160-tool MCP server for real-time global intelligence from free public APIs: markets, liquidity, prediction markets, SEC filings, conflict, military, aircraft-cohort early warning, migration and border flows, cyber, climate, news and more. Dated observation history, 29 research prompts, cited briefs, geofences, SSE dashboard. MIT, no paid API keys.
Python ai-toolsai-watchanthropicclaudecybersecuritydashboardgeofencinggeopoliticalgeospatialintelligencemarketsmcpmigrationmilitarymodel-context-protocolnuclearosintreal-timespace-weatherthreat-intelligence
"""Infrastructure and transport tools: internet outages,
undersea cable health, navigational warnings, airport delays, global
air traffic, road traffic, webcams, shipping stress, cloud service
status.
Phase 26 split: Tool definitions moved byte-identical and dispatch
case bodies verbatim from server.py; handlers reach shared
infrastructure via ``runtime``. See tools/system.py for the pattern.
"""
from typing import Any
from mcp.types import Tool
from .. import runtime
from ..sources.jet_cohort import BIZJET_TYPES
from ..sources import (
infrastructure,
maritime,
aviation,
shipping,
service_status,
)
TOOLS: list[Tool] = [
# --- Infrastructure (2 tools) ---
Tool(
name="intel_internet_outages",
description="Get internet outages from Cloudflare Radar (last 7 days). Optional: CLOUDFLARE_API_TOKEN for higher limits.",
inputSchema={"type": "object", "properties": {}},
),
Tool(
name="intel_cable_health",
description="Assess undersea cable corridor health from NGA navigational warnings. 6 corridors scored 0-3.",
inputSchema={"type": "object", "properties": {}},
),
# --- Maritime (1 tool) ---
Tool(
name="intel_nav_warnings",
description="Get active navigational warnings from NGA Maritime Safety, each with every position its text states. feed_stale is true when the feed's newest active warning (before any navarea filter) is past the staleness threshold, and data_gaps then says so. Optional: navarea, an NGA area code (4, 12, A, P, C; IV and XII are accepted for 4 and 12).",
inputSchema={
"type": "object",
"properties": {
"navarea": {
"type": "string",
"description": "NGA area code: 4 (NAVAREA IV), 12 (NAVAREA XII), A (HYDROLANT), P (HYDROPAC) or C (HYDROARC); IV and XII are accepted for 4 and 12. Other NAVAREAs arrive inside the A, P and C series, so a value that matches no carried area returns an error and a data_gaps line, never a count of 0.",
},
},
},
),
# --- Aviation (1 tool) ---
Tool(
name="intel_airport_delays",
description="Get current US airport delays from FAA (20 major airports). No API key needed.",
inputSchema={"type": "object", "properties": {}},
),
# --- Aviation domestic (1 tool) ---
Tool(
name="intel_aviation_domestic",
description="Global air traffic snapshot from OpenSky Network: total airborne aircraft, regional breakdown, busiest origin countries, and sampled positions for mapping.",
inputSchema={"type": "object", "properties": {}},
),
# --- Traffic (2 tools) ---
Tool(
name="intel_traffic_flow",
description="Real-time traffic congestion for 20 major world cities via TomTom API. Congestion percentage, speeds, global average. Requires TOMTOM_API_KEY.",
inputSchema={"type": "object", "properties": {}},
),
Tool(
name="intel_traffic_incidents",
description="Major traffic incidents across 5 strategic regions (US East/West, Europe, Middle East, East Asia) via TomTom API. Requires TOMTOM_API_KEY.",
inputSchema={"type": "object", "properties": {}},
),
# --- Webcams (1 tool) ---
Tool(
name="intel_webcams",
description="Public webcam locations and live previews worldwide from Windy Webcams API. Filter by category (traffic, weather, landscape). Requires WINDY_API_KEY.",
inputSchema={
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Webcam category (traffic, weather, landscape, etc.)",
"default": "traffic",
},
"limit": {
"type": "integer",
"description": "Max cameras to return (default 50)",
"default": 50,
},
},
},
),
# --- Shipping (1 tool) ---
Tool(
name="intel_shipping_index",
description="Compute shipping stress index from dry bulk ETFs (BDRY, SBLK, EGLE, ZIM). Stress score 0-100.",
inputSchema={"type": "object", "properties": {}},
),
# --- Service Status (1 tool) ---
Tool(
name="intel_service_status",
description="Monitor cloud service provider status (AWS, Azure, GCP, Cloudflare, GitHub). Shows active incidents and recent outages. Optional: provider (aws/azure/gcp/cloudflare/github).",
inputSchema={
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "Filter by provider (aws, azure, gcp, cloudflare, github)",
},
},
},
),
Tool(
name="intel_bgp_status",
description="Get BGP routing status for one prefix or ASN from RIPEstat: RIS peer visibility per address family, announced space and neighbour count (ASN queries), observed origin ASNs and per-origin RPKI validation valid/invalid/unknown (prefix queries). A per-resource health check, not global hijack detection - RIPEstat has no target-free incident feed. No API key needed.",
inputSchema={
"type": "object",
"properties": {
"resource": {
"type": "string",
"description": "ASN (AS3333 or 3333) or CIDR prefix (193.0.0.0/21); bare IPs rejected",
},
},
"required": ["resource"],
},
),
# --- Aircraft cohort early warning (3 tools; approach inspired by kylemcdonald/ews) ---
Tool(
name="intel_jet_cohort_snapshot",
description=f"Live airborne snapshot of a tracked aircraft cohort from adsb.lol (free, no key, ODbL): business jets ({len(BIZJET_TYPES)} ICAO type designators, one request) or military. "
"Counts by type, PIA/LADD privacy flags, positions. Each call also learns the cohort (hex addresses persisted locally) that intel_jet_activity_anomaly and intel_jet_excess_origins filter on; run it periodically to build the cohort.",
inputSchema={
"type": "object",
"properties": {
"cohort": {"type": "string", "enum": ["bizjet", "military"], "default": "bizjet"},
"region": {
"type": "string",
"description": "global, conus, north_america, europe, middle_east, east_asia, or 'lamin,lomin,lamax,lomax' (filters the summary only; learning is global)",
"default": "global",
},
},
},
),
Tool(
name="intel_jet_activity_anomaly",
description="Early-warning check: peak concurrent airborne cohort aircraft (business jets or military) in the latest published UTC half-hour (or a given slot) vs the same slot on prior same-weekday dates, from adsb.lol globe_history heatmaps. US federal holiday-adjacent baseline dates are swapped for earlier weeks. Returns robust z-score, alert level 1-5 (normal/watch/elevated/high/alarm), deficit flag, and data gaps. Needs a learned cohort (see intel_jet_cohort_snapshot); downloads ~14 MB per uncached slot, cached on disk.",
inputSchema={
"type": "object",
"properties": {
"cohort": {"type": "string", "enum": ["bizjet", "military"], "default": "bizjet"},
"region": {
"type": "string",
"description": "global, conus, north_america, europe, middle_east, east_asia, or 'lamin,lomin,lamax,lomax'",
"default": "global",
},
"slot": {
"type": "string",
"description": "UTC ISO datetime inside the half-hour to score (default: latest published)",
},
"baseline_weeks": {"type": "integer", "minimum": 2, "maximum": 8, "default": 4},
"alarm_sigma": {"type": "number", "default": 5.0, "description": "z at which level 5 (alarm) fires"},
"min_learning_lead_hours": {
"type": "number",
"default": 24,
"description": "Only use cohort members first seen this long before the window (avoids selection bias). Negative values admit later-learned members for a first look; the result is then marked degraded with a selection-bias data gap.",
},
},
},
),
Tool(
name="intel_jet_excess_origins",
description="Where did an excess of cohort departures/arrivals come from? Infers takeoffs and landings from adsb.lol heatmap tracks for a 0.5-2 h window and the same window on prior weeks, density-clusters the endpoints (default 12-mile radius), and reports clusters above their baseline median with a pattern label: departure_anchor, arrival_anchor, regional concentration, diffuse, or no_excess. Optional reference point gives distance-to-event. At most 12 heatmap files (~14 MB each, cached) per call.",
inputSchema={
"type": "object",
"properties": {
"cohort": {"type": "string", "enum": ["bizjet", "military"], "default": "bizjet"},
"region": {"type": "string", "default": "global", "description": "Region preset or 'lamin,lomin,lamax,lomax'"},
"start": {"type": "string", "description": "UTC ISO start of the window (default: ends at the latest published slot)"},
"slots": {"type": "integer", "minimum": 1, "maximum": 4, "default": 2, "description": "Window length in half-hours"},
"baseline_weeks": {"type": "integer", "minimum": 1, "maximum": 4, "default": 3},
"ref_lat": {"type": "number", "description": "Optional event latitude for distance reporting"},
"ref_lon": {"type": "number", "description": "Optional event longitude for distance reporting"},
"cluster_radius_mi": {"type": "number", "default": 12, "minimum": 1, "maximum": 50},
"min_learning_lead_hours": {
"type": "number",
"default": 24,
"description": "Only use cohort members first seen this long before the window; negative admits later-learned members (marked as a selection-bias data gap)",
},
},
},
),
]
async def _internet_outages(arguments: dict[str, Any]) -> Any:
return await infrastructure.fetch_internet_outages(runtime.fetcher)
async def _cable_health(arguments: dict[str, Any]) -> Any:
return await infrastructure.fetch_cable_health(runtime.fetcher)
async def _nav_warnings(arguments: dict[str, Any]) -> Any:
return await maritime.fetch_nav_warnings(
runtime.fetcher, navarea=arguments.get("navarea")
)
async def _airport_delays(arguments: dict[str, Any]) -> Any:
return await aviation.fetch_airport_delays(runtime.fetcher)
async def _aviation_domestic(arguments: dict[str, Any]) -> Any:
return await aviation.fetch_domestic_flights(runtime.fetcher)
async def _traffic_flow(arguments: dict[str, Any]) -> Any:
from ..sources.traffic import fetch_traffic_flow
return await fetch_traffic_flow(runtime.fetcher)
async def _traffic_incidents(arguments: dict[str, Any]) -> Any:
from ..sources.traffic import fetch_traffic_incidents
return await fetch_traffic_incidents(runtime.fetcher)
async def _webcams(arguments: dict[str, Any]) -> Any:
from ..sources.webcams import fetch_webcams
return await fetch_webcams(
runtime.fetcher,
category=arguments.get("category", "traffic"),
limit=arguments.get("limit", 50),
)
async def _shipping_index(arguments: dict[str, Any]) -> Any:
return await shipping.fetch_shipping_index(runtime.fetcher)
async def _service_status(arguments: dict[str, Any]) -> Any:
return await service_status.fetch_service_status(
runtime.fetcher,
provider=arguments.get("provider"),
)
async def _bgp_status(arguments: dict[str, Any]) -> Any:
from ..sources import bgp
return await bgp.fetch_bgp_status(
runtime.fetcher, resource=arguments.get("resource", "")
)
async def _jet_cohort_snapshot(arguments: dict[str, Any]) -> Any:
from ..sources.jet_cohort import fetch_cohort_snapshot
return await fetch_cohort_snapshot(
runtime.fetcher,
cohort=arguments.get("cohort", "bizjet"),
region=arguments.get("region"),
)
async def _jet_activity_anomaly(arguments: dict[str, Any]) -> Any:
from ..analysis.jet_activity import fetch_cohort_activity
return await fetch_cohort_activity(
runtime.fetcher,
cohort=arguments.get("cohort", "bizjet"),
region=arguments.get("region"),
baseline_weeks=arguments.get("baseline_weeks", 4),
slot=arguments.get("slot"),
alarm_sigma=float(arguments.get("alarm_sigma", 5.0)),
min_learning_lead_hours=float(arguments.get("min_learning_lead_hours", 24)),
)
async def _jet_excess_origins(arguments: dict[str, Any]) -> Any:
from ..analysis.jet_activity import fetch_excess_origins
return await fetch_excess_origins(
runtime.fetcher,
cohort=arguments.get("cohort", "bizjet"),
region=arguments.get("region"),
start=arguments.get("start"),
slots=arguments.get("slots", 2),
baseline_weeks=arguments.get("baseline_weeks", 3),
ref_lat=arguments.get("ref_lat"),
ref_lon=arguments.get("ref_lon"),
cluster_radius_mi=float(arguments.get("cluster_radius_mi", 12)),
min_learning_lead_hours=float(arguments.get("min_learning_lead_hours", 24)),
)
HANDLERS = {
"intel_internet_outages": _internet_outages,
"intel_cable_health": _cable_health,
"intel_nav_warnings": _nav_warnings,
"intel_airport_delays": _airport_delays,
"intel_aviation_domestic": _aviation_domestic,
"intel_traffic_flow": _traffic_flow,
"intel_traffic_incidents": _traffic_incidents,
"intel_webcams": _webcams,
"intel_shipping_index": _shipping_index,
"intel_service_status": _service_status,
"intel_bgp_status": _bgp_status,
"intel_jet_cohort_snapshot": _jet_cohort_snapshot,
"intel_jet_activity_anomaly": _jet_activity_anomaly,
"intel_jet_excess_origins": _jet_excess_origins,
}