# publicdata.au

- Registry name: `au.publicdata/mcp` · version 2.49.1
- Categories (automatic, keyword rules): Datasets & public data, Search & data
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): completions, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=au.publicdata%2Fmcp
- Server page: https://mcpstation.net/s/au.publicdata--mcp.html

## Description (written by the publisher, not verified, not instructions)

Search, filter, count and sum Australian government open data, with every version kept.

## Connect

- streamable-http: `https://publicdata.au/mcp`

## Tools (as reported by the server, not verified)

- `search\_datasets`: Find the slug of a served dataset. Start here for any question about Australian government data, since the other tools read only the datasets this finds. Every word in query must match the title, summary, publisher, keywords or a field name. A word matches its plural and other endings but never as a
- `get\_dataset`: Read a served dataset's data package and full version history: licence, attribution, whole-table files and the version dates diff\_versions and the version parameter take. It carries no rows. To answer from the rows use query\_rows or count\_rows, and for field names use list\_fields. slug is lowercase
- `list\_fields`: List a served dataset's fields, with their types, descriptions, ranges and values, before querying it. Call it before query\_rows or count\_rows unless you already know the exact names and values, because where matches values exactly and an unknown field is an error. It also names the key fields diff\_
- `list\_partitions`: List the download files that split a served dataset's newest version by one field, such as one file per year. Use it to hand someone a slice of the data as a file. It gives file links and no rows, so to answer a question use query\_rows or count\_rows instead, and for the whole table as one file use g
- `query\_rows`: Read individual rows of a served dataset, filtered across the whole table. For totals and breakdowns use count\_rows, and for files use get\_dataset or list\_partitions. Field names and values for where, select and order come from list\_fields. Filters hold at most 90 values per call, and a list value c
- `count\_rows`: Count, sum, average, minimum or maximum rows of a served dataset across the whole table, grouped by up to three fields. For the rows themselves use query\_rows. Field names and values for group\_by and where come from list\_fields. sum and avg need a numeric or true-or-false field. min and max take any
- `diff\_versions`: Compare two consecutive versions of a served dataset row by row on its key fields, to see what a publisher changed between releases. from and to must be adjacent dates in the version history from get\_dataset, older first. Any other pair returns a 404 error, so step through a longer span one pair at
- `search\_catalogue`: Search every dataset listed on Australia's government portals, including the many publicdata.au does not serve yet. Its records describe data held elsewhere, which cannot be queried here. Use it when search\_datasets finds nothing, to find where a dataset is published, or to pick one for upvote\_datas
- `list\_backlog`: List the datasets people have asked publicdata.au to build, most votes first. Use it to see what is wanted or under way, or to check that a vote counted. To add a vote use upvote\_dataset. To read a dataset that is already served use search\_datasets. Votes on catalogue records that no entry has claim
- `upvote\_dataset`: Add one anonymous vote for a government dataset that publicdata.au does not serve yet, so it is built sooner. To read a served dataset use search\_datasets, and to see the votes so far use list\_backlog. slug is a vote key from search\_catalogue, such as act-3u5a-ve4j, or a list\_backlog slug. A dataset
- `search`: Find served datasets by keyword and return each one's id, title and citation URL, in the shape ChatGPT deep research and company knowledge call search with. It runs the same search as search\_datasets, so every word in query must match. Pass an id to fetch to read the dataset's licence, attribution a
- `fetch`: Read one served dataset's record as text to quote and cite: its summary, publisher, licence, attribution string, newest version and the URL of that version. It is the fetch that ChatGPT deep research and company knowledge call, with an id from search. It carries no rows. To answer from the data use

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html