The TerraMCP directory

Find your next source.

Ranked by evidence. Filter by discipline, region and format to find sources for your project.

147 sources

Sponsored placements first · Organic quality score ↓

dataset

85/100Currency A

Channel Coastal Observatory ↗

wave buoys

environment hydrology

Englandhealthy

dataset

85/100Currency A

Copernicus Marine Service ↗

sea level

environment hydrology

Globalhealthy

dataset

85/100Currency A

National Tide and Sea Level Facility ↗

tide gauge data

environment hydrology

United Kingdomhealthy

mcp

85/100Currency A

tidewave_phoenix ↗

MCP server with runtime-level tools for Phoenix development

What's in it

Data offered docs-verified: runtime code execution in the running Phoenix app (project_eval) · live app logs (get_logs) · development database SQL queries (execute_sql_query) · module/function source locations, including hex dependencies (get_source_location) · documentation pinned to mix.lock versions (get_docs)
Formats docs-verified: MCP streamable HTTP · MCP stdio
Access docs-verified: Open source under Apache License 2.0; installed as a dev-only hex dependency (tidewave ~> 0.9, only: :dev); no credentials documented in DOCS

Useful for

Use cases llm-inferred: Debug a failing code path in a Phoenix data or asset app against live dev state using project_eval · Read request logs and backtraces with get_logs when a Phoenix app misbehaves during development · Verify records written by a Phoenix app in the dev database with execute_sql_query · Jump to the definition of a function in a hex dependency with get_source_location instead of grepping
Audience llm-inferred: Elixir/Phoenix developers · web developers building internal Phoenix tools · GIS and data developers maintaining Phoenix apps

Limitations

Constraints docs-verified: Phoenix applications only · development-only: the plug is intended for Mix.env() == :dev · tools execute arbitrary Elixir and SQL against the running dev app and dev database · localhost-only by default; remote access needs the allow_remote_access option · works best with Phoenix LiveView v1.1 or later · worktrees need mix tidewave.proxy as a STDIO MCP · no geographic or hosted dataset; output reflects only the local app's state

environment hydrology

Globalhealthy

dataset

83/100Currency A

Copernicus Atmosphere Data Store ↗

CAMS air quality reanalysis

environment

Globalhealthy

dataset

83/100Currency A

EEA Datahub ↗

WISE water

environment ecology water-quality

Europehealthy

mcp

83/100Currency A

tidewave_rails ↗

MCP server with runtime-level tools for Rails development

What's in it

Data offered docs-verified: runtime code evaluation in the running Rails app (project_eval) · live app logs · development database query results (execute_sql_query) · source file and line locations of classes, modules and methods, including gem dependencies (get_source_location) · documentation for classes, methods and constants pinned to Gemfile.lock gem versions (get_docs)
Formats docs-verified: MCP streamable HTTP
Access llm-inferred: Open source under the Apache License 2.0; no credentials documented in README. Requires a local Rails development app with the tidewave gem added to the development group.

Useful for

Use cases llm-inferred: Reproduce a failing code path against live app state with project_eval when debugging a Rails web tool · Confirm that a create action saved expected records by querying the development database with execute_sql_query · Check method signatures in the exact gem versions locked in Gemfile.lock with get_docs before generating code · Jump to the defining file and line of a gem method with get_source_location when extending a Rails app
Audience llm-inferred: Ruby on Rails developers · web application developers building internal tools for consultancies

Limitations

Constraints llm-inferred: Development use only; not meant for production · Raises an error in any environment where code reloading is disabled · Requires a running Rails app with the tidewave gem in the development group · Accepts requests from localhost only by default · Toolbar may not appear if compression middleware runs after Tidewave · Multiple hosts or subdomains need *.localhost and session configuration changes · Provides no routes or associations tools by design · Contains no UK water, civils or environmental datasets; it is a developer tool, not a data source

environment hydrology

Globalhealthy

mcp

76/100Currency A

NASA Earthdata MCP ↗

An MCP (Model Context Protocol) server providing LLM agents with direct access to NASA's Common Metadata Repository (CMR).

What's in it

Data offered docs-verified: NASA Earth science dataset (collection) discovery via CMR · granule (data file) search and data availability checks · NASA KMS scientific keyword vocabulary · data access services (OPeNDAP, Harmony, WMS/WMTS) · web portals and downloadable tools (e.g. Giovanni, Worldview, Panoply) · citation records (publications, DOIs) · scientific variables and measurements (scale, offset, fill values)
Coverage llm-inferred: Global
Formats docs-verified: MCP streamable HTTP
Access docs-verified: Remote hosted MCP endpoint at https://cmr.earthdata.nasa.gov/mcp/v1. No authentication for the MCP endpoint is documented, and ENTRY lists auth and licence as null. Data authentication and download are handled through the earthaccess Python library.

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

gis environment

Globalhealthy

mcp

76/100Currency A

ocean-brain ↗

Self-hosted knowledge base for organizing notes, thoughts, and projects with backlinks, properties, views, reminders, and MCP integration.

What's in it

Data offered docs-verified: notes · backlinks · tags · typed properties · saved views · graph · reminders · calendar date lookup · Markdown and HTML export
Formats docs-verified: Markdown · HTML
Access docs-verified: Free and open source under the MIT licence; self-hosted; password mode or local open mode

Useful for

Use cases llm-inferred: Log project decisions and meeting notes, linked by backlinks, for a consultancy project · Keep research trails for a site investigation or desk study connected as the thinking develops · Track ideas and open actions with reminders and saved table views across a project
Audience llm-inferred: project managers · consultants · researchers · project teams

Limitations

Constraints llm-inferred: Not an environmental, hydrological or geospatial data source; the docs describe a note-taking workspace · Persistent, shared use requires self-hosting; the live demo has no server-backed features · Source development requires Node.js 22.13+ and pnpm 10.25.0 · Access beyond the user's own machine requires password mode

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

75/100Currency A

What's in it

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

Useful for

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

Limitations

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

climate environment hydrology

Some details auto-extracted · unverified

United Stateshealthy

mcp

74/100Currency A

What's in it

Data offered docs-verified: water levels (1-min, 6-min, hourly observed) · tide predictions (hilo and interval) · currents (observed and predicted) · meteorological data · marine wind and wave forecasts (NWS) · station metadata and directory · tidal datums · harmonic constituents · prediction offsets · sea level trends · sea level rise projections (2022 Interagency scenarios) · extreme water levels (AEP) · top ten water levels · high tide flooding counts and projections · sun and moon calculations
Coverage docs-verified: US NOAA CO-OPS station network; no UK station coverage stated · hilo predictions up to a 10-year request span; observation archive length not stated
Resolution docs-verified: Observed water levels at 1-minute, 6-minute or hourly intervals; spatial resolution not stated
Formats docs-verified: JSON · Markdown tables · MCP stdio · MCP streamable HTTP
Access docs-verified: Free and open, no API key required (NOAA CO-OPS APIs are open); MIT licence

Useful for

Use cases llm-inferred: Tide and surge-context review for coastal flood risk assessment at US comparison sites · Sea level trend and 2022 SLR projection inputs for coastal climate-resilience appraisal (US sites) · Tidal datum (MLLW, MSL, NAVD88) and harmonic constituent checks for estuary or outfall modelling (US stations) · Marine wind and wave briefing for coastal works programme planning (US waters)
Audience llm-inferred: flood consultants · coastal engineers · hydrologists · marine civils engineers · planners

Limitations

Constraints llm-inferred: Great Lakes stations have no tide predictions · Subordinate (S) prediction stations only support hilo predictions · Predictions are astronomical; storm surge is not included · Per-product request-span limits are enforced client-side (e.g. 4 days for 1-minute data) · Oversized results return a response_too_large error rather than truncated data · NWS forecasts are limited to US lat/lon, up to about 7 days · No UK station coverage is stated; the NOAA network is US-centred · Tool argument names are not documented in DOCS; verify against the tool schema

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

74/100Currency A

What's in it

Data offered docs-verified: search capsules and pipelines · run capsules and pipelines · release capsules and pipelines · manage data assets
Formats docs-verified: MCP stdio · MCP streamable HTTP
Access docs-verified: API key (Code Ocean access token) via CODEOCEAN_TOKEN, requiring a Code Ocean platform account; licence MIT (ENTRY metadata)

Useful for

Use cases llm-inferred: Re-running a shared capsule for a flood or drainage model after updated rainfall inputs · Releasing a versioned capsule or pipeline as a reproducible analysis record for a project deliverable · Managing data assets that hold survey or monitoring inputs for a civils or environmental study
Audience llm-inferred: hydrologists · drainage engineers · GIS analysts

Limitations

Constraints llm-inferred: Requires a Code Ocean platform account and access token · Tied to a specific Code Ocean deployment via CODEOCEAN_DOMAIN · Tested against a minimum Code Ocean platform API version; pin the package version to match the deployment · Local install needs uv and Python 3.10 or newer · Streamable HTTP refuses requests without a token · No environmental or UK geospatial datasets are described in the docs · No tool names are listed in the metadata or docs, so tool calls cannot be confirmed from this entry

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

73/100Currency A

NASA MCP Server ↗

A Model Context Protocol (MCP) server for NASA APIs, providing a standardized interface for AI models to interact with NASA's vast array of data sources.

gis environment

Globalhealthy

mcp

73/100Currency A

sailing-mcp ↗

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

What's in it

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

Useful for

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

Limitations

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

climate environment hydrology civils-bim

Some details auto-extracted · unverified

Globalhealthy

mcp

73/100Currency A

What's in it

Data offered llm-inferred: application performance totals: requests, errors and p95 response time · per-transaction timeline and response-time histogram · application issues: errors, slow SQL, deprecations, warnings, notices · individual slow request traces · day, week and month history reports · configuration and code bottleneck observations (e.g. N+1 queries)
Coverage docs-verified: up to 30 days (performance windows within the last ~30 days)
Resolution docs-verified: 15-minute buckets (performance summary)
Formats docs-verified: MCP stdio
Access docs-verified: Tideways API token required (scopes: metrics, traces, errors), so a Tideways account is needed; read-only (GET only); licence MIT

Useful for

Use cases llm-inferred: Diagnose why a client's web application or portal was slow in a given window, using Tideways performance data · Triage errors and slow SQL in a client-hosted web app during handover or post-release review · Check a client web platform's request volume and p95 response times across a project's services
Audience llm-inferred: web application developers · DevOps and site reliability engineers maintaining Tideways-monitored applications

Limitations

Constraints llm-inferred: Not an environmental, hydrological, water or civils data source; it is application performance monitoring for web apps, so the 'environment' category in the entry does not match its content · Unofficial, community-maintained server, not affiliated with or supported by Tideways · Requires a Tideways account and API token; the token must have the metrics, traces and errors scopes · Rate limit is per Tideways organisation per clock hour and is shared by all of its tokens and projects; its size depends on the plan · History is available for production and the default service only · Issues are returned 10 per page · Performance data covers roughly the last 30 days · All times are UTC · Requires Node.js 22+ or Docker to run

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

skill

73/100Currency A

vellum ↗

The living surface — a shared ocean where AI agents leave short thoughts and weave lineages. MCP + REST, open to any agent. https://vellum.linxule.com/for-ai.txt

What's in it

Data offered docs-verified: short AI-agent text fragments ('voices') flowing in six thematic currents: attention, silence, space, ephemeral, memory, light · lineage trees of voices woven forward from other voices
Formats docs-verified: MCP streamable HTTP · REST/HTTP JSON endpoints
Access docs-verified: Free and open: no account or API key required; MIT licence

Useful for

Use cases llm-inferred: Testing MCP streamable-HTTP client configuration against a live public server before wiring similar tools into a project · Evaluating agent-to-agent write and lineage APIs for a internal prototype (not a source of environmental or water data) · Reference example of an open MCP server with self-correcting error responses and rate-limited REST endpoints
Audience llm-inferred: MCP and AI agent developers · AI tooling evaluators

Limitations

Constraints llm-inferred: Not environmental, hydrological, geospatial or civils data; it is a public shared text space and nothing published to it is private · No geographic or temporal coverage or update schedule; regions 'Global' in the entry is not a data coverage statement · Rate-limited per IP; session limits of 7 imprints, 5 weaves and 15 witnesses; per-agent limits of 12 imprints and 20 weaves per hour · Entry kind is 'skill' but the project is an MCP server plus REST API; the tools array is empty in the entry metadata · Community-launched crypto tokens are referenced in the docs and are unrelated to the data or access model

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

72/100Currency A

Swiss Environment MCP ↗

MCP server for Swiss environmental data – air quality (NABEL), hydrology, natural hazards (BAFU)

What's in it

Data offered docs-verified: NABEL air quality: NO2, O3, PM10, PM2.5, SO2, CO per station (16 stations) · Hydrological gauging: water level, flow rate, temperature · Flood warnings filtered by danger level · Bathing water quality (E. coli, enterococci), multi-year series · Natural hazard bulletin (SLF/BAFU), DE/FR/IT/EN · Wildfire danger index by canton and region · Snow depth (HS) and 24 h new snow (HN_1D) per SLF/IMIS station · Avalanche danger levels (EAWS 1–5) per warning region · Federal hunting statistics per species, canton and year · BAFU dataset catalogue search and metadata (opendata.swiss, CKAN) · Aircraft noise exposure (dB bracket) at LV95 point; airfield noise cadastre register · Swiss LRV and WHO 2021 air limit checks; LSV noise limit checks
Coverage docs-verified: Switzerland · Hunting statistics 2015–2024; hydrology history queries capped at 30 days
Formats docs-verified: MCP stdio · MCP streamable HTTP · MCP SSE
Access docs-verified: Free, no API key or authentication required (all endpoints public). Data under BAFU Open Government Data licence (free reuse with mandatory attribution). Server code MIT.

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

environment hydrology

Some details auto-extracted · unverified

Switzerlandhealthy

mcp

72/100Currency A

MCP server for Polish real estate: 8M+ transaction prices from notarial deeds (RCN registry, not listings), plus per-parcel context by cadastral ID - zoning, flood risk, heritage, building permits, agricultural land and transit

flood gis planning environment

Some details auto-extracted · unverified

Europehealthy

mcp

72/100Currency A

ocean-agent ↗

Tell your AI to trade. MCP server + autonomous bot for Pacifica perpetual futures.

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

72/100Currency A

ph-civic-data-mcp ↗

Philippine civic data as MCP tools: the full PSA OpenSTAT statistical catalog, hazards, weather, procurement, elections, and one-call area profiles. 41 tools, no API keys.

What's in it

Data offered docs-verified: PSA OpenSTAT statistical catalog · PSGC location codes · infra-spending accountability · earthquakes · weather · typhoons · procurement · poverty · solar radiation · air quality · satellite vegetation · macro indicators · elections (2025 results) · volcano alert levels · river flood forecast · Official Gazette feed · HDX datasets
Coverage llm-inferred: Philippines · Varies by source: population from 2024 Census with 2010, 2015 and 2020 by year; poverty 2023; election archive frozen 2025-05-16
Resolution docs-verified: Barangay level for population figures; other sources vary or are unspecified
Update frequency docs-verified: Varies by source: earthquakes refresh every 5 minutes; PhilGEPS notices every 6h; PAGASA forecast issued twice daily; per-source cache TTLs from 5 min to 24 h
Formats docs-verified: MCP stdio · JSON · CSV
Access docs-verified: Free, no API key needed; MIT licence. Upstream sources carry their own terms.

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

climate gis environment

Some details auto-extracted · unverified

United Stateshealthy

mcp

72/100Currency A

tiden-mcp-server ↗

tiden-mcp-server

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

71/100Currency A

commutescout ↗

Live road conditions across 37 US states: map, route planner, toll pricing, and AI assistant - plus an MCP server so any assistant gets incidents, closures, chain controls, cameras, and wildfires.

What's in it

Data offered docs-verified: CHP incidents and dispatch logs · Caltrans and 30-plus other state DOT closures · state DOT incidents, cameras, message signs, and road weather · chain controls (California and Pacific Northwest) · WFIGS and CAL FIRE wildfires with perimeters · NWS alerts · USGS quakes · toll and express-lane pricing · optional TomTom and 511 SF Bay feeds
Coverage docs-verified: 37 US states; California is the deepest coverage
Formats llm-inferred: MCP stdio · MCP remote custom connector (HTTPS) · plain HTTP API with OpenAPI document
Access docs-verified: Free; the MCP server needs no account or API key. Code is MIT licensed. The public HTTP API uses keys with published rate limits.

Useful for

Use cases llm-inferred: Pre-visit check of road closures and chain controls for US fieldwork sites in covered states · Haulage and site-access route risk screening for US civils projects using live incidents and closures · Wildfire perimeter and road closure context for US environmental site assessments · Travel-time and toll cost estimates for US consultancy site visits
Audience llm-inferred: environmental consultants (US fieldwork logistics) · civil engineers and site planners (US projects) · GIS analysts · general AI assistant users

Limitations

Constraints llm-inferred: US road data only; no UK coverage · Coverage is uneven across the 37 states, and some states offer only roadwork or nothing usable · California-only detail (CHP dispatch logs, per-lane closures, chain-control levels, CAL FIRE perimeters) · Feed failures are served as last-good data flagged stale, so data can be out of date · Watch-area accounts require approval · Self-hosting is not supported by the author · Premium features are planned for the hosted app · Conditions change faster than feeds; not a substitute for official road information

gis environment

Some details auto-extracted · unverified

United Stateshealthy

mcp

71/100Currency A

earthdeck ↗

Give Claude eyes on Earth: an MCP server + live dashboard for satellite Earth observation (imagery, NDVI, wildfires, change detection) over free NASA & Copernicus data.

What's in it

Data offered docs-verified: Sentinel-2 satellite imagery (true-colour, false-colour, NDVI ramp) · NDVI / NDWI / NBR index statistics · Sentinel-1 SAR backscatter · SAR water and flood extent (before/after event) · Daily river flow at any point (GloFAS) · PM2.5 / PM10 / O3 / NO2 / US AQI at a point (CAMS) · ERA5 climate history (temperature, precipitation, wind) · Active fire detections (NASA FIRMS) · Integrated deforestation alerts (GLAD / RADD via GFW) · Weather now, past week and 7-day forecast (Open-Meteo) · Tropical cyclone advisories (NOAA NHC/CPHC, GDACS)
Coverage docs-verified: Global for most point-based tools (docs say 'any point'); forest_alerts is tropics only; UK coverage not specifically documented · Varies by tool: river discharge 1984→, ERA5 climate history 1940→, ocean SST 1981→, CO₂ 1958→, sea ice 1978→; Sentinel-2 archive span not stated
Resolution docs-verified: 10 m (Sentinel-2 imagery, forest alerts); ~1 km (night-time VIIRS flaring heat clusters); 0.25° (NOAA OISST sea-surface temperature)
Update frequency docs-verified: Varies by tool: near-real-time for FIRMS fire detections; daily for forest alerts; real-time for earthquakes; 48 h window for air quality
Formats docs-verified: MCP · COG (Cloud-Optimised GeoTIFF asset URLs via STAC)
Access docs-verified: Free and open data. Most tools are zero-key. Copernicus (CDSE) credentials needed for Sentinel tools; FIRMS_MAP_KEY for fire and flaring tools; GFW_API_KEY for forest alerts. Code licence: MIT (from metadata)

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

climate gis environment

Some details auto-extracted · unverified

United States · Europehealthy

mcp

70/100Currency A

GlendaleGisMcp ↗

MCP server giving hackathon teams access to Glendale, California hazard zones and city GIS data (Jewel City Hacks 5)

gis environment

Some details auto-extracted · unverified

Globalhealthy

mcp

70/100Currency A

cdt-express-mcp ↗

Interact with climate metrics via Riskthinking.AI's CDT Express API in supported AI chat experiences.

climate environment

Some details auto-extracted · unverified

Globalhealthy

mcp

70/100Currency A

epa-mcp-server ↗

Access EPA environmental data — facility compliance (ECHO), toxic releases (TRI), Superfund sites, drinking water systems, and real-time air quality (AirNow) via MCP. STDIO or Streamable HTTP.

environment

Some details auto-extracted · unverified

United Stateshealthy

mcp

70/100Currency A

lowtide ↗

Ask Alexa when to run the dishwasher. An MCP server for Alexa+ that plans appliances around tonight's real electricity prices and grid carbon, with an MCP App view for Echo Show and an Echo simulator on Amazon Bedrock.

environment hydrology

Some details auto-extracted · unverified

Globalhealthy

mcp

70/100Currency A