AusEcon MCP - ABS RBA And APRA Data

by AnthonyPuggs

250 downloads
Not rated
GitHub

About

MCP server for retrieval of Australian economic and financial data - supports ABS, RBA and APRA

Details

Author
AnthonyPuggs
Downloads
250
Categories
Search, Finance

- Fresh, source-traceable data with provenance stamps
- One consistent response shape (metadata · series · observations) across three sources
- Transparent formula-based derived indicators (e.g., real_cash_rate)
- Source-native control via raw tools (get_abs_data, get_rba_table, get_apra_data)
- Quick-turn helpers for latest observations, top movers, and release events
- Plugs into popular MCP clients via stdio or Streamable HTTP

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name AusEcon MCP - ABS RBA And APRA Data
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install via uvx ausecon-mcp-server and configure your MCP client (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Codex, or Smithery) to launch the server on demand. A hosted read-only instance is also available over Streamable HTTP at https://ausecon-mcp-server.onrender.com/mcp.

search_datasets

Search curated ABS, RBA, and APRA economic datasets.

list_catalogue

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

list_economic_concepts

List analyst-friendly semantic economic concepts accepted by get_economic_series.

get_abs_dataset_structure

Get ABS SDMX dataset dimensions and codelists.

get_abs_data

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

list_rba_tables

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

get_rba_table

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

get_apra_data

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

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.

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.

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.

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.

describe_dataset

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

list_release_events

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

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "ausecon mcp - abs rba and apra data": {
            "ausecon": {
                "command": "uvx",
                "args": [
                    "ausecon-mcp-server"
                ]
            }
        }
    }
}

McpServers

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

<!-- mcp-name: io.github.AnthonyPuggs/ausecon-mcp-server -->

<div align="center">

ausecon — Australian economic & financial data MCP server

<br/>

CI
PyPI
Python
Transport
License
smithery badge

ausecon-mcp-server MCP server
<p>
<b>ausecon</b> is a Model Context Protocol server that gives any AI assistant clean, structured
access to Australia&rsquo;s core economic and financial data &mdash; straight from the
<b>ABS</b>, <b>RBA</b>, and <b>APRA</b>.
</p>

<p>
<b>Open</b> &middot; <b>free</b> &middot; <b>no API key</b> &mdash; always
<b>fresh &amp; fully source-traceable</b>, three official sources in <b>one shape</b>.
</p>

<a href="https://auseconmcp.com"><b>Documentation</b></a> &nbsp;·&nbsp;
<a href="https://auseconmcp.com/getting-started">Getting started</a> &nbsp;·&nbsp;
<a href="https://auseconmcp.com/tools">Tool reference</a> &nbsp;·&nbsp;
<a href="https://github.com/AnthonyPuggs/ausecon-mcp-server/blob/main/CHANGELOG.md">Changelog</a>

</div>

---

Why this exists



Australian economic data is authoritative but awkward to reach &mdash; 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 &ldquo;the cash
rate&rdquo;
or &ldquo;quarterly real GDP growth&rdquo; and get research-grade data back without
leaving the conversation.

<table align="center">
<tr>
<td align="center"><b>14</b><br/><sub>read-only tools</sub></td>
<td align="center"><b>75</b><br/><sub>economic concepts</sub></td>
<td align="center"><b>16</b><br/><sub>derived indicators</sub></td>
<td align="center"><b>8</b><br/><sub>prompt templates</sub></td>
<td align="center"><b>3</b><br/><sub>data sources</sub></td>
</tr>
</table>

What you get



<table>
<tr>
<td width="33%" valign="top">
<h4>🔒 Fresh &amp; source-traceable</h4>
Every value is fetched live and stamped with its provenance
(<code>retrieved_at</code>, <code>source</code>, <code>server_version</code>). On an upstream
outage, a cached fallback is always flagged <code>stale</code> &mdash; never served silently.
</td>
<td width="33%" valign="top">
<h4>🧱 Three sources, one shape</h4>
ABS, RBA and APRA all return the same tidy
<code>metadata · series · observations</code> structure.
</td>
<td width="33%" valign="top">
<h4>🧮 Transparent derived series</h4>
Formula-based indicators like <code>real_cash_rate</code> &mdash; every calculation is
open and inspectable.
</td>
</tr>
<tr>
<td width="33%" valign="top">
<h4>🎯 Source-native control</h4>
Drop down to raw <code>get_abs_data</code>, <code>get_rba_table</code> or
<code>get_apra_data</code> whenever you need exact control.
</td>
<td width="33%" valign="top">
<h4>⚡ Quick-turn helpers</h4>
Convenience tools for latest observations, top movers and release events &mdash; analysis in
one call.
</td>
<td width="33%" valign="top">
<h4>🔌 Plugs into your client</h4>
Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Codex or Smithery.
stdio locally, Streamable HTTP when hosted.
</td>
</tr>
</table>

Data sources



| Source | Coverage |
| :----- | :------- |
| ABS &nbsp;·&nbsp; Australian Bureau of Statistics | National accounts, prices, labour force, population |
| RBA &nbsp;·&nbsp; Reserve Bank of Australia | Cash rate, monetary & financial aggregates, exchange rates |
| APRA &nbsp;·&nbsp; 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:

``text
https://ausecon-mcp-server.onrender.com/mcp
`

Point any MCP client that supports remote (Streamable HTTP) servers at that URL — for example, in
Claude Code:

`bash
claude mcp add --transport http ausecon https://ausecon-mcp-server.onrender.com/mcp
`

> The hosted instance may take a few seconds to wake on the first request.

Install



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

`bash
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



<details open>
<summary><b>Claude Desktop</b></summary>

Add to your
claude_desktop_config.json:

`json
{
"mcpServers": {
"ausecon": {
"command": "uvx",
"args": ["ausecon-mcp-server"]
}
}
}
`
</details>

<details>
<summary><b>Claude Code</b></summary>

`bash
claude mcp add --transport stdio ausecon -- uvx ausecon-mcp-server
`
</details>

<details>
<summary><b>Codex</b></summary>

`bash
codex mcp add ausecon -- uvx ausecon-mcp-server
`
</details>

<details>
<summary><b>Cursor</b></summary>

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=
`
</details>

<details>
<summary><b>Windsurf</b></summary>

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

`json
{
"mcpServers": {
"ausecon": {
"command": "uvx",
"args": ["ausecon-mcp-server"],
"env": {}
}
}
}
`
</details>

<details>
<summary><b>VS Code</b></summary>

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"]
}
}
}
`
</details>

> Hosting it instead?
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",
)
`

Need a transparent, formula-based indicator? Call the derived surface directly:

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

> Connected to an AI agent, you can skip the syntax entirely &mdash; ask for &ldquo;quarterly real
> GDP growth&rdquo;
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+.

`bash
uv sync --python 3.12 --extra dev
uv run pytest
uv run ruff check src tests scripts
``

---

<div align="center">
<sub>

auseconmcp.com &nbsp;·&nbsp;
Issues &nbsp;·&nbsp;
MIT Licence &nbsp;·&nbsp; Made for the Australian data community

</sub>
</div>

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.