publicdata.au is an MCP server with 12 tools an agent can call, among them count_rows, diff_versions, fetch. It answers at https://publicdata.au/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 29 September 2026; the last check, on 15 November 2026, succeeded.
Search, filter, count and sum Australian government open data, with every version kept.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 Inputs: slug, group_by, metric, where, limit, version |
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 ret Inputs: slug, from, to |
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 f Inputs: id |
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_r Inputs: slug |
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_ |
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 u Inputs: slug |
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 c Inputs: slug, field |
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. Inputs: slug, where, select, order, limit, offset |
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 Inputs: query |
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 w Inputs: query, jurisdiction, votable_only, offset |
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 Inputs: query |
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_catalog Inputs: slug |
Every block below points at https://publicdata.au/mcp. Pick your client and copy.
claude mcp add --transport http publicdata-au https://publicdata.au/mcp
{
"mcpServers": {
"publicdata-au": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://publicdata.au/mcp"]
}
}
}{
"mcpServers": {
"publicdata-au": {
"url": "https://publicdata.au/mcp"
}
}
}{
"servers": {
"publicdata-au": {
"type": "http",
"url": "https://publicdata.au/mcp"
}
}
}{
"context_servers": {
"publicdata-au": {
"url": "https://publicdata.au/mcp"
}
}
}{
"mcpServers": {
"publicdata-au": {
"serverUrl": "https://publicdata.au/mcp"
}
}
}{
"mcpServers": {
"publicdata-au": {
"url": "https://publicdata.au/mcp"
}
}
}name: publicdata.au
version: 0.0.1
schema: v1
mcpServers:
- name: publicdata.au
type: streamable-http
url: https://publicdata.au/mcp{
"mcpServers": {
"publicdata-au": {
"httpUrl": "https://publicdata.au/mcp"
}
}
}{
"mcpServers": {
"publicdata-au": {
"type": "http",
"url": "https://publicdata.au/mcp"
}
}
}{
"mcpServers": {
"publicdata-au": {
"url": "https://publicdata.au/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fpublicdata.au%2Fmcp&type=streamable_http&id=publicdata-au&name=publicdata.au
It answered our last check on 15 November 2026 in 137 ms. Over 4 checks since 29 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by publicdata.au and served from publicdata.au, the vendor's own domain: https://publicdata.au/mcp.
12, as returned by the server's own tools/list on 18 November 2026: count_rows, diff_versions, fetch, get_dataset, list_backlog, list_fields, list_partitions, query_rows, and 4 more.
It answered our last check on 15 November 2026 in 137 ms. Over 4 checks since 29 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://publicdata.au/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: au.publicdata. Endpoint host: publicdata.au. ARD identifier: urn:air:au.publicdata:mcp:mcp.
First indexed 29 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.