au.publicdata/mcp

Est-ce que au.publicdata/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « au.publicdata/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 12 outils

• count_rows≈ 902 tokens

  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 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.

  Paramètres, retour & exemple (6)

  Paramètres

  • slug · string · requis
    Dataset slug from search_datasets
  • limit · integer · optionnel
    Groups to return, 1 to 1000. 100 when absent.
  • where · object · optionnel
    Filters by field name, applied to the whole table. A value may be a scalar for an exact, case-sensitive match, a list of scalars to match any of them, null to match blank or suppressed cells, {"min": n, "max": n} for an inclusive range, or {"like": "*text*"} for a pattern where * is the wildcard and case is ignored in ASCII letters. A blank cell never matches a scalar, a list or a range.
  • metric · string · optionnel
    count, or sum, avg, min or max of a field written as sum.field_name. count when absent.
  • version · string · optionnel
    A version date, YYYY-MM-DD, from get_dataset. The newest version when absent.
  • group_by · array · optionnel
    Fields to group by, for example ["crash_severity"]. One total when absent.

  Exemple d'appel

  {"name": "count_rows", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"file": "texte", "parts": [], "query": "texte", "groups": [], "metric": "texte", "matched": 1, "version": "texte", "group_by": [], "manifest": "texte", "truncated": true, "attribution": "texte"}}

• diff_versions≈ 598 tokens

  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 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.

  Paramètres, retour & exemple (3)

  Paramètres

  • to · string · requis
    Newer version date, YYYY-MM-DD
  • from · string · requis
    Older version date, YYYY-MM-DD
  • slug · string · requis
    Dataset slug from search_datasets

  Exemple d'appel

  {"name": "diff_versions", "arguments": {"to": "texte", "from": "texte", "slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"to": "texte", "key": [], "from": "texte", "note": "texte", "added": 1, "schema": {}, "changed": 1, "dataset": "texte", "removed": 1, "rows_to": 1, "examples": [], "rows_from": 1}}

• fetch≈ 382 tokens

  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 query_rows or count_rows, and for every version and file use get_dataset. One answer holds the text, with the same facts under metadata. An id that is not served returns an error. The call costs nothing against the rate limit.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    A dataset id from search, which is its slug. A publicdata.au dataset or version URL is read as its slug.

  Exemple d'appel

  {"name": "fetch", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "metadata": {}}}

• get_dataset≈ 349 tokens

  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 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Dataset slug from search_datasets

  Exemple d'appel

  {"name": "get_dataset", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"versions": "texte", "datapackage": {}}}

• list_backlog≈ 512 tokens

  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 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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_backlog", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"entries": [], "catalogue_votes": []}}

• list_fields≈ 564 tokens

  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_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.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Dataset slug from search_datasets

  Exemple d'appel

  {"name": "list_fields", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"key": [], "rows": 1, "slug": "texte", "title": "texte", "fields": [], "licence": "texte", "version": "texte", "publisher": "texte", "attribution": "texte", "partition_by": []}}

• list_partitions≈ 402 tokens

  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 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.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Dataset slug from search_datasets
  • field · string · requis
    A partition field named in the data package, for example crash_year or loc_local_government_area

  Exemple d'appel

  {"name": "list_partitions", "arguments": {"slug": "texte", "field": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"field": "texte", "partitions": [], "version_base": "texte"}}

• query_rows≈ 1018 tokens

  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 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.

  Paramètres, retour & exemple (7)

  Paramètres

  • slug · string · requis
    Dataset slug from search_datasets
  • limit · integer · optionnel
    Rows to return, 1 to 500. 50 when absent.
  • order · string · optionnel
    field.asc or field.desc, comma-separated. When absent, rows come in the order of the file they are read from. For the newest versions that is the version's own data.parquet, which keeps the publisher's order unless the dataset sorted it. Any other version is read from the Parquet file the answer names in file, and when that file is sorted the answer names its sort in order, which ties follow too.
  • where · object · optionnel
    Filters by field name, applied to the whole table. A value may be a scalar for an exact, case-sensitive match, a list of scalars to match any of them, null to match blank or suppressed cells, {"min": n, "max": n} for an inclusive range, or {"like": "*text*"} for a pattern where * is the wildcard and case is ignored in ASCII letters. A blank cell never matches a scalar, a list or a range.
  • offset · integer · optionnel
    Rows to skip. next_offset in each answer gives the next page.
  • select · array · optionnel
    Fields to return. Every field when absent.
  • version · string · optionnel
    A version date, YYYY-MM-DD, from get_dataset. The newest version when absent.

  Exemple d'appel

  {"name": "query_rows", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"file": "texte", "rows": [], "order": [], "parts": [], "query": "texte", "matched": 1, "version": "texte", "manifest": "texte", "attribution": "texte", "next_offset": 1}}

• search≈ 352 tokens

  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 and newest version. The same id is the slug that list_fields, query_rows and count_rows take. Up to 50 matches come back in one answer, with no paging. Each call costs one of the 60 queries each address may make in 10 seconds.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    Words from a title, publisher or field name

  Exemple d'appel

  {"name": "search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": []}}

• search_catalogue≈ 675 tokens

  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_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.

  Paramètres, retour & exemple (4)

  Paramètres

  • query · string · requis
    Words from a title, description or publisher
  • offset · integer · optionnel
    Rows to skip. next_offset in each answer gives the next page.
  • jurisdiction · string · optionnel · cth | nsw | vic | qld | wa | sa | tas | act
    One government. All when absent.
  • votable_only · boolean · optionnel
    Leave out records that cannot take a vote

  Exemple d'appel

  {"name": "search_catalogue", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"rows": [], "total": 1, "records": 1, "next_offset": 1, "catalogue_read": "texte"}}

• search_datasets≈ 408 tokens

  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 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    Words from a title, publisher or field name

  Exemple d'appel

  {"name": "search_datasets", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": []}}

• upvote_dataset≈ 316 tokens

  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 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    The vote key of a search_catalogue row, or a slug from /backlog.json

  Exemple d'appel

  {"name": "upvote_dataset", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"slug": "texte", "votes": 1}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://publicdata.au/mcp