accueil / serveurs / Géo & Temps / com.criora/criora
com.criora/criora
serveur MCP (Model Context Protocol) · criora 1.4.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que com.criora/criora est sûr ?
Au dernier audit MCP Hub, le serveur MCP « com.criora/criora » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.
Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.
Les 12 outils
- assess_place≈ 4522 tokens
Climate and disaster risk overview of one place or property in a single answer: this week's forecast risk by day, natural hazards happening nearby, the headline long-term exposures (heat, river and coastal flooding, sea level rise, water stress, drought, heavy rain, wildfire, climate zone) and the risk profile of the country it lies in. Use it first for an open question about one place ("is it safe there", "what are the risks", "should I worry about floods or heat"). For one specific question call the matching tool, which answers it in full: get_forecast, get_hazards_near, get_climate_profile or get_country_profile. To compare places, call get_climate_profile once per place. Give latitude and longitude, or a place name, which is resolved to its best match and reported back. Returns the forecast days, the hazard events, the headline climate layers with their sources, the country summary and criora_url, the place on the Criora map.
Paramètres, retour & exemple (3)
Paramètresplace· ? · optionnel
A place name or address, used only when latitude and longitude are not given. It is resolved to its best match by a geocoder shared by every user and limited to one lookup a second, so pass coordinates when you have themlatitude· ? · optionnel
Latitude of the place asked about, in degrees, WGS84. Give it with longitude, or give place insteadlongitude· ? · optionnel
Longitude of the place asked about, in degrees, WGS84. Give it with latitude, or give place instead
Exemple d'appel{"name": "assess_place", "arguments": {"place": "texte", "latitude": "texte", "longitude": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"climate": "texte", "country": "texte", "forecast": "texte", "location": "texte", "criora_url": "texte", "country_url": "texte", "resolved_from": "texte", "hazards_nearby": "texte"}} - compare_countries≈ 1301 tokens
Climate and disaster risk of two to ten named countries side by side: each one's overall risk score and class, its climate, nature, social, governance and adaptation scores, and its world rank by overall risk. Use it when the countries are known in advance. To find the countries most or least at risk use rank_countries; for one country's indicators, get_country_profile. Countries are ISO 3166-1 alpha-3 codes or English names; an unknown one is refused with the expected form. Scores run 0 to 100, higher is riskier, and rank 1 is the highest risk among 194 countries. Sources: INFORM Risk Index, ND-GAIN and the World Bank.
Paramètres, retour & exemple (1)
Paramètrescountries· array · requis
ISO3 codes or English names of 2 to 10 countries
Exemple d'appel{"name": "compare_countries", "arguments": {"countries": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"countries": []}} - fetch≈ 624 tokens
One Criora document as markdown, with its title, the Criora page to cite and the sources it draws on, by an id search returned. country:<ISO3> (country:BGD) gives the country's risk score, class and rank, each dimension with its class, and its most notable indicators against the world and regional medians. place:<latitude>,<longitude> (place:23.8103,90.4125) gives this week's forecast risk by day, the most notable hazard events nearby, the headline climate exposures and the country. page:methodology and page:sources are those pages of the site; catalog:layers lists every climate layer and catalog:indicators every country indicator. Use it to read a document for research and cite it. The specific tools answer with every figure as data, through get_country_profile, assess_place and the rest. An id of another form is refused with the forms it takes. A long text is cut at a paragraph, with the page that has the rest.
Paramètres, retour & exemple (1)
Paramètresid· string · requis
An id search returned: country:<ISO3>, place:<latitude>,<longitude>, page:<name> or catalog:layers / catalog:indicators
Exemple d'appel{"name": "fetch", "arguments": {"id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "metadata": "texte"}} - find_place≈ 536 tokens
Candidate coordinates for a place name or address, best match first, each with its full name and kind (city, state, road and so on). Call it when a name is ambiguous (several Springfields) and the right candidate must be chosen, or when one place is the subject of several calls and its coordinates should be looked up once. The other place tools take a name themselves and use its best match, so a single question about an unambiguous place needs no find_place first. It queries OpenStreetMap Nominatim (ODbL) through Criora's geocoder, which every user shares and which sends one request a second: a burst of calls waits its turn, and a name looked up in the last week is answered from a cache. A name that matches nothing returns an empty list. A city resolves to its centre as OpenStreetMap maps it.
Paramètres, retour & exemple (2)
Paramètreslimit· integer · optionnel
How many candidates to returnquery· string · requis
A place name or address, in any language
Exemple d'appel{"name": "find_place", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": []}} - get_climate_profile≈ 2883 tokens
Long-term climate risk and environmental data of a place or property, read at the point from 55 global layers: river and coastal flood depth of a 100-year flood now and in 2050 and 2080, sea level rise, extreme heat and cold days, heavy rain, drought (SPI-12, aridity, WRI drought risk), water stress, wind and storm days, warming and rainfall change to 2050 and 2080 (CMIP6), NDVI vegetation index and leaf area, wildfire burned area, soil moisture, snow, surface water, elevation, slope, land subsidence, land cover, built-up share and the Köppen climate zone. Use it for what a place is exposed to over years, and once per place to compare places; assess_place has only the headline layers. For this week's weather use get_forecast; for events happening now, get_hazards_near. Narrow it with categories, or with layers by id: the resource criora://layers, or fetch catalog:layers, lists every layer with its unit, years and source. Returns each layer's readings by band with its unit, year, cell size and source (ERA5, CMIP6, WRI Aqueduct, IPCC AR6, MODIS, JRC, Copernicus DEM and others). Give latitude and longitude, or a place name.
Paramètres, retour & exemple (5)
Paramètresplace· ? · optionnel
A place name or address, used only when latitude and longitude are not given. It is resolved to its best match by a geocoder shared by every user and limited to one lookup a second, so pass coordinates when you have themlayers· ? · optionnel
Only these layers, by id, e.g. ndvi/annual for the NDVI vegetation index or flood_riverine/inundation for river flood depth; every id with what it measures is in the resource criora://layers. Combined with categories, both are givenlatitude· ? · optionnel
Latitude of the place asked about, in degrees, WGS84. Give it with longitude, or give place insteadlongitude· ? · optionnel
Longitude of the place asked about, in degrees, WGS84. Give it with latitude, or give place insteadcategories· ? · optionnel
Only the layers of these categories; every layer when omitted. temperature: hottest day of the year, coldest night of the year, hot days over 35 °C, summer days, tropical nights, frost nights, ice days, mean temperature with the coldest and warmest month, UTCI felt temperature (heat and cold stress), warming to 2050 and 2080 (CMIP6), change in the warmest month's maximum to 2050 and 2080, change in the coldest month's minimum to 2050 and 2080; precipitation: heavy-rain days (10 to 100 mm) and the wettest day, precipitation with the driest and wettest month, daily rain of the wettest month, change in annual rainfall to 2050 and 2080, change in the wettest quarter's rainfall, change in the driest quarter's rainfall, drought risk (WRI Aqueduct), SPI-12 drought index, aridity index, snow cover, snow water equivalent, snowmelt, snow albedo; wind: strongest wind gust of the year, gale, storm and hurricane-force gust days, mean wind speed, CAPE, the energy of thunderstorms; water: baseline water stress (WRI Aqueduct), water stress in 2050 and 2080 (WRI Aqueduct), soil moisture, relative humidity, vapour pressure deficit, potential evaporation, surface water occurrence from 38 years of Landsat (JRC), share of lakes, rivers and wetlands, lake or wetland type, distance to the coast; flooding: river flood depth of a 100-year flood, now and in 2050 and 2080 (WRI Aqueduct), coastal flood depth of a 100-year flood, now and in 2050 and 2080 (WRI Aqueduct), GloFAS 30-day flood forecast, sea level rise to 2050 and 2100 (IPCC AR6); vegetation: NDVI vegetation index, annual mean, minimum and maximum (MODIS satellite), leaf area index of trees and shrubs, leaf area index of grass and crops, area burned by wildfire last year (GFED, satellite), area burned by wildfire each year since 2002 (GFED, satellite); terrain: elevation (Copernicus DEM), slope, terrain ruggedness, probability of land subsidence over 1 cm a year, land subsidence rate class; landcover: land cover class (MODIS satellite), built-up share of the land (JRC GHSL, Sentinel-2 and Landsat); misc: Köppen climate zone, now and in 2050 and 2080, solar radiation, solar radiation of the sunniest month, surface runoff
Exemple d'appel{"name": "get_climate_profile", "arguments": {"place": "texte", "layers": "texte", "latitude": "texte", "longitude": "texte", "categories": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"notes": [], "layers": [], "sources": {}, "datasets": {}, "location": "texte", "criora_url": "texte", "resolved_from": "texte"}} - get_country_profile≈ 2080 tokens
Climate and disaster risk of one country, of 194, for ESG, investment, insurance and humanitarian screening: the overall risk score (0 to 100, higher is riskier), class and world rank, and the climate, nature, social, governance and adaptation scores and classes, with its region and income group. Use it for one country in depth. For named countries side by side use compare_countries; for the countries most or least at risk, rank_countries; for a place inside a country, assess_place. include_indicators=true adds the indicators behind each dimension from the INFORM Risk Index, ND-GAIN and the World Bank (flood, earthquake and drought risk, water stress, food security, health, governance and about 150 more), those furthest from the world median first, each with its value, year, source and the medians of the world, region, subregion and income group; indicators_limit caps them per dimension, and criora://indicators lists them all. The country is an ISO 3166-1 alpha-3 code or its English name; an unknown one is refused with the expected form.
Paramètres, retour & exemple (3)
Paramètrescountry· string · requis
ISO 3166-1 alpha-3 code (e.g. BGD) or English country nameindicators_limit· integer · optionnel
With include_indicators, how many indicators to list per dimensioninclude_indicators· boolean · optionnel
Add the underlying indicators, the furthest from the world median first, each with its world and regional medians; the scores alone when false
Exemple d'appel{"name": "get_country_profile", "arguments": {"country": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"meta": "texte", "sources": "texte", "indicators": "texte", "country_url": "texte", "country_code": "texte", "nature_level": "texte", "nature_score": "texte", "social_level": "texte", "social_score": "texte", "climate_level": "texte", "climate_score": "texte", "overall_level": "texte"}} - get_forecast≈ 1897 tokens
This week's weather and extreme-weather risk at a place: heat waves and cold (graded on the UTCI felt temperature), storms and wind gusts, heavy rain, snow and freezing rain, by local day, with each day's risk class from Very low to Critical and the hazard behind it. Use it for the weather or the weather risk in the next seven days. For disasters already happening use get_hazards_near; for what a place is exposed to over years, get_climate_profile. Returns for each day the minimum and maximum temperature, peak precipitation rate, peak wind gust and the risk with its physical reading; hourly=true adds every forecast step. Steps are hourly on the first day, then 3-hourly, then 6-hourly from the fourth day, so a day's true peak can fall between two steps; a day marked partial is cut by the forecast window. Source: Environment and Climate Change Canada GDPS model, read at its 15 km cell. Give latitude and longitude, or a place name.
Paramètres, retour & exemple (4)
Paramètresplace· ? · optionnel
A place name or address, used only when latitude and longitude are not given. It is resolved to its best match by a geocoder shared by every user and limited to one lookup a second, so pass coordinates when you have themhourly· boolean · optionnel
Add every forecast step, hour by hour where the model has them, to the daily summarylatitude· ? · optionnel
Latitude of the place asked about, in degrees, WGS84. Give it with longitude, or give place insteadlongitude· ? · optionnel
Longitude of the place asked about, in degrees, WGS84. Give it with latitude, or give place instead
Exemple d'appel{"name": "get_forecast", "arguments": {"place": "texte", "hourly": true, "latitude": "texte", "longitude": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"run": "texte", "days": [], "notes": [], "steps": "texte", "units": {}, "issued": "texte", "source": "texte", "location": "texte", "precision": {}, "criora_url": "texte", "risk_scale": [], "resolved_from": "texte"}} - get_hazards_near≈ 1353 tokens
Natural disasters and hazards happening now or recently near a place: wildfires (NASA FIRMS satellite fire detections), earthquakes, floods, tropical cyclones (hurricanes and typhoons), volcanic eruptions and droughts (GDACS), US National Weather Service flood, tropical cyclone and fire warnings, and air quality (OpenAQ reference monitors). Use it for what is happening there now. For the weather forecast use get_forecast; for long-term exposure, get_climate_profile. Returns the most severe and most recent events first, each with its type, severity (low to critical), distance, bearing and time, and total and counts_by_type cover every event found. radius_km (1 to 500), event_types and days (1 to 30) narrow the search; without radius_km every type is searched at its largest distance, which radius_used_km reports. Give latitude and longitude, or a place name.
Paramètres, retour & exemple (6)
Paramètresdays· ? · optionnel
Only events of the last N days, 1 to 30; all current when omittedplace· ? · optionnel
A place name or address, used only when latitude and longitude are not given. It is resolved to its best match by a geocoder shared by every user and limited to one lookup a second, so pass coordinates when you have themlatitude· ? · optionnel
Latitude of the place asked about, in degrees, WGS84. Give it with longitude, or give place insteadlongitude· ? · optionnel
Longitude of the place asked about, in degrees, WGS84. Give it with latitude, or give place insteadradius_km· ? · optionnel
Search radius in km, 1 to 500; the largest when omittedevent_types· ? · optionnel
Only these kinds of event; every kind when omitted
Exemple d'appel{"name": "get_hazards_near", "arguments": {"days": "texte", "place": "texte", "latitude": "texte", "longitude": "texte", "radius_km": "texte", "event_types": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "total": 1, "center": "texte", "listed": 1, "generated_at": "texte", "resolved_from": "texte", "counts_by_type": {}, "radius_used_km": {}}} - get_map_events≈ 638 tokens
The hazard events the interactive map loads when the reader pans or zooms to a new view. The map calls it in clients that display it; to list the hazards near a place, use get_hazards_near.
Paramètres, retour & exemple (3)
Paramètreslatitude· number · requis
Latitude of the view's centrelongitude· number · requis
Longitude of the view's centreradius_km· number · requis
How far the view reaches from its centre, in km
Exemple d'appel{"name": "get_map_events", "arguments": {"latitude": 1, "longitude": 1, "radius_km": 1}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"events": []}} - rank_countries≈ 1174 tokens
The countries most or least at climate and disaster risk, overall or on one dimension (climate, nature, social, governance, adaptation), each with its score, risk class and rank, optionally only those in a region, subregion or income group. Answers "which countries are most exposed to climate risk", "the riskiest countries in Southern Asia" or "low-income countries with the lowest adaptation score". For countries named in advance use compare_countries; for one country in depth, get_country_profile. Regions, subregions and income groups are named as the countries' meta names them; a name no country has is refused with the names there are. The filters combine, and a combination that matches nothing returns an empty list; limit cuts the list, while matched counts every country that passed the filters. Scores run 0 to 100, higher is riskier. A country's rank is among all 194 countries, 1 being the highest risk: a filter narrows the list but not the rank. Countries without a score on the dimension are counted in no_score.
Paramètres, retour & exemple (6)
Paramètreslimit· integer · optionnel
How many countries to listorder· string · optionnel · highest_risk | lowest_risk
Most at risk first, or least at risk firstregion· ? · optionnel
Only countries in this UN region, e.g. Asiadimension· string · optionnel · overall | climate | nature | social | governance | adaptation
The score to rank bysubregion· ? · optionnel
Only countries in this UN M49 subregion, e.g. Southern Asiaincome_group· ? · optionnel
Only countries in this World Bank income group, e.g. Low income
Exemple d'appel{"name": "rank_countries", "arguments": {"limit": 1, "order": "highest_risk", "region": "texte", "dimension": "overall", "subregion": "texte", "income_group": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"order": "highest_risk", "listed": 1, "filters": "texte", "matched": 1, "no_score": 1, "countries": [], "dimension": "texte"}} - search≈ 537 tokens
Find Criora's documents on a subject, to read and cite with fetch: a country's climate and disaster risk profile, a place's risk report, the pages on Criora's methodology and data sources, and the data catalogue (every climate layer with satellite data such as NDVI, and the country indicators). Each result has the id fetch reads and the Criora page to cite. Use it to find what Criora has before reading it with fetch. For an answer in one call the specific tools are shorter: assess_place for a place, get_country_profile for a country, rank_countries for the countries most at risk. A country is found by its ISO 3166-1 alpha-3 or alpha-2 code or its English name. The words methodology or sources find those pages; layers, catalogue, satellite, NDVI or indicators find the data catalogue. Only when nothing else matches is the query looked up as a place name, in the geocoder every user shares; a place is found best by its name alone. Nothing found is an empty list.
Paramètres, retour & exemple (1)
Paramètresquery· string · requis
A country, a place name, or a subject: methodology, data sources, or the data catalogue (layers, NDVI, satellite, indicators)
Exemple d'appel{"name": "search", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": []}} - show_risk_map≈ 1310 tokens
Shows an interactive map of a place in clients that render apps, such as Claude and ChatGPT: this week's forecast risk over the area, hazard events nearby as markers, and the risk by day, which the reader can pan, zoom and open full screen. Instead of the risk, the map can lay the precipitation, temperature or wind forecast under the events (`layer`), hour by hour over the week, and the reader can switch between all four. A client without apps gets the same summary as text, with a link to the place on Criora's own map. Use it when the user wants to see the place, the week's risk or the hazards around it on a map, or when a map makes an answer clearer than a list. The figures come from the same sources as get_forecast and get_hazards_near, which give them in full. Give latitude and longitude, or place, which costs a lookup in the shared geocoder. With both, the coordinates are used and place only names the map, at no lookup: pass the name the user knows the place by, or the map is titled by its coordinates and country.
Paramètres, retour & exemple (5)
Paramètresfocus· string · optionnel · both | week | hazards
What the map shows: this week's forecast risk, the hazard events nearby, or bothlayer· string · optionnel · risk | precipitation | temperature | wind
The forecast field the map opens on, under the hazard events: the risk (default), or the precipitation, temperature or wind forecast when the question is about the weather itself. The reader can switch between them on the mapplace· ? · optionnel
A place name or address, used only when latitude and longitude are not given. It is resolved to its best match by a geocoder shared by every user and limited to one lookup a second, so pass coordinates when you have themlatitude· ? · optionnel
Latitude of the place asked about, in degrees, WGS84. Give it with longitude, or give place insteadlongitude· ? · optionnel
Longitude of the place asked about, in degrees, WGS84. Give it with latitude, or give place instead
Exemple d'appel{"name": "show_risk_map", "arguments": {"focus": "both", "layer": "risk", "place": "texte", "latitude": "texte", "longitude": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"days": "texte", "layer": "texte", "place": "texte", "radius_km": "texte", "criora_url": "texte", "events_total": "texte", "resolved_from": "texte", "counts_by_type": "texte"}}
C'est votre serveur ?
Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».