How clean the grid is right now (gCO2/kWh) and when the next cleanest window is — so an agent can schedule a workload or EV charge for the lowest-carbon moment.
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/carbon-intensity"
# MCP (keyless) — point any client at https://dynamicfeed.ai/mcp, then call:
carbon_intensity()
{ "intensity_gco2_kwh": 142, "index": "moderate",
"cleanest_upcoming": {"start": "2026-06-04T02:00Z", "gco2_kwh": 61} }
Carbon intensity changes by the half-hour with the fuel mix — a model can't know it. This serves live intensity plus a 24h forecast surfacing the cleanest window, so 'run this when the grid is greenest' becomes a real decision.
Great Britain (National Energy System Operator), CC-BY. The forward forecast surfaces the cleanest upcoming half-hour.
Yes — CC-BY 4.0 with attribution.