# publicdata.au

Give an AI agent a way to find and analyse Australian government open data. It can narrow records, count them and add up values.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5
- Author: National-Digital
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/National-Digital/publicdata.au
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/publicdataau

## What it does

publicdata.au lets an agent work with Australian government open data. Ask it to find datasets, apply filters, count matching records or calculate a sum. This suits questions that would otherwise mean browsing tables by hand.

Datasets are available in CSV, Excel, JSON, Parquet, SQLite, DuckDB, GeoJSON and GeoPackage. Publisher releases are retained as dated versions, with the publisher's file, a schema and a comparison to the preceding release. Each dataset follows its publisher's licence and attribution terms, so those terms vary by dataset.

To connect it to Claude Code, run `claude mcp add --transport http publicdataau https://publicdata.au/mcp`. The server also supports Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed and Gemini CLI.

## Requirements
- Remote server: `https://publicdata.au/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://publicdata.au/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add publicdataau --url https://publicdata.au/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "publicdataau": {
            "url": "https://publicdata.au/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "publicdataau": {
            "type": "http",
            "url": "https://publicdata.au/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http publicdataau https://publicdata.au/mcp
```

## When to use it
- find an Australian government open-data dataset
- filter records using specified conditions
- count matching rows in a dataset
- add up values in a filtered selection
- compare a dataset release with the one before it

## Example prompts
- Find Australian government open data about public spending and show relevant datasets.
- Filter this dataset to the requested period and count the matching records.
- Compare the latest dataset version with its previous release and describe the changes.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27844
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49863

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md