io.ausdata/aemo-mcp

Describe one NEM dataset — schema, filters, cadence, source URL. Examples: detail = await describe_dataset("dispatch_price") # → filters: [{key: "region", values: ["NSW1", "QLD1", ...]}] # → metrics: {rrp: "$/MWh"} # → cadence: "5 min" Returns: DatasetDetail with id, name, description, filters, units, source URL, and example invocation strings.

Query an AEMO NEM dataset and return observations. Examples: # Latest NSW dispatch price (preferred over latest() if you want # a window) resp = await get_data("dispatch_price", filters={"region": "NSW1"}) # Whole-day NSW dispatch price for a specific day resp = await get_data( "dispatch_price", filters={"region": "NSW1"}, start_period="2026-05-13", end_period="2026-05-13" ) # Generation by fuel for QLD, current resp = await get_data("generation_scada", filters={"region": "QLD1"}) # All 6 interconnectors right now resp = await get_data("interconnector_flows") Returns: DataResponse with records, units, period bounds, NEMWEB source URL, and AEMO attribution.

Return the most recent interval(s) for a NEM dataset. For 5-min feeds (dispatch_price, dispatch_region, interconnector_flows, generation_scada): returns the most recent 5-minute interval, typically 1-2 minutes after the interval close. For 30-min feeds (rooftop_pv, predispatch_30min): the most recent half-hour. For daily feeds (daily_summary): yesterday's data. Examples: # Current NSW spot price resp = await latest("dispatch_price", filters={"region": "NSW1"}) # Current generation mix in QLD resp = await latest("generation_scada", filters={"region": "QLD1"}) # Current flow across Heywood resp = await latest("interconnector_flows", filters={"interconnector": "V-SA"}) Returns: DataResponse with one observation per filtered (dimension, metric) tuple at the most recent interval. `stale=True` flag indicates the most recent interval is older than 2× the feed cadence (NEMWEB delay).

List every curated AEMO NEM dataset ID. These cover the great majority of typical NEM analytic queries: spot prices, regional demand and generation, interconnector flows, unit-level SCADA, rooftop PV (actual + forecast), 30-min predispatch forecasts, dispatch constraints, FCAS ancillary-service prices, trading (settlement) prices, and daily-settled summaries. Call this tool to get the live list rather than assuming a fixed count — the registry grows over time as new curated datasets are added. Example: ids = list_curated() # → ['daily_summary', 'dispatch_constraints', 'dispatch_price', # 'dispatch_region', 'fcas_prices', 'generation_scada', # 'interconnector_flows', 'predispatch_30min', 'rooftop_pv', # 'trading_price'] Returns: Sorted list of dataset IDs. Do not hardcode the count in calling code — query this tool live, since the registry grows.

Fuzzy-search the 7 curated AEMO NEM datasets. Use this when you don't know the exact dataset_id. The 7 curated datasets cover ~95% of typical NEM analytic queries — spot prices, demand, generation, rooftop PV, interconnector flows, forecasts. Examples: # Find the dataset that publishes the spot price results = await search_datasets("spot price") # → [{id: 'dispatch_price', name: 'NEM Dispatch Price ...', ...}] # Discover what's available on rooftop solar results = await search_datasets("rooftop pv", limit=5) Returns: List of DatasetSummary (id, name, description, cadence), ranked by relevance. All v0 datasets are curated.