Skip to main content
Glama
ausecon MCP Server for ABS | RBA | APRA data

ausecon MCP Server for ABS | RBA | APRA data

CI Integration PyPI Python Transport License

ausecon-mcp-server MCP server

Documentation  ·  Getting started  ·  Tool reference  ·  Changelog


Why this exists

Australian economic data is authoritative but awkward to reach. It sits behind three different portals with three different formats, and each one expects you to already know its identifiers. ausecon puts that data in front of an AI assistant with nothing to sign up for and no key to manage. Every series is fetched from the source, cached for up to an hour, stamped with when it was actually retrieved, and returned in the same metadata · series · observations shape whether it came from the ABS, the RBA, or APRA. Ask for "the cash rate" or "quarterly real GDP growth" and the assistant works out the right call.

Related MCP server: Banco Central do Brasil (BCB) — SGS MCP

What you get

Data sources

Source

Coverage

ABS  ·  Australian Bureau of Statistics

National accounts, prices, labour force, population

RBA  ·  Reserve Bank of Australia

Cash rate, monetary & financial aggregates, exchange rates

APRA  ·  Aust. Prudential Regulation Authority

ADI & insurer statistics, with release-cadence estimates

All three agencies publish this data under CC BY 4.0. If you republish figures, credit the agency, not ausecon. See Data Sources and Licensing for the attribution wording and the licences' exceptions.

Try it instantly (no install)

A hosted read-only, no-API-key instance speaks MCP over Streamable HTTP at:

https://mcp.auseconmcp.com/mcp

Point any MCP client that supports remote servers at that URL, with no authentication:

  • Claude (web, desktop and mobile): add it as a custom connector. Data results appear as interactive charts.

  • ChatGPT: add it as a custom MCP server on the web. Availability depends on your plan.

  • Gemini: add it as a custom app in the Gemini web app. Availability depends on your account and region.

In Claude Code, Codex CLI or Gemini CLI:

claude mcp add --transport http ausecon https://mcp.auseconmcp.com/mcp
codex mcp add ausecon --url https://mcp.auseconmcp.com/mcp
gemini mcp add --transport http ausecon https://mcp.auseconmcp.com/mcp

See Client Setup for more clients.

The hosted instance may take a few seconds to wake on the first request. The previous https://ausecon-mcp-server.onrender.com/mcp URL continues to work and points at the same instance.

Install

The package lives on PyPI and is meant to be launched on demand by your MCP client through uvx:

uvx ausecon-mcp-server

The server speaks MCP over standard input and output. Run on its own it just sits there waiting for a client, so there is nothing to see until one connects.

Connect your client

claude mcp add --transport stdio ausecon -- uvx ausecon-mcp-server
codex mcp add ausecon -- uvx ausecon-mcp-server

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "ausecon": {
      "command": "uvx",
      "args": ["ausecon-mcp-server"]
    }
  }
}

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

{
  "mcpServers": {
    "ausecon": {
      "command": "uvx",
      "args": ["ausecon-mcp-server"]
    }
  }
}

Or paste this one-click link into your browser:

cursor://anysphere.cursor-deeplink/mcp/install?name=ausecon&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJhdXNlY29uLW1jcC1zZXJ2ZXIiXX0=

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "ausecon": {
      "command": "uvx",
      "args": ["ausecon-mcp-server"],
      "env": {}
    }
  }
}

Install in VS Code

Or add to .vscode/mcp.json (workspace) or your user mcp.json:

{
  "servers": {
    "ausecon": {
      "type": "stdio",
      "command": "uvx",
      "args": ["ausecon-mcp-server"]
    }
  }
}

To host it yourself, smithery.yaml and Dockerfile.smithery ship a Streamable HTTP deployment at /mcp. See the Smithery guide.

A quick taste

Find the concept you want, then ask for the series:

list_economic_concepts(query="cash rate")

get_economic_series(
    concept="cash_rate_target",
    start="2020-01-01",
)

Derived indicators have their own tool:

get_derived_series(concept="real_cash_rate", last_n=12)

Connected to an AI agent, you can skip the syntax entirely. Ask for "quarterly real GDP growth" and it works out which tools to call.

Develop locally

Python 3.12 is recommended; the CI matrix supports 3.10+.

uv sync --python 3.12
uv run pytest
uv run ruff check src tests scripts

The repo also ships a manual benchmark (evals/) that measures the server's impact on model answers across 52 Australian-economics questions, comparing a bare model, web search, and the ausecon tools. Ground-truth resolution is free to check:

uv run --group evals python -m evals.run_eval --dry-run

A full run makes paid API calls, so read the evaluation harness guide before starting one.

Disclaimer

ausecon is an independent open-source project maintained by an individual. It is not affiliated with, endorsed by or operated by the Australian Government, the Australian Bureau of Statistics, the Reserve Bank of Australia or the Australian Prudential Regulation Authority. Their names are used only to identify where the data comes from.

The data belongs to those agencies and is published under their own licences; see Data Sources and Licensing. ausecon passes it through as published, with no warranty. Check important figures against the original source, which every response links to in metadata.retrieval_url.


auseconmcp.com  ·  Issues  ·  MIT Licence

Available Tools

14 tools
describe_datasetDescribe DatasetB
Read-onlyIdempotent
Inspect

Describe a source-native ABS, RBA, or APRA dataset without hiding native IDs.

Inputs: source (required), identifier (required), table_id, include_structure. Returns: Plain-English dataset description preserving source-native identifiers.

get_abs_dataGet ABS DataA
Read-onlyIdempotent
Inspect

Expert/source-native ABS SDMX retrieval in a normalised response shape.

Curated indicators from ABS dataflows, such as CPI inflation, the unemployment rate and GDP growth, are also available through get_economic_series, which can return several in one result and one chart.

In MCP Apps hosts (claude.ai, Claude Desktop) a result with up to eight series is already shown to the user as an interactive chart with a data table, so another chart of the same data would duplicate it.

Inputs: dataflow_id (required), key, last_n, end_period, +3 more. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

get_abs_dataset_structureGet ABS Dataset StructureA
Read-onlyIdempotent
Inspect

Get ABS SDMX dataset dimensions and codelists.

Inputs: dataflow_id (required). Returns: ABS SDMX dataset structure with dimensions and codelists.

get_apra_dataGet APRA DataA
Read-onlyIdempotent
Inspect

Expert/source-native APRA public XLSX publication retrieval.

Only curated official APRA publication IDs are accepted; arbitrary URLs are not.

Curated indicators from APRA publications, such as bank capital ratios and housing loan exposures, are also available through get_economic_series, which can return several in one result and one chart.

In MCP Apps hosts (claude.ai, Claude Desktop) a result with up to eight series is already shown to the user as an interactive chart with a data table, so another chart of the same data would duplicate it.

Inputs: publication_id (required), last_n, end_date, table_id, +3 more. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

get_derived_seriesGet Derived SeriesA
Read-onlyIdempotent
Inspect

Read-only retrieval for the narrow transparent derived series layer.

Date bounds accept YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD and are normalised to the derived series frequency.

In MCP Apps hosts (claude.ai, Claude Desktop) a result with up to eight series is already shown to the user as an interactive chart with a data table, so another chart of the same data would duplicate it.

Inputs: concept (required), end, start, last_n. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

get_economic_seriesGet Economic SeriesA
Read-onlyIdempotent
Inspect

Main analyst-facing retrieval tool for curated ABS, RBA and APRA concepts.

list_economic_concepts lists the accepted concepts. Date bounds accept YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD and are normalised to the resolved source.

A list of up to eight concepts returns them together in one result, which MCP Apps hosts display as one chart.

In MCP Apps hosts (claude.ai, Claude Desktop) a result with up to eight series is already shown to the user as an interactive chart with a data table, so another chart of the same data would duplicate it.

Inputs: concept (required), end, start, last_n, +4 more. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

get_latest_observationsGet Latest ObservationsA
Read-onlyIdempotent
Inspect

Source-aware convenience wrapper for the latest observations.

Without series_ids, a broad dataset returns every series it contains; series_ids narrows it. get_economic_series(concept=...) returns a single curated indicator as one series.

Inputs: source (required), identifier (required), key, count, +2 more. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

get_rba_tableGet RBA TableA
Read-onlyIdempotent
Inspect

Expert/source-native RBA statistical table retrieval in a normalised response shape.

Curated indicators from RBA tables, such as the cash rate target, mortgage rates, bond yields and credit growth, are also available through get_economic_series, which can return several in one result and one chart.

In MCP Apps hosts (claude.ai, Claude Desktop) a result with up to eight series is already shown to the user as an interactive chart with a data table, so another chart of the same data would duplicate it.

Inputs: table_id (required), last_n, end_date, series_ids, +2 more. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

get_top_observationsGet Top ObservationsA
Read-onlyIdempotent
Inspect

Source-aware convenience wrapper for highest or lowest numeric observations.

Without series_ids, a broad dataset returns every series it contains; series_ids narrows it. get_economic_series(concept=...) returns a single curated indicator as one series.

Inputs: source (required), identifier (required), n, key, +7 more. Returns: Normalised retrieval response returned by ABS, RBA, APRA, semantic, and derived…

list_catalogueList CatalogueA
Read-onlyIdempotent
Inspect

List curated ABS, RBA, and APRA catalogue entries, optionally filtered by source, category, or tag. Unranked complement to search_datasets.

Inputs: tag, source, category, include_ceased, +1 more. Returns: Curated ABS, RBA, and APRA catalogue entries.

list_economic_conceptsList Economic ConceptsA
Read-onlyIdempotent
Inspect

List analyst-friendly semantic economic concepts accepted by get_economic_series.

Inputs: query, source, category. Returns: Curated semantic economic concepts.

list_rba_tablesList RBA TablesA
Read-onlyIdempotent
Inspect

Deprecated compatibility alias. list_catalogue(source="rba") returns the same curated RBA tables.

Inputs: category, include_discontinued. Returns: Curated RBA table catalogue entries.

list_release_eventsList Release EventsC
Read-onlyIdempotent
Inspect

List source-aware release calendar or release-pulse events.

Inputs: limit, query, source, end_date, +1 more. Returns: ABS, RBA, and APRA release calendar events.

search_datasetsSearch DatasetsB
Read-onlyIdempotent
Inspect

Search curated ABS, RBA, and APRA economic datasets.

Inputs: query (required), source. Returns: Ranked ABS, RBA, and APRA catalogue search results.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 14 tools

    Disambiguation4/5

    The set has a clear layered design (curated get_economic_series vs. source-native get_abs_data/get_rba_table/get_apra_data), and descriptions explicitly cross-reference each other to steer selection. Residual overlap remains between search_datasets and list_catalogue, between describe_dataset and get_abs_dataset_structure, and between the latest/top convenience wrappers and the primary retrieval tools, plus list_rba_tables is a deprecated duplicate of list_catalogue.

    Naming Consistency5/5

    All tools use snake_case with a predictable verb_noun shape (get_*, list_*, search_*, describe_*). Pluralization and subject ordering are consistent across the whole set, and source prefixes (abs/rba/apra) are applied systematically.

    Tool Count4/5

    Fourteen tools is a reasonable size for a three-source (ABS/RBA/APRA) economic data server with both expert and analyst-facing surfaces. One slot is wasted on the deprecated list_rba_tables alias, which the description itself says to avoid.

    Completeness4/5

    Read-only coverage is broad: discovery (search_datasets, list_catalogue, list_economic_concepts), structure/description, native retrieval for all three sources, curated retrieval, derived series, latest/top convenience wrappers, and a release calendar. Gaps are minor, such as structure introspection only being source-native for ABS and no explicit cross-source comparison operation.

    Maintenance

    ActivityMaintained
    ResponsivenessUsually handled

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      A
      maintenance
      MCP server for the Brazilian Central Bank (BCB/SGS) public API, providing access to 18,000+ economic time series. Includes a curated catalog of 150+ popular indicators organized in 12 categories: interest rates (Selic), inflation (IPCA, IGP-M, INPC), exchange rates (USD, EUR), GDP, employment, credit, fiscal data, and more. Supports historical queries with date filters, latest values, metadata loo
      17
      640 npm
      11
      MIT
    • A
      license
      A
      quality
      F
      maintenance
      One-call Australian energy-market plumbing via AEMO — cited, structured responses for market data and analysis, not a data broker.
      5
      196 PyPI
      MIT