Tutorial: Crisis Intelligence

Government

Data source: GDACS, GDELT

Overview

Crisis Intelligence searches across 2 data sources (GDACS, GDELT) in a single query. It deduplicates and normalizes results, saving you from building 2 separate integrations. This tutorial walks through all 4 tools with working code examples.

Prerequisites

Sign up at https://context.gnist.ai/signup for a free API key (100 calls/day).
Choose your integration method: MCP protocol or REST API.

Connect via MCP

Add to your MCP client config (Claude Desktop, Cursor, etc.):

MCP Config

{
  "mcpServers": {
    "gnist-crisis-intelligence": {
      "url": "https://context.gnist.ai/mcp/crisis-intelligence/",
      "headers": {
        "Gnist-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Tools (4)

`search_crises`

Search for crises combining GDACS disaster alerts, USGS earthquakes, NOAA weather alerts, and GDELT news. Returns structured disaster events, seismic data, active weather alerts, and related news articles from global media. All eight sources are queried in parallel for fast response. Sources: - GDACS: UN/EU disaster alerts (earthquakes, floods, cyclones, volcanoes, droughts, wildfires) - USGS: Real-time seismic events with magnitude, depth, and location - NOAA NWS: Active US weather alerts (severe storms, floods, fire weather) - NVE: Norwegian flood warnings with regional activity levels - SMHI: Swedish weather warnings (fire risk, storms, floods, extreme weather) - DMI: Danish weather warnings (storms, rain, wind, snow, fog, ice) - FMI: Finnish weather warnings via MeteoAlarm (fire risk, storms, wind, rain, flooding) - GDELT: Global news media coverage and sentiment Examples: search_crises(query="earthquake") search_crises(query="flood", country="Bangladesh", alert_levels="Orange,Red") search_crises(query="wildfire California", event_types="WF", news_timespan="24h")

Parameter	Type	Required	Description
`query`	string	required	Search term — crisis type, country, or topic (e.g. 'earthquake Turkey', 'flood Bangladesh').
`from_date`	string	optional	Start date (YYYY-MM-DD). Defaults to 90 days ago. (default: )
`to_date`	string	optional	End date (YYYY-MM-DD). Defaults to today. (default: )
`event_types`	string	optional	Comma-separated: EQ (earthquake), TC (tropical cyclone), FL (flood), VO (volcano), DR (drought), WF (wildfire). (default: )
`alert_levels`	string	optional	Comma-separated: Green, Orange, Red. (default: )
`country`	any	optional	Filter by country name.
`news_timespan`	string	optional	GDELT news lookback: 24h, 7d, 1m. (default: `7d`)
`max_events`	integer	optional	Max disaster events. (default: `25`)
`max_articles`	integer	optional	Max news articles. (default: `10`)
`min_magnitude`	number	optional	Minimum earthquake magnitude for USGS data. (default: `4.5`)
`max_earthquakes`	integer	optional	Max USGS earthquake results. (default: `10`)
`max_weather_alerts`	integer	optional	Max NOAA weather alerts. (default: `10`)
`max_flood_warnings`	integer	optional	Max NVE flood warnings (Norway). (default: `10`)
`max_smhi_warnings`	integer	optional	Max SMHI weather warnings (Sweden). (default: `10`)
`max_dmi_warnings`	integer	optional	Max DMI weather warnings (Denmark). (default: `10`)
`max_fmi_warnings`	integer	optional	Max FMI weather warnings (Finland). (default: `10`)

curl -X POST "https://context.gnist.ai/mcp/crisis-intelligence/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "search_crises", "arguments": {"query": "'earthquake"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/crisis-intelligence/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'query': "'earthquake"}, 'name': 'search_crises'}},
)
print(resp.json())

`get_active_crises`

Get currently active disaster events worldwide from GDACS. Returns ongoing crises from the last 90 days. Defaults to Orange and Red alert levels — the most significant events requiring attention. Event types: - EQ: Earthquake - TC: Tropical Cyclone - FL: Flood - VO: Volcano - DR: Drought - WF: Wildfire Examples: get_active_crises() get_active_crises(alert_levels="Red") get_active_crises(event_types="EQ,VO", country="Japan")

Parameter	Type	Required	Description
`event_types`	string	optional	Comma-separated: EQ, TC, FL, VO, DR, WF. Empty = all types. (default: )
`alert_levels`	string	optional	Comma-separated: Green, Orange, Red. Default: Orange,Red. (default: )
`country`	any	optional	Filter by country name.
`limit`	integer	optional	Max events to return. (default: `50`)

curl -X POST "https://context.gnist.ai/mcp/crisis-intelligence/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "get_active_crises", "arguments": {"event_types": ""}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/crisis-intelligence/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'event_types': ''}, 'name': 'get_active_crises'}},
)
print(resp.json())

`list_crisis_sources`

List all crisis intelligence data sources and their coverage. Shows which disaster monitoring systems and news sources are queried during crisis searches. Examples: list_crisis_sources()

curl -X POST "https://context.gnist.ai/mcp/crisis-intelligence/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "list_crisis_sources", "arguments": {}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/crisis-intelligence/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {}, 'name': 'list_crisis_sources'}},
)
print(resp.json())

`report_feedback`

Report a bug, feature request, or general feedback for this data source. Use this when something doesn't work as expected, when you'd like a new feature, or when you have suggestions for improvement. Args: feedback: Describe the issue or suggestion. feedback_type: One of 'bug', 'feature_request', or 'general'.

Parameter	Type	Required	Description
`feedback`	string	required
`feedback_type`	string	optional	(default: `general`)

curl -X POST "https://context.gnist.ai/mcp/crisis-intelligence/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "report_feedback", "arguments": {"feedback": "example"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/crisis-intelligence/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'feedback': 'example'}, 'name': 'report_feedback'}},
)
print(resp.json())

Common Patterns

Search then retrieve
Use search_crises to find items, then get_active_crises to get full details. This two-step pattern is common for exploring data before drilling down.

Pagination
Several tools support limit, offset, or page parameters. Start with small limits during development, then increase for production queries.

Date range filtering
Use date range parameters to narrow results to a specific time window. Dates are typically in YYYY-MM-DD format.

FAQ

What data does Crisis Intelligence provide?

Unified crisis monitoring combining GDACS disaster alerts (earthquakes, floods, cyclones, volcanoes, droughts, wildfires) with GDELT global news coverage. It exposes 4 tools: search_crises, get_active_crises, list_crisis_sources, report_feedback.

What do I need to get started?

A Gnist API key (free tier: 100 calls/day). Sign up at https://context.gnist.ai/signup.

What format does the Crisis Intelligence API return?

JSON, via either MCP protocol (JSON-RPC 2.0) or REST API.

Which data sources does Crisis Intelligence aggregate?

GDACS, GDELT. Results are deduplicated and normalized into a consistent format.