Skip to main content
Glama
aemo-mcp

aemo-mcp

aemo-mcp

mcp-name: io.ausdata/aemo-mcp

PyPI Python License Tests CodeQL Glama MCP server quality

Ask Claude about Australia's electricity market and get real, current numbers — 5-minute spot prices, regional demand, generation by fuel, interconnector flows, rooftop solar — not "I don't have access to that data." This MCP server gives Claude (and other MCP clients like Cursor) live access to the Australian Energy Market Operator (AEMO) NEMWEB feeds, with curated mappings for the most-asked indicators.

Hosted access? For cross-source queries, webhooks, an always-on REST API, and a uniform response envelope across all 9 sources, see ausdata.io — free tier available (500 calls/mo, no card).

Companion to abs-mcp (ABS macro stats), rba-mcp (RBA interest + FX rates), ato-mcp (ATO tax + ACNC charity), apra-mcp (banking + superannuation), aihw-mcp (health & welfare), asic-mcp (companies + financial advisers), and au-weather-mcp (Australian weather) — together they cover the most-asked Australian official data.

What you can ask

Once installed, your LLM can answer questions like:

Question

What the tool does

What's the current NSW spot price?

latest("dispatch_price", filters={"region":"NSW1"})

Did SA hit negative pricing in the last 24 hours?

get_data("dispatch_price", filters={"region":"SA1"}, start_period=…) and filter value < 0

Generation by fuel type right now in QLD

latest("generation_scada", filters={"region":"QLD1"}), aggregated by fuel

Weekly average dispatch price for VIC, last 4 weeks

get_data("dispatch_price", filters={"region":"VIC1"}, start_period=…)

Rooftop PV forecast for tomorrow

get_data("rooftop_pv", filters={"section":"forecast"}, start_period="<tomorrow>")

What's the current flow across Heywood (VIC ↔ SA)?

latest("interconnector_flows", filters={"interconnector":"V-SA"})

Total NEM demand right now

latest("dispatch_region")

Every answer comes with the interval timestamp (AEMO market time, UTC+10), units (MW, $/MWh), and a link back to the NEMWEB source. The MCP wraps NEMWEB's CSV/ZIP feeds and exposes them through 5 plain-English tools.

Related MCP server: Luminus

Install

# After publish:
uvx --upgrade aemo-mcp

# Local dev:
uv pip install -e .

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "aemo": {
      "command": "uvx",
      "args": ["--upgrade", "aemo-mcp"]
    }
  }
}

Why --upgrade? uvx aemo-mcp (without the flag) uses whatever wheel is cached and never adopts new PyPI releases on its own. --upgrade makes uvx check PyPI on each launch and pull a newer release if one exists. Recommended for everyone except offline-first / pinned-version workflows. To verify which version is currently serving you, look at the server_version field on any DataResponse.

If you also have rba-mcp / abs-mcp installed, all servers run side-by-side. Claude disambiguates with the server prefix (aemo:get_data, rba:get_data, abs:get_data).

For local dev (pre-PyPI):

{
  "mcpServers": {
    "aemo": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/aemo-mcp", "aemo-mcp"]
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json (or workspace .cursor/mcp.json):

{
  "mcpServers": {
    "aemo": {
      "command": "uvx",
      "args": ["--upgrade", "aemo-mcp"]
    }
  }
}

Tools

Tool

What it does

search_datasets(query, limit=10)

Fuzzy-search the 7 curated NEM datasets by name, topic, or region.

describe_dataset(dataset_id)

Schema, filters, source URL, cadence, and example queries for one dataset.

get_data(dataset_id, filters, start_period, end_period, format)

Query data. Records / series / csv format.

latest(dataset_id, filters)

Most recent 5-min or 30-min interval for time-series feeds.

list_curated()

The 7 curated dataset IDs.

Curated datasets

The 7 datasets cover ~95% of typical NEM analytic queries:

dataset_id

Cadence

Source

Use case

dispatch_price

5 min

DispatchIS / DISPATCHPRICE

Current spot price per region; negative-pricing detection

dispatch_region

5 min

DispatchIS / DISPATCHREGIONSUM

Demand + scheduled + semi-scheduled gen + net interchange

interconnector_flows

5 min

DispatchIS / DISPATCHINTERCONNECTORRES

MW flow + losses across NEM interconnectors

generation_scada

5 min

Dispatch_SCADA

DUID-level MW (every unit), aggregable by fuel

rooftop_pv

30 min

ROOFTOP_PV/ACTUAL + FORECAST

Regional rooftop solar (actual + forecast)

predispatch_30min

30 min

PredispatchIS

30-min forecast, ~40h horizon

daily_summary

Daily

Daily_Reports

Yesterday's full data in one drop

Use list_curated() to enumerate, describe_dataset(dataset_id) to learn the filters available on each.

Regions

NSW1 (New South Wales), QLD1 (Queensland), SA1 (South Australia), TAS1 (Tasmania), VIC1 (Victoria). Western Australia (WEM) and the Northern Territory are not on the NEM and are out of scope.

Trust contract

Every DataResponse carries:

  • source = "Australian Energy Market Operator"

  • attribution — AEMO Copyright Permissions verbatim attribution string

  • source_url — the NEMWEB folder the data came from

  • retrieved_at — UTC timestamp of the fetch

  • interval_start / interval_end — period covered

  • stale — True if the latest interval is older than 2× the feed cadence

  • server_version — the wheel that served the call

Licence + attribution

This package is MIT-licensed (see LICENSE).

The AEMO data it fetches is published under AEMO's Copyright Permissions policy: AEMO grants general permission to use AEMO Material for any purpose (commercial included) on the sole condition of accurate attribution of the relevant material and AEMO as its author. See https://aemo.com.au/privacy-and-legal-notices/copyright-permissions.

End-users redistributing data fetched via this server must credit AEMO. The canonical attribution string is on every DataResponse.attribution.

Worked examples

"What's the current NSW spot price?"

latest(dataset_id="dispatch_price", filters={"region": "NSW1"})

→ {"records": [{"period": "2026-05-14T10:05:00+10:00", "value": 87.5, "dimensions": {"region": "NSW1", "metric": "rrp"}, "unit": "$/MWh"}], ...}

"NSW spot price for the last 24 hours"

get_data(dataset_id="dispatch_price", filters={"region": "NSW1"},
         start_period="2026-05-13", end_period="2026-05-14")

"Did SA hit negative pricing in the last 24 hours?"

get_data(dataset_id="dispatch_price", filters={"region": "SA1"},
         start_period="<24h ago>")

Then the LLM filters value < 0 client-side.

"Generation by fuel type right now in QLD"

latest(dataset_id="generation_scada", filters={"region": "QLD1"})

→ DUID-level rows with fuel attribution; the LLM aggregates by fuel.

How it works

  • Live-fetch only. No NEMWEB archives in the wheel. Every request goes through the cache.

  • Cache TTLs tuned per cadence. 60s for 5-min feeds, 5min for 30-min feeds, 1h forecasts, 24h daily archive. Timestamped historical files are immutable in NEMWEB and cache effectively forever.

  • In-flight request deduplication. Concurrent callers for the same URL share one HTTP request. Critical at 5-min cadence with many users.

  • Latest-file detection is purely lexicographic on the NEMWEB directory listing — AEMO embeds the interval timestamp in every filename (PUBLIC_DISPATCHIS_YYYYMMDDHHmm_<seq>.zip), so max() is enough.

  • Multi-section CSV parser handles AEMO's I,/D, row format where a single ZIP holds several tables (DISPATCHPRICE, DISPATCHREGIONSUM, DISPATCHINTERCONNECTORRES, etc.).

Development

git clone https://github.com/Bigred97/aemo-mcp
cd aemo-mcp
uv sync --extra dev
uv pip install -e .
uv run pytest -q

Run live tests (hit NEMWEB):

uv run pytest -q -m live

Zero-flake validation:

for i in $(seq 1 10); do uv run pytest -q || break; done

Sister MCPs (Australian Public Data portfolio)

Want all 9 sources behind one REST API? The hosted gateway at ausdata.io adds cross-source joins, full history, webhooks, and HMAC-signed responses on top of these MCPs — free tier (500 calls/mo, no card).

  • abs-mcp — Australian Bureau of Statistics (CPI, unemployment, ERP, building approvals)

  • rba-mcp — Reserve Bank of Australia (cash rate, lending stats, exchange rates)

  • ato-mcp — Australian Taxation Office (tax stats, ACNC charities)

  • apra-mcp — Australian Prudential Regulation Authority (banking, insurance, super)

  • aihw-mcp — Australian Institute of Health and Welfare

  • asic-mcp — Australian Securities and Investments Commission (company registers)

  • aemo-mcp — this one. Australian Energy Market Operator (NEM dispatch, spot prices, generation).

  • au-weather-mcp — Open-Meteo (Bureau of Meteorology aggregator)

  • wgea-mcp — Workplace Gender Equality Agency

  • aus-identity — Postcode / state / ABN normalisation helper used by all sisters

Author

Built by Harry Vass. Issues + PRs welcome at github.com/Bigred97/aemo-mcp.

Available Tools

5 tools
describe_datasetA

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.

Inputs: dataset_id (required). Returns: Full dataset metadata returned by describe_dataset().

get_dataA

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.

Inputs: dataset_id (required), filters, start_period, end_period, +1 more. Returns: Uniform response shape across all sibling MCPs.

latestA

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).

Inputs: dataset_id (required), filters. Returns: Uniform response shape across all sibling MCPs.

list_curatedA

List the 7 curated AEMO NEM dataset IDs.

These cover ~95% of typical NEM analytic queries: spot prices, regional demand and generation, interconnector flows, unit-level SCADA, rooftop PV (actual + forecast), 30-min predispatch forecasts, and daily-settled summaries.

Example: ids = list_curated() # → ['daily_summary', 'dispatch_price', 'dispatch_region', # 'generation_scada', 'interconnector_flows', # 'predispatch_30min', 'rooftop_pv']

Returns: Sorted list of dataset IDs. Always 7 entries today.

Inputs: no named parameters. Returns: result

search_datasetsA

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.

Inputs: query (required), limit. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a distinct purpose: describe_dataset provides schema details, get_data retrieves arbitrary time ranges, latest returns the most recent interval, list_curated enumerates datasets, and search_datasets performs fuzzy search. Even though get_data and latest both retrieve data, their use cases are clearly separated by examples and descriptions.

    Naming Consistency4/5

    Tool names are in snake_case and follow a verb_noun pattern for four tools (describe_dataset, get_data, list_curated, search_datasets). The exception is 'latest', which is an adjective rather than a verb, but it is still concise and commonly understood in data contexts.

    Tool Count5/5

    With 5 tools, the server covers the essential operations for interacting with AEMO NEM datasets: schema discovery, data retrieval, latest value shortcut, dataset listing, and fuzzy search. This scope is neither too sparse nor too heavy for the domain.

    Completeness5/5

    The toolset provides a complete workflow for read-only access to AEMO NEM data: discover available datasets (list_curated, search_datasets), inspect schema (describe_dataset), and retrieve data (get_data, latest). There are no obvious missing operations like update or delete, which are not expected in this read-only context.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server for real-time electricity prices, carbon intensity, and energy analytics across 41+ zones in Europe, Great Britain, the United States, and Australia. Query live prices, compare zones, check gas storage levels, get green scores, find optimal charging windows, and access advanced analytics. Free Basic tier requires no API key. Install via npx gridpulse-mcp or connect directly via Streamab
      -
    • A
      license
      B
      quality
      B
      maintenance
      Provides real-time European and GB electricity grid data via MCP, including generation, prices, carbon intensity, and grid infrastructure.
      44
      70 npm
      7
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server for querying ENTSO-E Transparency Platform data including actual load, generation per type, cross-border flows, and installed capacity.
      84 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      MCP server for Swiss electricity data from three official sources — production mix, consumption forecast, storage-lake fill, consumer price index, tariffs per municipality, and dataset discovery. Zero authentication.
      12
      52 PyPI
      MIT