This MCP server provides Australian economic and financial data sourced from the ABS, RBA, and APRA. It covers datasets including CPI, GDP, the cash rate, labour, and more, exposed through MCP tools. The repository lists 14 tools and is categorized with topics spanning Australian data and economics.

🛠️ Key Features

Data coverage: Australian economic and financial datasets
Sources: ABS, RBA, APRA
Includes metrics such as CPI, GDP, cash rate, and labour
Tooling count: 14

🚀 Use Cases

Retrieve Australian macroeconomic indicators (e.g., CPI and GDP)
Access Reserve Bank–related data such as the cash rate
Work with labour-related economic datasets from supported providers

⚡ Developer Benefits

MCP integration for standardized tool access
Clear topic alignment for discovery: Australian Bureau of Statistics, Reserve Bank of Australia, and related economics/finance data

⚠️ Limitations

Supported sources are limited to ABS, RBA, and APRA (as stated)
Document excerpt provided does not describe specific tool names, schemas, or access methods beyond the stated categories

ausecon — Australian economic & financial data 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

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

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

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 3.12
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:

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}

query	string	required	Discovery query text.
source	any	optional	Optional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority.

source	any	optional	Optional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority.
category	any	optional	Optional curated catalogue or semantic concept category filter.
tag	any	optional	Optional curated catalogue tag filter.
include_ceased	boolean	optional	Whether to include ceased ABS catalogue entries.
include_discontinued	boolean	optional	Whether to include discontinued RBA catalogue entries.

query	any	optional	Optional query for filtering semantic economic concepts.
source	any	optional	Optional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority.
category	any	optional	Optional curated catalogue or semantic concept category filter.

dataflow_id	string	required	Non-empty dataset or table id.
key	string	optional	ABS SDMX key, or "all" for all series.
start_period	any	optional	Optional ABS period bound in YYYY, YYYY-QN, YYYY-MM, or YYYY-SN format.
end_period	any	optional	Optional ABS period bound in YYYY, YYYY-QN, YYYY-MM, or YYYY-SN format.
last_n	any	optional	Optional limit returning only the most recent N observations per series; metadata.truncated is true when older observations were dropped.
updated_after	any	optional	Optional ISO date or datetime accepted by the ABS updatedAfter API.
include_observation_dimensions	boolean	optional	Whether to repeat the full dimension dict on every observation. Off by default because the same dimensions already appear on each series descriptor and are encoded in series_id.

category	any	optional	Optional RBA catalogue category filter.
include_discontinued	boolean	optional	Whether to include discontinued RBA catalogue entries.

Australian Economic Data (ABS, RBA & APRA)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

search_datasets

list_catalogue

list_economic_concepts

get_abs_dataset_structure

get_abs_data

list_rba_tables

get_rba_table

get_apra_data

get_economic_series

get_derived_series

get_latest_observations

get_top_observations

describe_dataset

list_release_events

Why this exists

What you get

Fresh & source-traceable

Three sources, one shape

Transparent derived series

Source-native control

Convenience tools

Works with your client

Data sources

Try it instantly (no install)

Install

Connect your client

A quick taste

Develop locally

Install

Related servers

table_id	string	required	Non-empty dataset or table id.
series_ids	any	optional	Optional list of non-empty source-native series IDs to keep after download.
start_date	any	optional	Optional ISO date bound in YYYY-MM-DD format.
end_date	any	optional	Optional ISO date bound in YYYY-MM-DD format.
last_n	any	optional	Optional limit returning only the most recent N observations per series; metadata.truncated is true when older observations were dropped.
include_observation_dimensions	boolean	optional	Whether to repeat the full dimension dict on every observation. Off by default because the same dimensions already appear on each series descriptor and are encoded in series_id.

publication_id	string	required	Non-empty dataset or table id.
table_id	any	optional	Non-empty dataset or table id.
series_ids	any	optional	Optional list of non-empty source-native series IDs to keep after download.
start_date	any	optional	Optional ISO date bound in YYYY-MM-DD format.
end_date	any	optional	Optional ISO date bound in YYYY-MM-DD format.
last_n	any	optional	Optional limit returning only the most recent N observations per series; metadata.truncated is true when older observations were dropped.
include_observation_dimensions	boolean	optional	Whether to repeat the full dimension dict on every observation. Off by default because the same dimensions already appear on each series descriptor and are encoded in series_id.

concept	string	required	Curated semantic concept name.
variant	any	optional	Optional curated concept variant, such as headline, underlying, or target.
geography	any	optional	Optional geography selector for a curated concept, usually aus for Australia.
frequency	any	optional	Optional requested frequency for a curated concept, such as monthly, quarterly, or annual.
start	any	optional	Optional analyst-friendly date bound: YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD. Semantic retrieval normalises this to the resolved source frequency.
end	any	optional	Optional analyst-friendly date bound: YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD. Semantic retrieval normalises this to the resolved source frequency.
last_n	any	optional	Optional limit returning only the most recent N observations per series; metadata.truncated is true when older observations were dropped.
include_observation_dimensions	boolean	optional	Whether to repeat the full dimension dict on every observation. Off by default because the same dimensions already appear on each series descriptor and are encoded in series_id.