Aussie Data MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUSSIE_DATA_CACHE_DIR | No | Override the cache directory. Responses are cached for 6 hours by default (memory + temp dir). | |
| AUSSIE_DATA_CACHE_TTL_HOURS | No | Override the cache time-to-live in hours. Responses are cached for 6 hours by default (memory + temp dir). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_cpiA | Australian inflation from the ABS monthly Consumer Price Index, by item and capital city. Use measure 'annual_change' for 'what is inflation' (year-on-year %), 'monthly_change' for month-on-month %, 'index' for price levels. The RBA's preferred underlying measure is trimmed_mean. For rent inflation use item 'rents'. Other items can be passed as an ABS CPI index code (find codes with abs_describe_dataflow on 'CPI'). |
| get_labour_forceB | ABS Labour Force survey, monthly: unemployment rate, participation, employment and more, for Australia or any state/territory. Rates are in %, counts are in thousands of people. Seasonally adjusted by default, which is what news reports quote. |
| get_cash_rateA | The Reserve Bank of Australia cash rate target, monthly average (% per year). Use for 'what's the cash rate', rate hikes/cuts over time, or to line up rates against CPI, rents or jobs. |
| get_lending_ratesB | RBA indicator lending rates (advertised, % per year), monthly: home loans for owner-occupiers and investors (variable standard, variable discounted, 3-year fixed), small business, credit cards and personal loans. |
| get_exchange_ratesA | Australian dollar exchange rates from the RBA (units of foreign currency per A$1), plus the trade-weighted index (TWI). Daily data from 2023; monthly (last value of each month) by default. |
| rba_seriesA | Fallback for RBA data the focused tools don't cover (e.g. f6 actual lending rates, f2 bond yields, g1 inflation expectations, d1 credit growth). Call with just |
| get_commute_pulseA | How Sydney is commuting since COVID, from TfNSW Opal tap data (Commute Pulse). 'friday_gap' = Friday evening tap-ons as a share of Tue-Thu, monthly since 2020 - the core return-to-office measure (1.0 = no gap). Also: 'monday_gap', 'evening_volume' (Tue-Thu evening tap-ons per day), 'baseline' (pre-COVID ratios), 'cbd_hourly' (CBD tap-ons by hour, pre-COVID vs last 12 months), 'suburban_morning' (Friday vs midweek 7-9am outside the centres). |
| abs_search_dataflowsA | Search the ABS Data API catalogue (1,000+ datasets) by keyword. Use when CPI and Labour Force don't cover the question - e.g. wages, building approvals, population, retail trade, GDP. Returns dataflow ids for abs_describe_dataflow. |
| abs_describe_dataflowA | List an ABS dataflow's dimensions (in key order) and their codes, so you can build an SDMX key for abs_get_data. Use |
| abs_get_dataB | Fetch any ABS dataflow with an SDMX key from abs_describe_dataflow. Keep keys narrow - an empty key on a big dataflow returns thousands of series. Use last_n to just get the latest values. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
The focused tools (get_cpi, get_labour_force, get_cash_rate, get_lending_rates, get_exchange_rates, get_commute_pulse) each target a distinct dataset, and the three abs_* tools form a clear search/describe/fetch pipeline. The only real overlap is the intentional fallback pattern: rba_series can reproduce get_cash_rate data, and abs_get_data can cover CPI, so an agent could occasionally pick the generic path instead of the shortcut.
Six tools follow a clean get_<subject> pattern, and the ABS tools use a readable <source>_<verb>_<object> convention (abs_search_dataflows, abs_describe_dataflow, abs_get_data). rba_series breaks the pattern by having no verb, but the naming is otherwise predictable and family-grouped rather than chaotic.
At 10 tools the set is well-scoped: a handful of focused shortcuts plus a small generic ABS/RBA escape hatch. Every tool earns its place and none feels redundant or bolted on.
Core Australian macro questions (inflation, jobs, cash rate, lending, FX, commuting) have dedicated tools, and abs_search_dataflow/abs_describe_dataflow/abs_get_data plus rba_series close the long tail of ABS and RBA datasets. This gives full query coverage with no obvious dead ends.