Australian Economic Data (ABS, RBA & APRA)

io.github.AnthonyPuggsPublished by GitHub account AnthonyPuggsv1.15.0Updated Oct 30, 2026

Australian economic data from the ABS, RBA, and APRA: CPI, GDP, cash rate, labour, and more.

VerifiedStreamable HTTPWeb executableFinanceData & Analytics

Overview

AI-generated overview

Read-only MCP server giving assistants structured access to official Australian economic data from the ABS, RBA and APRA, with no API key.

What you can do
  • Discover datasets and concepts: search curated ABS/RBA/APRA catalogues, list catalogue entries, list analyst-friendly economic concepts, and describe datasets.
  • Retrieve series: fetch curated economic series by concept with flexible date bounds, plus a small transparent derived-series layer such as real rates and yield-curve slope.
  • Query source-native data: pull ABS SDMX data and dataset structures, RBA statistical tables, and curated APRA XLSX publications.
  • Get quick views: latest observations, highest or lowest observations, and release calendar events.
  • All sources return one metadata, series and observations shape with provenance stamps.
When to use it
Useful when an assistant needs current or historical Australian macro and financial figures — CPI, GDP, unemployment, cash rate, credit, yields, exchange rates or prudential statistics — and should cite traceable official sources instead of web search.
Requirements
Either the hosted Streamable HTTP endpoint (no install, no key) or a local process via uvx from the PyPI package ausecon-mcp-server, which needs Python and uv. No account, API key, environment variables or headers are required. Network access to the ABS, RBA and APRA sources is needed.
Before you install
All 14 tools are read-only, so nothing is written or changed. Data is fetched from third-party government sources and cached for up to an hour; if a source is down after the cache expires, stale data is returned flagged as stale. The hosted instance may take a few seconds to wake on first request. The optional evaluation harness makes paid API calls.

Installation

In SourceWeft

  1. Open Australian Economic Data (ABS, RBA & APRA) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.AnthonyPuggs%2Fausecon-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "australian-economic-data-abs-rba-apra": {
      "type": "http",
      "url": "https://mcp.auseconmcp.com/mcp"
    }
  }
}

README

[ausecon — Australian economic & financial data MCP server]

[CI] [Integration] [PyPI] [Python] [Transport] [License]

[ausecon-mcp-server MCP server]

ausecon is a Model Context Protocol server that gives an AI assistant structured access to Australia’s official economic and financial data, straight from the ABS, RBA, and APRA.

Open source, free, and no API key. Every series comes back fresh & fully source-traceable, and all three sources share one response shape.

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.

14
read-only tools		83
economic concepts		16
derived indicators		8
prompt templates		3
data sources

What you get

Fresh & source-traceable
Every value is fetched from the source, cached for up to an hour, and stamped with its provenance (retrieved_at, source, server_version). If a source is down after the cache expires, the old copy is returned flagged stale and never served silently.
Three sources, one shape
ABS, RBA and APRA all return the same metadata · series · observations structure, so anything written against one source works for the other two.
Transparent derived series
Formula-based indicators like real_cash_rate, with the formula and its input series returned alongside the numbers.
Source-native control
Drop down to get_abs_data, get_rba_table or get_apra_data when you need a specific dataflow, table, or series ID.
Convenience tools
Latest observations, top movers, and the release calendar, each in a single call.
Works with your client
Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Codex or Smithery. stdio locally, Streamable HTTP when hosted.

Data sources

SourceCoverage
ABS  ·  Australian Bureau of StatisticsNational accounts, prices, labour force, population
RBA  ·  Reserve Bank of AustraliaCash rate, monetary & financial aggregates, exchange rates
APRA  ·  Aust. Prudential Regulation AuthorityADI & insurer statistics, with release-cadence estimates

Try it instantly (no install)

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

text
https://mcp.auseconmcp.com/mcp

Point any MCP client that supports remote servers at that URL. In Claude Code:

bash
claude mcp add --transport http ausecon https://mcp.auseconmcp.com/mcp

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:

bash
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 Code
bash
claude mcp add --transport stdio ausecon -- uvx ausecon-mcp-server
Codex
bash
codex mcp add ausecon -- uvx ausecon-mcp-server
Claude Desktop

Add to your claude_desktop_config.json:

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

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

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

Or paste this one-click link into your browser:

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

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

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

[Install in VS Code]

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

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:

python
list_economic_concepts(query="cash rate")
get_economic_series(    concept="cash_rate_target",    start="2020-01-01",)

Derived indicators have their own tool:

python
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+.

bash
uv sync --python 3.12uv run pytestuv 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:

bash
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.

auseconmcp.com  ·  Issues  ·  MIT Licence

Source: README.md at commit 46865a9

Tools

14

search_datasets

Search Datasets

Search curated ABS, RBA, and APRA economic datasets.

Parametersqueryrequiredsource

list_catalogue

List Catalogue

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

Parameterstagsourcecategoryinclude_ceasedinclude_discontinued

list_economic_concepts

List Economic Concepts

List analyst-friendly semantic economic concepts accepted by get_economic_series.

Parametersquerysourcecategory

get_abs_dataset_structure

Get ABS Dataset Structure

Get ABS SDMX dataset dimensions and codelists.

Parametersdataflow_idrequired

get_abs_data

Get ABS Data

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

Parameterskeylast_nend_perioddataflow_idrequiredstart_periodupdated_afterinclude_observation_dimensions

list_rba_tables

List RBA Tables

Deprecated compatibility alias. Prefer list_catalogue(source="rba").

Parameterscategoryinclude_discontinued

get_rba_table

Get RBA Table

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

Parameterslast_nend_datetable_idrequiredseries_idsstart_dateinclude_observation_dimensions

get_apra_data

Get APRA Data

Expert/source-native APRA public XLSX publication retrieval. Only curated official APRA publication IDs are accepted; arbitrary URLs are not.

Parameterslast_nend_datetable_idseries_idsstart_datepublication_idrequiredinclude_observation_dimensions

get_economic_series

Get Economic Series

Preferred analyst-facing retrieval tool for curated ABS/RBA economic concepts. Use list_economic_concepts for discovery. Date bounds accept YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD and are normalised to the resolved source.

Parametersendstartlast_nconceptrequiredvariantfrequencygeographyinclude_observation_dimensions

get_derived_series

Get Derived Series

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.

Parametersendstartlast_nconceptrequired

get_latest_observations

Get Latest Observations

Source-aware convenience wrapper for the latest observations. For a single curated indicator prefer get_economic_series(concept=...), which resolves one series; pass series_ids=[...] to narrow a broad dataset instead of returning every series it contains.

Parameterskeycountsourcerequiredtable_ididentifierrequiredseries_ids

get_top_observations

Get Top Observations

Source-aware convenience wrapper for highest or lowest numeric observations. For a single curated indicator prefer get_economic_series(concept=...), which resolves one series; pass series_ids=[...] to narrow a broad dataset instead of returning every series it contains.

Parametersnkeysourcerequiredend_datetable_iddirectionend_periodidentifierrequiredseries_idsstart_datestart_period

describe_dataset

Describe Dataset

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

Parameterssourcerequiredtable_ididentifierrequiredinclude_structure

list_release_events

List Release Events

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

Parameterslimitquerysourceend_datestart_date

Version history

3
  1. v1.15.0LatestOct 30, 2026
  2. v1.14.6Oct 29, 2026
  3. v1.14.5Sep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts