Australian Economic Data (ABS, RBA & APRA)

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

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. 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/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 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"]
    }
  }
}

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.

auseconmcp.com · Issues · MIT Licence