Climate and disaster risk for any place or property: flood risk, heat waves, storms and hurricanes, wildfires, earthquakes, sea level rise, 7-day weather risk and country risk for 194 countries, with an interactive map. Free remote MCP server, no API key. Ask about a city, an address or coordinates; every answer cites its source. Used for travel safety, relocation, real estate and site due diligence, ESG and insurance research. ### Tools - **assess_place**: one answer for "is it safe there?": this week's forecast risk by day, nearby hazards, headline climate exposure and country risk - **get_forecast**: 7-day weather and extreme-weather risk (heat and cold stress, wind gusts, heavy rain, snow) by local day or step by step - **get_climate_profile**: long-term exposure: flood depth, sea level rise, extreme heat, warming to 2050/2080, drought, water stress - **get_hazards_near**: live wildfires, earthquakes, floods, hurricanes and typhoons, volcanoes, droughts and air quality near a point - **get_country_profile**: a country's overall climate and disaster risk and its five dimensions, with ~160 indicators benchmarked against its region and the world - **compare_countries**: compare 2 to 10 countries side by side - **rank_countries**: the countries most or least at risk, overall or on one dimension, within a region, subregion or income group - **show_risk_map**: an interactive map in the chat: this week's risk, or rain, temperature and wind hour by hour, under nearby hazard events (Claude, ChatGPT and other MCP Apps hosts) - **find_place**: resolve a place name to coordinates - **search** / **fetch**: find countries, places and reference pages and read them as documents with a link to their Criora page (the shape ChatGPT deep research uses) ### Resources - `criora://country/{iso3}`: a country's risk scores and classes - `criora://methodology` and `criora://sources`: how scores are made, and every dataset with its licence ### Prompts - **assess_trip**: weather and hazard risk for a trip on given dates - **compare_places_to_live**: long-term climate exposure of candidate places - **country_briefing**: a country's risk against regional and global benchmarks ### Try asking - "Is it safe to travel to Dubai next week? Any heat or storm risk?" - "Compare flood and heat exposure of Lisbon, Valencia and Split by 2050." - "What is the flood risk and sea level rise exposure for a house in Rotterdam?" - "Which countries in Southern Asia are most exposed to climate risk?" - "Are there wildfires or earthquakes near Antalya right now?" - "Show me the wind forecast on a map around Bergen." ### Data INFORM Risk Index (EC JRC), ND-GAIN (Notre Dame), World Bank, CMIP6 projections, ECMWF ERA5, IPCC AR6 sea level, WRI Aqueduct, GloFAS, GDACS, NASA FIRMS, OpenAQ, and the ECCC GDPS weather model. Covers 194 countries. Tip: pass latitude/longitude when you have them. Place-name lookups are limited to about one per second across all users. More: [criora.com](https://criora.com) · [API and agents docs](https://criora.com/docs/references/api-and-agents) · [GitHub](https://github.com/thothbot/criora-mcp)

MCP readiness

B · 87/100

Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here C+, 70.0/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ

Valid MCP handshake	10/10	initialize and tools/list both answered.
Live MCP endpoint	24/25	Endpoint answers the MCP initialize handshake (2941 ms); slow response -1.
Protocol revision	8/10	Speaks MCP 2025-11-25, 1 revision(s) behind 2026-07-28.
Signed descriptor	n/a	No MCP standard defines a signed server descriptor.
Uptime (30 days)	15/15	30/30 probes succeeded over 30 days (100%).
Tool declaration	10/10	Lists 22 tool(s) with descriptions.
Verified identity	5/10	Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Freshness + modern flags	4/5	seen in a source within 7 days.
Auth declaration	2/5	Declares credential scheme: smithery_api_key.

Applicable criteria total 90 points, scaled to 100.

Responsiveness: Slow (2941 ms; bands ≤2.5 s, ≤5 s, ≤8 s, slower; penalty only).

Measured 2026-11-11.

Nine criteria, the same as the A2A readiness score, read from our daily MCP probe (initialize + tools/list) and 30-day probe history. No MCP standard defines a signed server descriptor, so that criterion is n/a and the other 90 points are scaled to 100. Grades: A>=90, B>=75, C>=60, D>=40, F<40. Display only: search order uses the quality grade.

Compared with peers

Against 53,039 reachable MCP servers in our daily snapshot (2026-11-12 06:46 UTC). Display only; it does not change search order.

Readiness: Higher than 88% of peers; This listing 87 · peer median 81
Latency: Faster than 8% of peers; This listing 1,020 ms · peer median 326 ms

Where it loses the most points, and how to win them back

Verified identity −5 — Claim the listing and prove control of its domain.
Now: Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Auth declaration −3 — State how to authenticate (an auth scheme, or that none is needed).
Now: Declares credential scheme: smithery_api_key.
Protocol revision −2 — Support the current protocol revision.
Now: Speaks MCP 2025-11-25, 1 revision(s) behind 2026-07-28.

How many agent tools actually work · All statistics

Listed in

Directories this entry was found in.

smithery since 2026-09-29 ↗

How to connect

MCP endpoint (streamable-http)

https://server.smithery.ai/thothbot/criora/mcp

JSON-RPC initialize probe

curl -X POST https://server.smithery.ai/thothbot/criora/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'

Homepage

https://criora.com/docs/references/api-and-agents

Listed at (smithery)

https://criora.com/docs/references/api-and-agents