Not UK-specific: no UK gauge network or UK-specific dataset is listed in the docs · forest_alerts covers the tropics only · Copernicus, FIRMS and GFW tools need API keys or credentials · UNEP MARS methane data unavailable (no public API) · Project is new; the Earth Watch ledger feature is marked new (M1) · Many tools depend on third-party public APIs, so maintenance and availability risk is external

Useful for

Use cases llm-inferred

NDVI/SAVI vegetation-health screening of a site or catchment from Sentinel-2 for baseline ecology or land-use context · NDWI/MNDWI water-extent mapping of a UK reservoir, lake or floodplain for flood or drought context · NDBI built-up mapping and multi-date composites to track development change around a site · Random Forest land-cover classification with custom training points for habitat or land-use baselines

Audience llm-inferred

GIS analysts · ecologists · hydrologists · environmental consultants · planners · drainage engineers

Limitations

Constraints docs-verified

Hosted server runs on Render's free tier and may take 30 seconds to wake when idle · axion_sar2optical is only available through the hosted server · Exports over 10MB need S3, which requires AWS credentials and a bucket · NAIP imagery is US only · All data is accessed via the AWS Earth Search STAC API, a third-party dependency

Useful for

Use cases llm-inferred

Pre-survey screening of low-cloud Sentinel-2 scenes for a site AOI over a chosen date window · Terrain inputs from Copernicus DEM for catchment or drainage outfall assessment · Land-cover baseline from ESA WorldCover or IO LULC for habitat or planning context · Building footprint extraction from MS Buildings for flood exposure or drainage catchment screening

Audience llm-inferred

GIS analysts · hydrologists · drainage engineers · ecologists · planners

Limitations

Constraints llm-inferred

Supported datasets are listed in an external collections.md, which is not included in the provided docs · Place-name geocoding depends on the external Nominatim service · No UK-specific coverage or resolution details stated in the docs · Release history and maintenance status not stated in the docs

Useful for

Use cases llm-inferred

FRA context: national river and lake layers for regional water-body mapping · Site context screening: boundary, transport and pipeline layers around a project site · Constraint screening: intersect pipeline or transport features with a study area using execute_sql · Desk-study GIS base layers for China-based projects

Audience llm-inferred

GIS analysts · planners · hydrologists (regional context only) · civils engineers (regional context only)

Limitations

Constraints llm-inferred

Data currency 2019 for the 2021 public edition · 1:1,000,000 scale is too coarse for site-level or detailed drainage/flood modelling · China-only coverage; CGCS2000 / SRID 4326, not British National Grid (EPSG:27700) · No UK datasets; cannot substitute for UK sources such as OS, EA or NRFA data · Requires local PostgreSQL/PostGIS setup, GDAL/OGR and manual GDB import via scripts before use · Data import is script-based, not an MCP tool; execute_sql allows SELECT only · Maintenance and support commitments are not stated in the docs

Useful for

Use cases llm-inferred

Geocode site addresses to coordinates for a desk-based constraints screen · Locate watercourses, outfalls or pumping stations within a radius of a site for a drainage or FRA context map · Pull OSM features inside a local authority or catchment boundary for a planning or ecology baseline · Reverse geocode survey points to their nearest address for site records

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · ecologists · planners

Limitations

Constraints docs-verified

Nominatim is limited to one request per second; request starts are spaced 1,050 ms apart · Nominatim tools select objects by name, address, proximity or ID only, never by tag · Overpass tag filters take literal text; regex, alternation and negation require openstreetmap_query_raw · Overpass pages cap at 500 features and place search at 40 results per call · Overpass area data age is reported as areasTimestamp; a boundary ref that maps to no area returns an empty page · Data is ODbL-licensed and every response carries the ODbL attribution · Public Nominatim and Overpass endpoints are shared; heavy use needs a self-hosted or mirror instance · Server auth defaults to none (MCP_AUTH_MODE); OAuth is an optional server setting, not an upstream requirement

Useful for

Use cases llm-inferred

FRA baseline: watercourses and waterbodies within a site bounding box via get_waterways · BNG habitat baseline screening: green spaces (forest, meadow, grass, farmland) as desk-based land-cover context · Site context mapping: roads and railways for access and noise-source screening · Drainage strategy: building footprints in a catchment bounding box for a rough impermeable-area estimate

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · ecologists · planners · GIS analysts

Limitations

Constraints docs-verified

DOCS recommend use only for education, research and non-profit purposes; commercial consultancy use needs checking against OSM and Overpass usage terms · Recommended bounding box 0.005° × 0.005° or smaller (about 500 m); maximum 0.001 square degrees to avoid timeouts; building queries are costlier than road queries · DOCS recommend no more than 1 request per second; results cached for 15 minutes (TTL) · Depends on public Overpass API servers with a 3-server fallback; availability not guaranteed · DOCS examples and performance figures are Tokyo-only; UK coverage and data quality not documented · Last changelog entry is v1.1.0 dated 2025-07-08; maintenance activity uncertain as of 2026-10 · ENTRY tools field lists input_path, output_path and query, which are parameter names, not tool names · OSM attribution and ODbL obligations not addressed in DOCS

Useful for

Use cases llm-inferred

Isochrone catchment around a site for accessibility screening (calculate_isochrone) · Snapping survey or GPS points to the OSM road network before analysis (snap_to_roads, map_match_gps) · Checking OSM data quality (OSMOSE issues) in an area before reusing it as a baseline · Route distance and travel-time matrices for site-visit planning (get_distance_matrix)

Audience llm-inferred

GIS analysts · planners · environmental consultants · developers building AI/MCP workflows

Limitations

Constraints llm-inferred

Local install required: Node.js v18 or higher, plus an npm build step · Community project by Grab; no support or SLA stated · Relies on third-party services (Nominatim, OSRM, Overpass, OSMOSE, Taginfo) whose availability and rate limits are not described · Global OSM scope; no UK-specific coverage described · No update frequency, resolution or time span stated · Tool parameter schemas and output formats are not documented in DOCS · Entry lists no tools; tool names are taken from DOCS

Useful for

Use cases llm-inferred

Baseline water quality and streamflow screening near a site from nearest USGS monitoring stations (US sites) · Permitted discharger and effluent violation screening upstream of a development site (US sites) · 303(d) impaired waters and TMDL status check for a site's receiving water during environmental screening · Species presence and occurrence records for an ecological desk study

Audience llm-inferred

environmental consultants · hydrologists · ecologists · GIS analysts · planners

Limitations

Constraints llm-inferred

Core sources (USGS, NOAA, EPA) are US federal datasets; UK coverage is not evidenced in the docs · USGS tool only returns stations with active real-time sensors near the coordinates; some sites may return no data · airnow_air_quality needs a free AirNow API key, which conflicts with the catalogue auth field saying no key is required · Act tools are not implemented yet; the server currently only reads data · Docs describe the project as a starting point, so maintenance and stability are unproven · Depends on third-party APIs (USGS, NOAA, EPA, iNaturalist, GBIF, AirNow) remaining available

Useful for

Use cases llm-inferred

Export print-quality layouts and Map Series from an ArcGIS Pro project for consultation or planning reports · Run clip, buffer or intersect geoprocessing on site or catchment layers and add outputs to the live map for review · Query layer attributes to build constraint or receptor tables for an assessment · Let an agent assemble and symbolise a thematic map in the open project while the consultant watches

Audience llm-inferred

GIS analysts · flood risk consultants · drainage engineers · planners · ecologists

Limitations

Constraints docs-verified

Requires a licensed ArcGIS Pro install; no ArcPy outside Pro · Live bridge needs the .NET add-in built and installed in Pro, plus MCP registration · Verified only on ArcGIS Pro 3.4 / ArcPy 3.4.3 / .NET 8 · Cartographic authoring (symbology, layout, layer management) is still an open frontier on the roadmap · Noncommercial licence; commercial use needs a paid licence · Tool arguments and parameter names are not documented in the README

Useful for

Use cases llm-inferred

Batch field additions and attribute calculations on drainage or site layers, driven from an AI chat prompt · Running GP tools (e.g. Buffer, Clip, Dissolve, Statistics) on flood-extent or catchment layers without manual geoprocessing dialogs · Exporting CAD/Excel outputs for civils or BIM handover, with outputs opened or added to the map automatically · Checking the open project and layer inventory before reporting on a planning or land-use GIS dataset

Audience llm-inferred

GIS analysts · civils/BIM engineers · drainage engineers · planners · hydrologists

Limitations

Constraints docs-verified

Windows 64-bit only; requires ArcGIS Pro 3.4+ · Requires ArcGIS Pro to be running · No authentication; service bound to 127.0.0.1 and must not be exposed to the local network · Destructive operations need explicit second confirmation from the user

Useful for

Use cases llm-inferred

Slope classification of a site DEM to support earthworks and drainage feasibility · Riparian buffer around watercourses, erased from a site boundary before developable area is calculated · Watershed delineation and catchment area from a DEM for drainage strategy inputs · Zonal slope statistics per parcel, plot or zone for site appraisal reporting

Audience llm-inferred

GIS analysts · hydrologists · drainage engineers · planners · civils engineers

Limitations

Constraints llm-inferred

Built for ArcGIS Pro 3.x on Windows; paths and config are Windows-specific · Terrain and raster tools need a Spatial Analyst licence · Runs as a stdio subprocess with one connection per client · arcpy calls are synchronous, so long jobs need a stable ArcGIS Pro connection · Documentation is in Indonesian and the CRS examples are Indonesian (UTM 47-50, DGN95) · No licence information in metadata · Metadata region is Global, but the stated design target is Indonesian palm oil plantation GIS teams

Useful for

Use cases llm-inferred

Scripting QGIS project setup from prompts: create project, load boundary and DEM layers, zoom to AOI · Running centroid or other processing algorithms on catchment or parcel layers with saved outputs · Generating choropleth or constraint map renders for planning and FRA figures · Prototyping PyQGIS analysis scripts before moving them into a production workflow

Audience llm-inferred

GIS analysts · flood consultants · hydrologists · planners · drainage engineers

Limitations

Constraints llm-inferred

Only tested on QGIS 3.22 and 3.34 · QGIS desktop must be open with the plugin server started manually · execute_code runs arbitrary Python and the docs advise caution · Community fork of jjsantos01/qgis_mcp; maintenance risk · No authentication documented

Useful for

Use cases llm-inferred

Prompt-driven loading and styling of site or catchment layers into a QGIS project · Running Processing algorithms such as centroids on consultancy vector data · Rendering map figures for FRA or planning report appendices · Scripted PyQGIS attribute checks on shapefile or GeoPackage datasets

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · hydrologists · planners

Limitations

Constraints llm-inferred

Requires QGIS running locally with the plugin socket server started manually · Docs state QGIS 3.X but only tested on 3.22 · execute_code runs arbitrary Python and needs caution · DOCS describe jjsantos01/qgis_mcp, but ENTRY URL is the kicker315 fork, so behaviour may differ · No data coverage: this is a tool, not a dataset · Tool parameter schemas are not given in DOCS

Useful for

Use cases llm-inferred

Buffer drainage outfalls or watercourse setback zones for a site boundary or constraints layer · Overlay flood-zone or habitat polygons with a development site to screen constraints · Run GDAL raster or vector preprocessing on GIS inputs before hydrology or drainage modelling

Audience llm-inferred

GIS analysts · civils engineers · drainage engineers · environmental consultants · developers building LLM-driven QGIS agents

Limitations

Constraints llm-inferred

Requires QGIS 3.22+ with Python bindings installed locally · Requires Python 3.10-3.11 · All 14 services must be started locally (ports 32821-32834) before the agent can connect · Natural-language task handling depends on an external OpenAI or compatible LLM API · README contains placeholder repository links, so maintenance status is unclear

Example tool calls docs-verified

{
  "tool": "buffer",
  "arguments": {
    "INPUT": "/path/to/input.shp",
    "DISTANCE": 500,
    "OUTPUT": "/path/to/output.shp"
  }
}

Useful for

Use cases llm-inferred

Pre-flight CRS, extent and null-geometry checks on client layers in QGIS before a flood or drainage model build · Render the current QGIS map view to an image for a site-context figure in a report · Run QGIS Processing algorithms (e.g. clipping catchment layers) from a Codex session

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · hydrologists

Limitations

Constraints llm-inferred

execute_code runs arbitrary PyQGIS inside QGIS Desktop and should be used sparingly · QGIS Desktop must be open with the plugin server running on port 9877 · Setup is documented for Windows (PowerShell packaging helper, Windows paths) · Port conflicts need manual edits to the plugin UI and the bundled server default · Derived from the Claude-oriented jjsantos01/qgis_mcp project; no licence stated

Useful for

Use cases llm-inferred

Editable QGIS map and print layout of site or gauge points from a client spreadsheet for a flood or drainage report · Interpolated surface or contour map from point survey readings for a ground-conditions or drainage strategy appraisal · Getis-Ord Gi* hotspot or KDE map of asset or incident locations for a planning or environmental baseline · Bivariate or graduated choropleth atlas of catchment or area-based statistics for a client deliverable

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · hydrologists · ecologists · planners

Limitations

Constraints docs-verified

Requires QGIS desktop open with the QGIS MCP plugin server started (port 9876) · SKILL.md and most references are in Chinese; algorithm-reference.md is English · Without an MCP connection only a static preview sketch is possible, not a QGIS deliverable · Ships synthetic example data only; real field data must be kept out of public forks · Not a data source: the user must supply the tabular or spatial data

Useful for

Use cases llm-inferred

Web map viewer of flood-zone and site-boundary layers in a Mapbox GL JS app, driven by an AI agent · Drawing proposed drainage routes or SuDS locations as GeoJSON over 3D terrain for client presentations · Flying the map camera to catchment or site extents for stakeholder consultation maps

Audience llm-inferred

GIS analysts · planners · civils and drainage engineers building web map viewers

Limitations

Constraints llm-inferred

Map control only: no datasets (rainfall, river levels, DEM, flood extents) are offered · Needs a Mapbox GL JS map open in a browser with the bridge connected to ws://localhost:9200 · Only 5 default toolsets (about 30 tools) are active; draw, style and 3d must be enabled with enable_toolset · ENTRY lists only list_toolsets and enable_toolset, while DOCS describe 40+ tools · ENTRY auth cites env var YOUR_TOKEN, but DOCS show the token entered on the browser page

Example tool calls docs-verified

{
  "tool": "flyTo",
  "arguments": {
    "center": [
      2.2945,
      48.8584
    ],
    "zoom": 16
  }
}

Useful for

Use cases llm-inferred

Verify and normalise site or client addresses against BAN before importing them into a project database · Drive-time catchment population and income profile for a proposed development site (socio-economic baseline) · Travel-time matrix between survey sites to plan field visits · SIRENE count of establishments by activity and business-failure rate in a study area as socio-economic context

Audience llm-inferred

GIS analysts · planners · environmental consultants preparing socio-economic baselines · civils and drainage engineers (address and routing data only)

Limitations

Constraints llm-inferred

Data covers France only (BAN, INSEE, SIRENE, BODACC, OpenStreetMap France); not applicable to UK projects · Tools are plan-gated: search_nearby and route_matrix need Growth; compute_route needs Business; zone_stats and zone_compare need Growth; upgrade message returned if plan does not cover a tool · Richer fields (e.g. INSEE Filosofi grid, Lambert 93 coordinates) depend on plan · Establishment counts are a floor and business-failure procedures a floor; activity stops are a ceiling; current-year failure data is partial · Requires OAuth sign-in with a TrustyData account before first tool use · Hosted service only: availability depends on TrustyData and its status page; underlying data API source is not in the repository · ENTRY tool list does not match docs: zone_de_chalandise, comparer_emplacements, potentiel_commerce, verifier_adresses and qualifier_entreprise are prompts per docs, not tools; zone_stats and zone_compare are tools but are missing from ENTRY

Useful for

Use cases llm-inferred

Preliminary hazard screening (earthquakes, volcano alert level, typhoons) for a Philippine overseas project site · River flood outlook for a Philippine city or catchment via get_flood_forecast · Procurement and infrastructure-spending review for a Philippine client bid using PhilGEPS notices · Population and poverty baseline for a Philippine development project area

Audience llm-inferred

hazard and risk consultants · GIS analysts · international development consultants · planners

Limitations

Constraints llm-inferred

Philippines-only data, so not relevant to UK sites; the ENTRY regions field wrongly says United States · Catalogue auth field lists PAGASA_API_TOKEN, which conflicts with the docs' no-API-key statement; verify before use · Many sources are scraped HTML, PXWeb JSON or undocumented APIs, so upstream changes can break tools · Election tools read an archive frozen on 2025-05-16 · query_psa_dataset needs an explicit code for every dimension, refuses 'all' and '*', caps at 1000 cells, and needs describe_psa_dataset first · Upstream outages return upstream_error envelopes, not empty lists; handle that flag explicitly · Heuristic indicators are statistical only; allegations need independent investigation and a second source · Each HDX dataset has its own licence; check license_id before reuse · ENTRY tools field lists status values (success, empty, etc.), not tool names; see docs/tool-reference.md

Useful for

Use cases llm-inferred

Locate French river flow or hydrometric datasets for a cross-border comparison or desk study · Find French water-quality or flood-related open datasets for a transboundary catchment review · Identify French geocoding dataservices (e.g. Adresse API) to place French site addresses

Audience llm-inferred

GIS analysts · hydrologists · environmental consultants · planners

Limitations

Constraints llm-inferred

Covers French open data from data.gouv.fr only; no UK datasets · Streamable HTTP transport only; STDIO and SSE are not supported · Public hosted endpoint: no availability guarantee stated in docs · Results depend on the metadata and quality of third-party datasets on data.gouv.fr · Documented parameters are given only for search_datasets; other tools are not described in detail

Useful for

Use cases llm-inferred

Pull Berlin environmental, traffic and geodata records (Umwelt, Verkehr, Geo categories) as baseline inputs for Berlin-based site assessments · Locate resource download URLs for Berlin datasets to feed GIS or hydrology workflows · Check dataset licence and recency before reusing Berlin data in client reports

Audience llm-inferred

GIS analysts · planners · environmental consultants · hydrologists · civils engineers working on Berlin projects

Limitations

Constraints llm-inferred

Berlin-only scope; the 'Global' region tag in the entry overstates coverage · Catalogue only, with no DataStore: data must be downloaded from resource URLs · Dataset licences vary, so each record's licence must be checked before reuse · Local use needs uv and a Python install; remote SSE mode needs self-hosting · Docs state no rate limits or uptime guarantees, and the server depends on upstream CKAN availability · Docs and tool descriptions are in German · Dataset file formats are not specified in the docs

Useful for

Use cases llm-inferred

Run a Linux-only geospatial or hydrological model in an isolated container on a Mac, then inspect its logs · Reproduce a Linux GDAL/PROJ toolchain for a project deliverable without leaving the Mac · Review an audit trail of container tool calls for a model run that needs to be documented

Audience llm-inferred

developers working with Linux containers on macOS · GIS analysts and hydrologists running containerised tools · computational and modelling engineers

Limitations

Constraints docs-verified

Apple Silicon Mac on macOS 26 only · Requires Apple's container tool installed and started (container system start) · Default read-only mode; write and destructive tools need --mode=safe or --mode=full · Host folder mounts are off by default and need --allow-host-mounts · Source code is maintained privately; this repository holds binaries and docs only

Useful for

Use cases llm-inferred

Building footprint extraction from aerial imagery as exposure or drainage catchment inputs · Water-body segmentation from satellite or aerial imagery for flood extent baseline mapping · Bi-temporal change detection for land-use or built-form change screening across survey dates · GFM embedding similarity and clustering to zone a site or study area by surface form

Audience llm-inferred

GIS analysts · remote sensing analysts · flood consultants · hydrologists · ecologists · planners

Limitations

Constraints docs-verified

Embedding tools (tessera, gse, galileo) need a proxy to reach Google-hosted data; without one they return a structured error rather than results · GEE-backed embeddings require Google OAuth, non-commercial registration and project binding · On-the-fly embeddings for other models (e.g. prithvi) are an unchecked roadmap item · finetune_remote (TerraTorch via Colab) is roadmap only and is not among the 16 tools · Verified only on Windows 11 x64, CPU-only; other platforms and GPU use are not documented · Upstream geoai 0.42.0 masks_to_vector regularize bug is worked around by fixing regularize=False · Heavy tests need a sample imagery file, and model weights download on first use · Pre-1.0 version (0.2.x) with heavy upstream dependencies (geoai-py, torch, rs-embed)

Useful for

Use cases llm-inferred

Review a river-crossing flood impact assessment chapter against initial design and construction drawings, listing data conflicts, assumptions and open items · Set up P-III frequency analysis and design flood checks for a channel or river-crossing project, with a data-gap table before calculation · Check open-channel water surface profile, weir and hydraulic jump assumptions as a second-pass review of a drainage or hydraulic calculation · Structure a feasibility or preliminary design report by checking data closure and calculation linkage across chapters

Audience llm-inferred

hydrologists · hydraulic engineers · flood risk and flood impact assessment consultants · dam, sluice and levee structural engineers · report reviewers

Limitations

Constraints llm-inferred

Public version excludes personal, project and classified material, so no project data is included · Built around Chinese engineering practice and Chinese standards; not directly applicable to UK standards without adaptation · Software tools such as HEC-RAS and MIKE 11 are referenced only; the skill does not run models · Numerical inputs must be verified against authoritative design data and current codes; missing data is flagged as to be confirmed rather than filled in · Young project with two releases (v1.0.0 in June 2026, v1.0.1 in July 2026), so maintenance history is short

Useful for

Use cases llm-inferred

Seasonal forecast baseline series from 1993 to present for drainage or flood-risk climate context (monthly_mean with a computed ensemble mean) · ERA5 historical rainfall and temperature inputs for a catchment or drainage assessment background · Climate context download for water resource or civils design discussions

Audience llm-inferred

hydrologists · flood consultants · drainage engineers · climate or data analysts

Limitations

Constraints docs-verified

Early stage: only the cds-download skill is available; more skills are planned · The ensemble_mean product type only covers real-time years (~2017 onward); 1993-present requires monthly_mean and a manually computed ensemble mean · No GHCN station parsing or QC-flag skill yet (planned)

Useful for

Use cases llm-inferred

Reference pattern for grounding AI assistant answers in 3D site or catchment context in a CesiumJS viewer · Prototyping AI-assisted camera control and 3D Tiles/terrain review for planning or drainage schemes · Agent-skill-driven CesiumJS code generation for internal geospatial visualisation tools

Audience llm-inferred

GIS analysts · web developers building CesiumJS apps · BIM and civils engineers reviewing 3D models

Limitations

Constraints docs-verified

Repository is deprecated; active development has moved to cesiumjs-ai-starter-app and cesiumjs-skills · Legacy architecture used a WebSocket bridge needing a separate local server process per user, tied to a single browser tab, and not scalable · No UK-specific or consultancy datasets; coverage is global and it provides integration patterns rather than data

Useful for

Use cases llm-inferred

Chat-driven loading of catchment, site boundary and constraint layers into an open QGIS project for review · Running buffer or clip geoprocessing via execute_processing for site constraint screening · Rendering the current map view to an image for draft report figures or client markup

Audience llm-inferred

GIS analysts · drainage engineers · hydrologists · planners

Limitations

Constraints llm-inferred

Requires QGIS Desktop running with the plugin server started manually (localhost:9876) before the MCP server can connect · Documented as tested only with QGIS 3.38 and ministral-3:latest; other versions and models are unverified · Needs a local Ollama model that supports agents and tool use · execute_code runs arbitrary PyQGIS code, so it needs careful handling in client work · Default ports are localhost only; no remote, multi-user or authentication setup is documented · Provides no datasets of its own; it controls QGIS, so data must already be available locally · No maintenance status, release cadence or beta status is stated in the docs

Useful for

Use cases llm-inferred

Bulk geocoding of site or asset address lists from a spreadsheet · Drive-time and walk-time isochrones for site accessibility and catchment screening · Route and travel-time estimates for site visit or survey planning · Static map images with markers and route overlays for report figures

Audience llm-inferred

GIS analysts · planners · civils and environmental consultancy staff

Limitations

Constraints llm-inferred

Requires a Stadia Maps API key · Must be built locally (bun or npm) before use · Transport type and exact tool names not stated in docs · UK coverage for geocoding, routing and maps not stated; entry region is China · Starter server: tool schemas consume context and tools need tailoring

Useful for

Use cases llm-inferred

Travel-time isochrones and drive or walk reachability from a depot or site for survey and sampling crew scheduling · Travel-time matrix and multi-stop route optimisation for multi-site monitoring rounds such as river or outfall sampling · Static map images of site location, catchment context and sampling points for report figures · Offline buffer, area and point-in-polygon checks on site boundaries or consultation zones

Audience llm-inferred

GIS analysts · civil engineers (site logistics) · environmental consultants · planners

Limitations

Constraints llm-inferred

Requires a Mapbox access token (MAPBOX_ACCESS_TOKEN) · Global, general-purpose location platform; no UK hydrology, flood, rainfall or environmental datasets among the listed tools · Geocoding, POI, routing and isochrone tools call Mapbox APIs; usage limits and pricing are not stated in DOCS · Interactive render_map_tool works only in MCP Apps clients (e.g. Claude Desktop, Claude Code, VS Code with GitHub Copilot, Goose); use static_map_image_tool elsewhere · Resource fallback tools (resource_reader_tool, category_list_tool) are off by default; enable CLIENT_NEEDS_RESOURCE_FALLBACK=true for clients without resource support · Tool argument schemas are not included in DOCS

Useful for

Use cases llm-inferred

FRA baseline flows from nearest gauge using gdf-statistics (mean flow, Q95, Q50) · QMED and peak-flow statistics for flood estimation cross-checks · Catchment descriptor extraction (land cover, geology, FEH descriptors, SAAR) for hydrological inputs

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · GIS analysts

Limitations

Constraints docs-verified

Test service: URL patterns, parameters and data formats may change before an operational release · No access controls currently, but this may not always be the case · Time-series requests accept only a single station and a single data-type per call · Update schedule is referenced on the NRFA site but not stated in the docs

Useful for

Use cases llm-inferred

Scottish FRA baseline flows and levels from the nearest SEPA gauging station · Calibrating or validating Scottish hydrological and hydraulic models against observed river levels · Low-flow and dry-weather baseline for water environment or abstraction assessments in Scotland

Audience llm-inferred

flood consultants · hydrologists · drainage engineers · GIS analysts

Limitations

Constraints docs-verified

Access keys are complicated to use, so the docs recommend accessing data without a key where possible · The documentation site is marked BETA

Useful for

Use cases llm-inferred

Pre-scope satellite imagery availability (Ready vs Archived) over a site before committing to a download · Find dated scenes over a catchment for flood event or land-cover baseline review · Save recurring study-area searches for reuse in monitoring or EIA baseline work

Audience llm-inferred

GIS analysts · flood consultants · ecologists · planners

Limitations

Constraints llm-inferred

Downloads and cart require a Bhoonidhi login (bhd auth login or env vars) · Archived scenes may need a request on the portal before they can be downloaded · Priced and on-order scenes are only staged to the cart; ordering and payment happen on the Bhoonidhi portal · Background download jobs last only as long as the server process; large downloads should use the standalone bhd CLI · Imagery is under the Bhoonidhi EULA: credit ISRO-IRS and do not resell original products commercially · Archive time span and per-mission resolution are not stated in DOCS · Third-party community project; maintenance commitment not stated

Useful for

Use cases llm-inferred

Client-site presentation: fly the globe to a project location from a natural-language prompt · Visualising a time-dynamic scene (CZML) for a catchment or asset presentation · Prototyping an LLM-driven 3D GIS viewer before wiring in own UK water or civils data

Audience llm-inferred

GIS analysts · software developers building LLM-driven 3D viewers

Limitations

Constraints llm-inferred

Starter template, not a data source: no datasets are bundled · Chat needs an LLM API key; without one only a plain viewer runs · Terrain and imagery quality depends on the optional Cesium Ion token · Requires Node.js ≥ 22 and npm ≥ 9 for local dev, or Docker · Catalogue kind is 'mcp', but the docs describe an MCP client bridge that consumes external servers; no MCP tools are listed in metadata · Metadata region is Global, with no UK-specific data or coverage described

Useful for

Use cases llm-inferred

Flood-extent and river surface visualisation for FRA or flood-event briefings in a WebGIS dashboard (water surface effect) · Pressure-flow animation on water network pipes for options presentations to clients (pipe flow effect) · Radar or scan-cone overlays on a digital twin of a site for client-facing 3D dashboards

Audience llm-inferred

GIS analysts · web and front-end developers building WebGIS dashboards · digital twin and BIM/3D visualisation teams

Limitations

Constraints docs-verified

Visualisation effects only; it supplies no hydrological, rainfall, gauge or survey datasets · Host project must provide its own Cesium version, static assets, CESIUM_BASE_URL and Viewer initialisation · Public demo is not live until GitHub Pages is enabled · Docs state no coverage, resolution or update cadence for any data · No MCP tool names are documented, so MCP tool use cannot be verified from the docs

Useful for

Use cases llm-inferred

Site context imagery: clip configured imagery to a site boundary and export GeoTIFF for report figures · Site history review using Esri Wayback historical imagery versions · Catchment screening: DEM GeoTIFF extraction for drainage and flood baseline checks · Boundary prep: convert KML/SHP/GeoPackage site boundaries and clip OSM vector layers

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · planners · environmental consultants

Limitations

Constraints docs-verified

Windows x64 desktop app only · Version 0.2.x; earlier builds are public test releases · Connecting to a data source does not grant download rights; licensing must be checked per provider · No UK-specific sources documented; examples are China-focused (e.g. Tianditu needs own credentials) · Historical imagery release date is not the capture date · Scanned PDF auto page-splitting still pending; OCR removed from base package · Trial credits limited to first 100 eligible accounts · Scheduled tasks require the local app to keep running in the background

Useful for

Use cases llm-inferred

Literature review and ranked research-gap analysis for a drainage or flood-risk evidence base before writing a technical note · Novelty check and spatial regression (OLS/GWR) on catchment attributes to support an evidence-based method statement · Dataset discovery and download with provenance logging from government portals for baseline environmental data · Consolidating pipeline outputs into a narrative technical report

Audience llm-inferred

GIS analysts · GIScientists · remote sensing researchers · geoscientists

Limitations

Constraints llm-inferred

Built for academic research workflows (papers, journal templates, reviewer loops); consultancy deliverables such as FRA or drainage design are not covered by the docs · Delivered as Claude Code skills (Markdown workflows), not as a standalone MCP data server; the tool names listed are skills · Requires Claude Code and paid Anthropic API usage · Track B spatial work needs a conda environment with geopandas, pysal, libpysal, esda, spreg, mgwr, rasterio and xarray; Track A deep-learning work needs a CUDA GPU (optional) · Requires copying the skills folder into ~/.claude/skills or a project .claude/skills directory before use · Licence not stated in metadata; maintenance status unknown · Automated pipelines are intended to run with human checkpoints; output needs expert review

Example tool calls docs-verified

{
  "tool": "lit-review",
  "arguments": {
    "$ARGUMENTS": "SuDS performance evidence for UK urban drainage strategies"
  }
}

{
  "tool": "data-download",
  "arguments": {
    "$ARGUMENTS": "UK river gauge daily flow records for the Thames catchment"
  }
}

{
  "tool": "spatial-analysis",
  "arguments": {
    "$ARGUMENTS": "Test whether catchment rainfall-runoff relationships vary spatially, with ESDA and conditional diagnostics"
  }
}

Useful for

Use cases llm-inferred

Buffer watercourses, clip a DEM to the buffer and derive slope for a site or FRA-style terrain screen (mirrors the documented quickstart example) · Select drainage or utility assets by attribute or geometry to map site constraints · Save a verified processing chain as a .model3 and re-run it on other catchments or sites

Audience llm-inferred

GIS analysts · Flood consultants · Hydrologists · Drainage engineers · Civils engineers working in QGIS

Limitations

Constraints llm-inferred

Requires a desktop QGIS installation; it is a QGIS plugin, not a standalone server or MCP endpoint · Dependencies must be installed from the Settings tab (Check / Install Dependencies) before use · OpenAI, Gemini and Anthropic need API keys, which conflicts with the ENTRY note that no credentials are documented · Output quality depends on the chosen LLM and on the data QGIS can load; no data coverage or resolution is defined by the plugin · Combined work is governed by QGIS GPL v2+ and PyQt GPL v3 terms alongside the MIT licence · No version, release status or maintenance information is given in the docs

Useful for

Use cases llm-inferred

Pull open terrain, land-cover or hydrology datasets into an open QGIS project for early site screening, checking each dataset's licence first · Run repeatable Processing steps (e.g. clip, buffer, reproject) on project layers, approving each step before it changes data · Style constraint layers and build print layouts for flood or drainage option plans

Audience llm-inferred

GIS analysts · flood consultants · drainage engineers · hydrologists · ecologists · planners

Limitations

Constraints docs-verified

Hosted AI service: no offline mode and no local model, so an internet connection is needed · Answers come from an AI model and can be wrong; review every change before accepting · Each message plus a project description (CRS, canvas extent, layer names, types, field names) is sent to TerraLab's hosted service in the EU · Requires QGIS 3.28 or later · UK-specific coverage of the open data catalog is not stated · Hosted service is not licensed for reuse and text and data mining rights are reserved

Useful for

Use cases llm-inferred

Terrain and catchment analysis workflow guidance in QGIS for drainage or flood risk baselines · GDAL, GRASS and SAGA command guidance for DEM and raster processing · PyQGIS script generation for batch clipping or reprojection of site and boundary layers · Discovery of global geodata sources for early-stage project area baselines

Audience llm-inferred

GIS analysts · hydrologists · flood consultants · drainage engineers

Limitations

Constraints llm-inferred

Provides assistance and tutorials rather than a dataset or API · Interaction text and QGIS environment information (version, view extent, layer metadata) are collected to improve service quality · Screenshot feature is optional and disabled by default · No data coverage, resolution or update frequency stated in the docs · Depends on QGIS desktop installation

Useful for

Use cases llm-inferred

Reproducible FRA or drainage analysis packaged as a project.yaml and pipeline.py so a reviewer can rerun it · Discovering and assessing open geospatial datasets for a site constraints screen · Reviewing PostGIS or DuckDB spatial queries for catchment or constraint overlays · Building an interactive map dashboard to share options with a client or planner

Audience llm-inferred

GIS analysts · hydrologists · drainage engineers · flood consultants · planners · ecologists

Limitations

Constraints llm-inferred

Guidance skill, not a data source: output quality depends on the agent and on the data it finds · Docs show no UK-specific sources; examples are NYC and Tartu · Building the Pages site needs Python project dependencies, Node 20+ and npm · Install needs git, nodejs and npx already present · Existing v1 manifests with a map must declare presentation.map.basemap.kind · Default basemap fallback relies on goplex.ee Protomaps tiles · Docs text is truncated at the end, so some content may be missing

Useful for

Use cases llm-inferred

Check whether two Sentinel-2 scenes from different seasons can support a changed-hectares claim before any pixel arithmetic · Verify CRS and units before reporting flood extent or catchment area figures · Audit spatial leakage before reporting validation scores for a flood or susceptibility model · Confirm DEM and terrain-hydrology preconditions before reporting flow-path outputs

Audience llm-inferred

GIS analysts · remote sensing analysts · hydrologists · flood consultants · geospatial developers building AI agent workflows

Limitations

Constraints docs-verified

Behaviour figures come from one runtime and model pair (Claude Code 2.1.214/2.1.222, claude-sonnet-5) and are not universal · Behaviour figures are model-judged, uncalibrated and not yet human-verified · The repository's own Phase 3 quality gate fails: 4.3% critical failures and 19.6% full-criterion pass rate · Known routing defects: 1 false positive, 4 false negatives, 1 incomplete route and 11 execution errors · Routing shows which skill loaded, not whether the answer was correct · Contains no data feeds or UK-specific datasets; it supplies method guidance only · ENTRY kind is 'mcp' and its tools list names skills, but the docs describe Agent Skills rather than an MCP server

Useful for

Use cases llm-inferred

Flood-risk screening: shortlist DEM, rainfall and exposure datasets in GEE for a hill-catchment AOI · BNG habitat baseline: Sentinel-2 NDVI composite for a site AOI, exported to Google Drive · Drainage strategy: GEE rainfall grid extraction for an AOI as a design-input check

Audience llm-inferred

GIS analysts · hydrologists · flood risk consultants · drainage engineers · ecologists

Limitations

Constraints llm-inferred

ENTRY states no credentials documented, but DOCS describe Earth Engine authorisation and project-level quota checks · Datasets are accessed through Google Earth Engine; the plugin does not host data itself · Earth Engine project quotas and usage limits apply · GeoMaster is bundled as a skill snapshot, not a live-synced repository, so it may drift from upstream · Install examples are Windows/PowerShell-focused

Useful for

Use cases llm-inferred

Batch-export GEE rasters or feature tables to Google Drive for downstream GIS work · Monitor GEE export tasks and retry failed reduceRegion/reduceRegions jobs using tileScale after out-of-memory errors · Upload custom site or catchment assets to GEE for regional analysis

Audience llm-inferred

GIS analysts · hydrologists · ecologists · remote sensing analysts · Python-based geospatial developers

Limitations

Constraints llm-inferred

Requires a Google Earth Engine account and an EE-enabled Google Cloud project · Skill covers workflow operations only; it does not itself provide a dataset or coverage details · Docs do not state data coverage, resolution, or output formats · Entry metadata lists auth as an env-var CLIENT_SECRET, which the docs do not describe; docs use ee.oauth credentials instead · Drive download relies on the EE OAuth token including the drive scope · Designed for Claude Code and Codex agent setups; no MCP interface