Categories › Data & Databases › Files, spreadsheets, CSV & PDFs
Search, filter, count and sum Australian government open data, with every version kept.
Remote server: your requests and data go to publicdata.au. Claude Code: claude mcp add --transport http publicdata-au https://publicdata.au/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
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 datasetget_dataset — Read a served dataset's data package and full version history: licence, attribution, whole-table files and the version dates diff_versions alist_fields — List a served dataset's fields, with their types, descriptions, ranges and values, before querying it. Call it before query_rows or count_rolist_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 slicequery_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_dcount_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 themseldiff_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 ansearch_catalogue — Search every dataset listed on Australia's government portals, including the many publicdata.au does not serve yet. Its records describe datlist_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 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 ssearch — Find served datasets by keyword and return each one's id, title and citation URL, in the shape ChatGPT deep research and company knowledge cfetch — Read one served dataset's record as text to quote and cite: its summary, publisher, licence, attribution string, newest version and the URL Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.