Summary
Connects Claude directly to the Australian Bureau of Statistics, Reserve Bank of Australia, and APRA data feeds. You get ten tools for querying CPI, GDP, cash rate targets, labour force stats, and 70 other curated economic series, plus nine derived indicators like real cash rate calculations. The semantic layer means you can ask for concepts like "cash_rate_target" instead of hunting through dataset codes, though raw ABS and RBA table access is available when you need exact source control. Built on stdio with HTTP transport support, ships via PyPI, and includes prompt templates for common analyst workflows. Useful when you're building economic analysis tools or need Australian macro data without writing yet another scraper.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
10 tools
search_datasetsSearch curated ABS, RBA, and APRA economic datasets.2 params
Search curated ABS, RBA, and APRA economic datasets.
Parameters* required
querystringDiscovery query text.
sourcevalueOptional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority.
list_catalogueList curated ABS, RBA, and APRA catalogue entries, optionally filtered by source, category, or tag. Unranked complement to ``search_datasets``.5 params
List curated ABS, RBA, and APRA catalogue entries, optionally filtered by source, category, or tag. Unranked complement to ``search_datasets``.
Parameters* required
categoryvalueOptional curated catalogue or semantic concept category filter.
include_ceasedbooleanWhether to include ceased ABS catalogue entries.default: false
include_discontinuedbooleanWhether to include discontinued RBA catalogue entries.default: false
sourcevalueOptional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority.
tagvalueOptional curated catalogue tag filter.
list_economic_conceptsList analyst-friendly semantic economic concepts accepted by get_economic_series.3 params
List analyst-friendly semantic economic concepts accepted by get_economic_series.
Parameters* required
categoryvalueOptional curated catalogue or semantic concept category filter.
queryvalueOptional query for filtering semantic economic concepts.
sourcevalueOptional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority.
get_abs_dataset_structureGet ABS SDMX dataset dimensions and codelists.1 params
Get ABS SDMX dataset dimensions and codelists.
Parameters* required
dataflow_idstringNon-empty dataset or table id.
get_abs_dataExpert/source-native ABS SDMX retrieval in a normalised response shape.6 params
Expert/source-native ABS SDMX retrieval in a normalised response shape.
Parameters* required
dataflow_idstringNon-empty dataset or table id.
end_periodvalueOptional ABS period bound in YYYY, YYYY-QN, YYYY-MM, or YYYY-SN format.
keystringABS SDMX key, or "all" for all series.default: all
last_nvalueOptional positive observation count limit.
start_periodvalueOptional ABS period bound in YYYY, YYYY-QN, YYYY-MM, or YYYY-SN format.
updated_aftervalueOptional ISO date or datetime accepted by the ABS updatedAfter API.
list_rba_tablesDeprecated compatibility alias. Prefer list_catalogue(source="rba").2 params
Deprecated compatibility alias. Prefer list_catalogue(source="rba").
Parameters* required
categoryvalueOptional RBA catalogue category filter.
include_discontinuedbooleanWhether to include discontinued RBA catalogue entries.default: false
get_rba_tableExpert/source-native RBA statistical table retrieval in a normalised response shape.5 params
Expert/source-native RBA statistical table retrieval in a normalised response shape.
Parameters* required
end_datevalueOptional ISO date bound in YYYY-MM-DD format.
last_nvalueOptional positive observation count limit.
series_idsvalueOptional list of non-empty source-native series IDs to keep after download.
start_datevalueOptional ISO date bound in YYYY-MM-DD format.
table_idstringNon-empty dataset or table id.
get_apra_dataExpert/source-native APRA public XLSX publication retrieval. Only curated official APRA publication IDs are accepted; arbitrary URLs are not.6 params
Expert/source-native APRA public XLSX publication retrieval. Only curated official APRA publication IDs are accepted; arbitrary URLs are not.
Parameters* required
end_datevalueOptional ISO date bound in YYYY-MM-DD format.
last_nvalueOptional positive observation count limit.
publication_idstringNon-empty dataset or table id.
series_idsvalueOptional list of non-empty source-native series IDs to keep after download.
start_datevalueOptional ISO date bound in YYYY-MM-DD format.
table_idvalueNon-empty dataset or table id.
get_economic_seriesPreferred 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.7 params
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.
Parameters* required
conceptstringCurated semantic concept name.
endvalueOptional analyst-friendly date bound: YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD. Semantic retrieval normalises this to the resolved source frequency.
frequencyvalueOptional requested frequency for a curated concept, such as monthly, quarterly, or annual.
geographyvalueOptional geography selector for a curated concept, usually aus for Australia.
last_nvalueOptional positive observation count limit.
startvalueOptional analyst-friendly date bound: YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD. Semantic retrieval normalises this to the resolved source frequency.
variantvalueOptional curated concept variant, such as headline, underlying, or target.
get_derived_seriesRead-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.4 params
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.
Parameters* required
conceptstringDerived concept name.
endvalueOptional analyst-friendly bound for a derived series: YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD. Bounds are normalised to the derived series frequency.
last_nvalueOptional positive observation count limit.
startvalueOptional analyst-friendly bound for a derived series: YYYY, YYYY-QN, YYYY-SN, YYYY-MM, or YYYY-MM-DD. Bounds are normalised to the derived series frequency.
ausecon is a Model Context Protocol server that gives any AI assistant clean, structured access to Australia’s core economic and financial data — straight from the ABS, RBA, and APRA.
Open · free · no API key — always fresh & fully source-traceable, three official sources in one shape.
Documentation · Getting started · Tool reference · Changelog
Why this exists
Australian economic data is authoritative but awkward to reach — scattered across portals,
formats, and identifiers you have to memorise. ausecon is the open, free, no-API-key way to
put it in front of any AI assistant: every series comes back fresh and fully source-traceable, stamped with its provenance,
in one consistent shape
(metadata · series · observations) across all three regulators. Ask for “the cash
rate” or “quarterly real GDP growth” and get research-grade data back without
leaving the conversation.
| 14 read-only tools |
83 economic concepts |
16 derived indicators |
8 prompt templates |
3 data sources |
What you get
🔒 Fresh & source-traceableEvery value is fetched live and stamped with its provenance (retrieved_at, source, server_version). On an upstream
outage, a cached fallback is always flagged stale — never served silently.
|
🧱 Three sources, one shapeABS, RBA and APRA all return the same tidymetadata · series · observations structure.
|
🧮 Transparent derived seriesFormula-based indicators likereal_cash_rate — every calculation is
open and inspectable.
|
🎯 Source-native controlDrop down to rawget_abs_data, get_rba_table or
get_apra_data whenever you need exact control.
|
⚡ Quick-turn helpersConvenience tools for latest observations, top movers and release events — analysis in one call. |
🔌 Plugs into your clientClaude 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)
Prefer not to install anything? 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 (Streamable HTTP) servers at that URL — for example, in Claude Code:
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/mcpURL continues to work and points at the same instance.
Install
The package lives on PyPI and is designed to be
launched on demand by your MCP client via uvx:
uvx ausecon-mcp-server
The server speaks MCP over standard input/output. Launched on its own, it simply waits for a client to connect.
Connect your client
Claude Code
claude mcp add --transport stdio ausecon -- uvx ausecon-mcp-server
Codex
codex mcp add ausecon -- uvx ausecon-mcp-server
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ausecon": {
"command": "uvx",
"args": ["ausecon-mcp-server"]
}
}
}
Cursor
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=
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"ausecon": {
"command": "uvx",
"args": ["ausecon-mcp-server"],
"env": {}
}
}
}
VS Code
Or add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"ausecon": {
"type": "stdio",
"command": "uvx",
"args": ["ausecon-mcp-server"]
}
}
}
Hosting it instead?
smithery.yamlandDockerfile.smitheryship 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",
)
Need a transparent, formula-based indicator? Call the derived surface directly:
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 maps your request to the right tool calls for you.
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 — see the evaluation harness guide before running one.
auseconmcp.com · Issues · MIT Licence · Made for the Australian data community
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Categories
Registryactive
Packageausecon-mcp-server
TransportSTDIO
UpdatedApr 19, 2026
