GIS & earth observation

Useful for

Use cases llm-inferred

Desk-based site context overview (terrain, imagery, nearby live signals) before a site visit · Weather context review for an event window using forecast wind and observed radar replay · Visual briefing material for client and stakeholder presentations using scene capture

Audience llm-inferred

GIS analysts · flood consultants (visualisation only) · planners · civils/BIM engineers (visualisation only)

Limitations

Constraints llm-inferred

Traffic is simulated along real roads from aggregate location data, not measured · CCTV camera poses and rocket launch trajectories are coarse estimates · Public camera feeds only over listed regions · Google Maps and Cesium ion features are subject to provider terms and quotas · Voice control requires an OpenAI key · Bundled Nepal flood data is non-commercial only · Licence listed as Other, so reuse terms need checking before commercial use · Older versions no longer work with OpenStreetMap data sources and need updating

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

Useful for

Use cases llm-inferred

Screening private warehouse layers for proximity to road or utility networks (e.g. features within 5 km of a motorway) for constraint mapping · Sanity-checking polygon area and line length of GIS query outputs before using them in a report · Joining site or asset points to Overture Maps building or road layers for baseline context · Rendering spatial query results as a map for client or peer review

Audience llm-inferred

data scientists · analysts · GIS analysts · spatial data engineers

Limitations

Constraints llm-inferred

Requires access to a supported warehouse (PostGIS, BigQuery, Snowflake or Wherobots) and its local CLI credentials · BigQuery queries are capped at a 10 GiB scan by default · Benchmark suite covers only London, Berlin and Paris cases (8 assertions) · Map-feedback loop needs the optional Dekart CLI · ENTRY notes no credentials documented in README, while the docs rely on local bq/snow/dekart auth · Not UK-specific; no UK datasets are named in the docs · Version check telemetry is on by default (disable with DO_NOT_TRACK=1)

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

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

Index shared-drive shapefiles and PostGIS tables for a flood-risk or drainage project data room, searchable by metadata · Publish a shared map of survey or site-investigation layers as a link or embed for client review · Serve catalogued vector layers to QGIS or ArcGIS via OGC API Features for FRA or environmental baseline work · Run buffer, clip, and intersect analysis on consultancy layers, such as constraint buffers around watercourses

Audience llm-inferred

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

Limitations

Constraints docs-verified

Read-only MCP server for coding agents (per docs) · Self-hosted: requires a running GeoLens stack of six containers (about 1.3 GB resident) · WFS, ArcGIS, and OGC API Features imports are one-shot copies, not live · Map previews capped at 500 features; dissolve is materialize-only · GeoLens's own REST API can change between minor releases; standards APIs track their specifications · Semantic search needs an embedding provider and admin setup · No MCP tool names are given in the metadata or docs

Useful for

Use cases llm-inferred

Build a FLAC3D slope model and estimate factor of safety · Model tunnel excavation in jointed rock with 3DEC and check block displacements · Simulate landslide runout with MPoint and report the final deposit profile · Check unbalanced force on a PFC simulation while it is still running

Audience llm-inferred

geotechnical engineers · geomechanics modellers · civils engineers · researchers using ITASCA software

Limitations

Constraints docs-verified

Requires an ITASCA engine installed locally · Execution tools require the bridge to be started inside the engine GUI or IPython console · Engine version support is limited to the listed versions (PFC 6.0/7.0/9.0, FLAC 7.0/9.0, 3DEC 7.0/9.0, with 9.0+ recommended) · Documentation tools work without the bridge

Useful for

Use cases llm-inferred

Offline basemap with 90m/30m contours for site walkover and drainage gradient screening · Nearest-POI screening for field visits (hospitals, pharmacies, fuel, water taps) with named POIs ranked first · Agent-driven route and access-track planning exported as GPX for field teams

Audience llm-inferred

GIS analysts · civils engineers · drainage engineers · ecologists · planners

Limitations

Constraints llm-inferred

Self-hosting required: about 101 GB storage for planet.mbtiles, plus about 290 GB optional for contours · Hiking difficulty and sac_scale data absent on stock OpenMapTiles tiles; routing is not difficulty-aware without the extended profile · drinking_water POIs include springs and troughs and are not a potability guarantee · geocode and reverse_geocode tools are not registered unless PHOTONSERVER is set · analyze_gpx and follow_route are listed in catalogue metadata but are not documented in DOCS · Router is documented as a basic router, not a full-featured one; routing segments capped at 50 km straight-line by default · Single-maintainer project; no maintenance commitments stated

Useful for

Use cases llm-inferred

Drive a 3D terrain or site view of a proposed drainage or channel scheme from natural-language prompts during client meetings · Load survey or flood-extent GeoJSON into a browser Cesium viewer to review extents and feature values · Build an in-house browser assistant that lets engineers query and control a 3D project map

Audience llm-inferred

GIS analysts · civils engineers · flood consultants · web developers building map-based AI assistants

Limitations

Constraints docs-verified

Demonstration scenes use demonstration data, not surveyed heights or official statistics · WebMCP browser path is Chrome 149+ experimental · Codex map plugin is a community beta and requires a compatible MCP Apps host

Example tool calls docs-verified

{
  "tool": "openCesiumMap",
  "arguments": {}
}

Useful for

Use cases llm-inferred

Stormwater drainage model build from GIS inputs with QA and audit trail · Peak-flow and rainfall-runoff screening for drainage strategy options · Reproducible SWMM run handover with provenance records for client review

Audience llm-inferred

drainage engineers · hydrologists · stormwater modellers · GIS analysts

Limitations

Constraints llm-inferred

Pre-1.0 (v0.9.4), so interfaces may change · Real storm networks only for 35 Canadian cities via SWMMCanada; elsewhere SWMManywhere synthesis, which is not a calibrated or validated network · Validation rows are evidence-bounded: GIS preprocessing concept, prepared-input path and uncertainty smoke are not calibrated performance claims · Raw GIS path handles structured layers only, not arbitrary CAD/GIS recognition · ENTRY lists region as United States, but DOCS do not describe US or UK coverage, so UK suitability is unverified · Agent features need an LLM provider; one-line installers run a remote script · ENTRY auth says no credentials documented, but DOCS describe API key configuration · No MCP tool names or transport documented in DOCS; ENTRY tools list is empty · One evidence row (v0.7.1) states calibration is next-milestone scope

Useful for

Use cases llm-inferred

Desk-study search of a CKAN portal for open environmental or flood-related datasets to scope a site baseline · Checking whether a local authority's CKAN portal publishes drainage or asset datasets before making a data request · Pulling DataStore tabular monitoring records via SQL into a spreadsheet for trend analysis · Reviewing dataset resource formats and metadata to confirm reuse suitability for a client report

Audience llm-inferred

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

Limitations

Constraints docs-verified

Tool output capped at 50,000 characters; oversized text and Markdown responses are cut · ckan_datastore_search returns 100 rows by default, maximum 32,000 · ckan_package_search returns 10 results per page by default, maximum 1,000 · Hosted endpoint shares a 100k requests/day quota · HTTP response body capped at 32 MiB (CKAN_MAX_RESPONSE_BYTES for local Node.js deployments) · ckan_find_portals relies on the datashades.info live registry (~950 portals)

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

Preview and compare candidate basemap styles for a client web map or flood-risk viewer · Quick visual check of site boundary or drainage-asset GeoJSON via geojson.io before sharing with a client · Audit which Mapbox token scopes a GIS web map deployment actually needs

Audience llm-inferred

GIS analysts · web mapping developers · drainage engineers reviewing GeoJSON outputs

Limitations

Constraints llm-inferred

GeoJSON preview tool is Beta · Each tool needs a token with specific scopes; wrong scope causes authentication errors · Preview style tool needs at least one public token with styles:read scope · Developer and styling tooling only; provides no environmental or hydrological datasets · Hosted endpoint is a separate devkit URL; the linked hosted-MCP guide points at a different endpoint

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

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

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

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

Useful for

Use cases llm-inferred

Serve a client's GeoParquet or PMTiles dataset from its existing bucket as an OGC API, without loading it into a database · Expose project geodata to QGIS or partner systems via OGC API Features with OIDC-protected access · Give AI agents read access to project geospatial collections through the MCP endpoint

Audience llm-inferred

GIS analysts · GIS developers · data engineers · geospatial platform administrators

Limitations

Constraints llm-inferred

Cloud Optimized GeoTIFF has no native provider; only a worked example is documented · Requires Python 3.12 or later · Enterprise identity (EMA/ID-JAG) is noted as still under verification · Tracks pygeoapi releases, so upstream changes feed into maintenance · MCP tool list is empty in ENTRY metadata

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

Slope and aspect from a site DEM for drainage or earthworks setting-out (raster_operations) · Overlay and dissolve constraint layers such as flood zones and site boundaries in a project GDB (geometry_analysis) · Hot-spot or kernel density analysis of flood or incident records (spatial_statistics) · Export PDF/PNG map plates for planning or flood risk assessment submissions (export_layout)

Audience llm-inferred

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

Limitations

Constraints docs-verified

Windows only; needs a licensed ArcGIS Pro installation and its Python environment set as ARCPY_PYTHON_PATH · Automated tests use mocked arcpy; the 100 geoprocessing tools are not validated across scenarios on a licensed runtime · Ten state-mutating tools (e.g. delete_dataset, repair_geometry) refuse to run without confirm: true · Some tools need Esri Spatial or Network extension licences · Sketch-to-GIS demo is marked 'coming soon'

Useful for

Use cases llm-inferred

Portal content inventory and stale-content governance audit before handover of a project GIS deliverable · Broken-reference and service health check on web maps and layers before issuing them to field or client teams · Export of project web map layers as PNG/PDF for consultancy report figures · Attribute query of hosted feature layers (e.g. asset or site records) for data QA

Audience llm-inferred

GIS analysts · GIS and portal administrators · environmental and civils consultancy staff who manage ArcGIS Online or Enterprise content

Limitations

Constraints llm-inferred

Independent open-source project, not affiliated with Esri (per DOCS disclaimer) · Requires portal credentials; catalogue auth field conflicts with DOCS · Many tools are write or destructive (delete, share, offboard_user, batch operations); read-only mode via MCP_READ_ONLY=true should be set for exploratory use · Admin tools such as portal_health require administrator privileges · Publishing behaviour is version-specific (fixes for ArcGIS Enterprise 12.x in v1.14.0) · Self-signed Enterprise certificates need MCP_TLS_VERIFY=false, which weakens TLS verification

Useful for

Use cases llm-inferred

Discover NASA Earthdata datasets for a study area using keyword and bounding-box search · Preview granule scope for a time window in manifest mode before committing to a bulk download · Generate notebook-ready download scripts for satellite data analysis in script mode · Pull granules into a project folder on a server runtime in download mode where server-side writes are intended

Audience llm-inferred

hydrologists · GIS analysts · flood consultants · environmental consultants · civils and water engineers working with satellite data

Limitations

Constraints docs-verified

Download mode requires NASA Earthdata Login credentials · Download mode writes files to the server runtime, not the user's machine · Earthdata-only: no notebook or runtime tools in the server itself · Coverage area, time span and resolution are not stated in the docs

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