Which subway, bus and rail lines are running, delayed or down right now — across hundreds of transit systems worldwide, normalized into one feed.
Keyless over MCP, or one REST call with a free key. Every datapoint is provenance-stamped and citeable.
# REST (free key)
curl -H "X-API-Key: $KEY" "https://dynamicfeed.ai/transit?only_issues=true&limit=8"
# MCP (keyless) — point any client at https://dynamicfeed.ai/mcp, then call:
transit_status(only_issues=true)
{ "system": "MTA Subway", "line": "A", "status": "Delays", "operational": false,
"observed_at": "2026-06-04T13:00:00Z" }
A model can't know if the L train is down right now. This normalizes hundreds of agencies' GTFS-Realtime feeds into one live status feed, so a travel or logistics agent can route around disruptions as they happen.
Hundreds worldwide via GTFS-Realtime — major metro, bus and rail agencies. Filter to disruptions with only_issues.
Real-time agency feeds, polled continuously; every row is time-stamped.
Over MCP, yes; the REST endpoint uses a free key.