publicdata.au

Australian government open data republished as CSV, Excel, JSON, Parquet, SQLite, DuckDB, GeoJSON and GeoPackage at URLs that never change.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • 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 matc
  • 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 ro
  • 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

What data it sees

Do you need an account

No: the server works without sign-in

Australian government open data republished as CSV, Excel, JSON, Parquet, SQLite, DuckDB, GeoJSON and GeoPackage at URLs that never change. Every release is a dated version that keeps its content, with schema, provenance and a diff. Run by National Digital. No government agency has endorsed it.

Tools:

  • Search datasets: Find the slug of a served dataset.
  • Read a 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.
  • List a dataset's fields: List a served dataset's fields, with their types, descriptions, ranges and values, before querying it.
  • List partition files: List the download files that split a served dataset's newest version by one field, such as one file per year.
  • Query rows: Read individual rows of a served dataset, filtered across the whole table.
  • Count and sum rows: Count, sum, average, minimum or maximum rows of a served dataset across the whole table, grouped by up to three fields.
  • Compare versions: Compare two consecutive versions of a served dataset row by row on its key fields, to see what a publisher changed between releases.
  • Search government portals: Search every dataset listed on Australia's government portals, including the many publicdata.au does not serve yet.
  • List the build backlog: List the datasets people have asked publicdata.au to build, most votes first.
  • Vote for a dataset: Add one anonymous vote for a government dataset that publicdata.au does not serve yet, so it is built sooner.

The fields of one dataset by slug: types, the publisher's descriptions, ranges and the values each field holds. Find slugs with search_datasets or resources/list.

The MCP server records nothing about who calls it or what they ask. To keep the rate limit, it counts row tool calls per address in Cloudflare's cache for 10 seconds.

How to connect

How to connect publicdata.au to Claude

The server address to paste into Claude settings:

https://publicdata-au--national-digital.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect publicdata.au to ChatGPT

The server address to paste into ChatGPT settings:

https://publicdata-au--national-digital.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect publicdata.au to Cursor

The server address to paste into Cursor settings:

https://publicdata-au--national-digital.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

search_datasetsFind 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 prefix, so bus does not find business. Up to 50 matches come back in one answer, with no paging. If nothing matches, try fewer or broader words, then search_catalogue. Each call costs one of the 60 queries each address may make in 10 seconds.
get_datasetRead 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 letters, digits and hyphens, the part after /d/ in a dataset page URL, such as au-road-deaths. The whole history comes back in one answer, with no paging. It needs no key or sign-in, and costs nothing against the rate limit. A slug that is not served returns a 404 error.
list_fieldsList 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_versions compares on and the partition fields list_partitions accepts. slug is lowercase letters, digits and hyphens, the part after /d/ in a dataset page URL, such as au-road-deaths. The answer describes the newest version, in one page. The call costs nothing against the rate limit. A slug that is not served or not loaded for queries returns an error.
list_partitionsList 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 get_dataset. field must be one of the partition_by fields that list_fields names, and any other field returns a 404 error. Every value comes back in one answer, with no paging. The call costs nothing against the rate limit.
query_rowsRead 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 cannot contain a comma. version can be any date in the version history from get_dataset. A version too large for one file is stored as period parts and answered from them, in period order. A filter on the period field reads only the parts it can match, and parts names the periods read. One page holds up to limit rows, and offset steps through the rest until next_offset is null. An unknown field or version returns an error naming it. Each call costs two of the 60 queries each address may make in 10 seconds.
count_rowsCount, 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 field. version can be any date in the version history from get_dataset. A version too large for one file is stored as period parts and answered from them. A filter on the period field reads only the parts it can match, and parts names the periods read. Groups come back largest first, and truncated means raise limit or narrow where. An unknown field or version returns an error naming it. Each call costs two of the 60 queries each address may make in 10 seconds.
diff_versionsCompare 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 a time. A dataset with no key, which list_fields shows as an empty key, gets row counts only, and a dataset with one version has nothing to compare. One answer holds the counts of rows added, removed, changed and unchanged, the keys of the rows added, removed and changed, and up to ten changed rows with their old and new values. The call costs nothing against the rate limit.
search_catalogueSearch 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_dataset. query matches every word against the title, summary and publisher, as search_datasets does. A page holds 20 records, those that can take a vote first. Pass next_offset as offset for the next page, up to 5000. Each call costs three of the 60 queries each address may make in 10 seconds.
list_backlogList 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 claimed yet come back apart, under the vote key search_catalogue uses. The whole backlog comes back in one answer, with no paging, and the call costs nothing against the rate limit.
upvote_datasetAdd 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 that is served, being built or closed returns an error saying it is not open for votes. No identity is recorded, so a vote cannot be withdrawn, and a second vote from the same caller on the same day adds nothing. The answer gives the dataset's vote total after this call. The call costs nothing against the rate limit.