# publicdata.au (remote · publicdata.au)

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

- Trust score: 79/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-03

## Components

- remote · `publicdata.au`: 79/100 (this document), [markdown](https://verifymcp.io/servers/au-publicdata-mcp/publicdata.md), [page](https://verifymcp.io/servers/au-publicdata-mcp/publicdata)

## Channel facts

- Endpoint: `https://publicdata.au/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-03.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 88/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 17227 tokens (~79/item across 218 items; 10 tools + 208 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the publicdata.au MCP server?

publicdata.au is a hosted endpoint at https://publicdata.au/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http au-publicdata-mcp 'https://publicdata.au/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "au-publicdata-mcp": {
      "url": "https://publicdata.au/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "au-publicdata-mcp": {
      "type": "http",
      "url": "https://publicdata.au/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.au-publicdata-mcp]
url = "https://publicdata.au/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "au-publicdata-mcp": {
      "type": "remote",
      "url": "https://publicdata.au/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add au-publicdata-mcp --url 'https://publicdata.au/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  au-publicdata-mcp:
    url: "https://publicdata.au/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "au-publicdata-mcp": {
      "Transport": "http",
      "Url": "https://publicdata.au/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add au-publicdata-mcp -t streamable-http -u 'https://publicdata.au/mcp'
```

### Other

```json
{
  "mcpServers": {
    "au-publicdata-mcp": {
      "type": "http",
      "url": "https://publicdata.au/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-03 (score 79, +1)

- [functional improvement] Schema quality: 94 → 79
- [functional] New resource “act-2003-bushfire”
- [functional] New resource “act-air-quality”
- [functional] New resource “act-barbecues”
- [functional] New resource “act-bdm-registrations”
- [functional] New resource “act-contracts-register-2016-2017”
- [functional] New resource “act-engineers-register”
- [functional] New resource “act-historic-death-index”
- [functional] New resource “act-historic-marriage-index”
- [functional] New resource “act-lakes-rivers-water-quality”
- [functional] New resource “act-licences-transferred-interstate”
- [functional] New resource “act-licences-transferred-to-act”
- [functional] New resource “act-mobile-distraction-camera-locations”
- [functional] New resource “act-mobile-speed-camera-visits”
- [functional] New resource “act-mutual-recognition-register”
- [functional] New resource “act-notifiable-invoices”
- [functional] New resource “act-parking-offences”
- [functional] New resource “act-police-stations”
- [functional] New resource “act-recreational-water-quality-2018-19”
- [functional] New resource “act-recreational-water-quality-2019-20”
- [functional] New resource “act-traffic-camera-locations”
- [functional] New resource “act-traffic-camera-offences”
- [functional] New resource “act-traffic-camera-offences-2010-2021”
- [functional] New resource “act-vehicles-registered”
- [functional] New resource “nsw-bdm-disposal-methods-monthly”
- [functional] New resource “nsw-bdm-registrations-monthly”
- [functional] New resource “nsw-beachwatch-sites”
- [functional] New resource “nsw-liquor-licence-premises”
- [functional] New resource “nsw-popular-baby-names”
- [functional] New resource “nsw-primary-class-sizes”
- [functional] New resource “nsw-public-holidays”
- [functional] New resource “nsw-public-schools”
- [functional] New resource “nsw-rental-bond-lodgements-2021”
- [functional] New resource “nsw-rental-bond-lodgements-2022”
- [functional] New resource “nsw-rental-bond-lodgements-2023”
- [functional] New resource “nsw-rental-bond-lodgements-2024”
- [functional] New resource “nsw-rental-bond-lodgements-2025”
- [functional] New resource “nsw-rental-bond-refunds-2021”
- [functional] New resource “nsw-rental-bond-refunds-2022”
- [functional] New resource “nsw-rental-bond-refunds-2023”
- [functional] New resource “nsw-rental-bond-refunds-2024”
- [functional] New resource “nsw-rental-bond-refunds-2025”
- [functional] New resource “nsw-school-intake-zones-future”
- [functional] New resource “nsw-school-intake-zones-primary”
- [functional] New resource “nsw-school-intake-zones-secondary”
- [functional] New resource “nsw-school-term-dates”
- [functional] New resource “nsw-top-baby-names-by-lga-female”
- [functional] New resource “nsw-top-baby-names-by-lga-male”
- [functional] New resource “nsw-traffic-count-stations”
- [functional] New resource “nsw-traffic-volume-yearly”
- [functional] New resource “qld-bushfire-incidents-current”
- [functional] New resource “qld-emergency-department-busyness”
- [functional] New resource “qld-emergency-department-facilities”
- [functional] New resource “qld-emergency-department-waits-now”
- [functional] New resource “sa-adelaide-city-barbecues”
- [functional] New resource “sa-air-quality-monitoring-sites”
- [functional] New resource “sa-baby-names-boys”
- [functional] New resource “sa-baby-names-girls”
- [functional] New resource “sa-boat-registrations”
- [functional] New resource “sa-camera-detections-not-accepted”
- [functional] New resource “sa-camera-expiation-offences”
- [functional] New resource “sa-crime-statistics”
- [functional] New resource “sa-dog-cat-incidents”
- [functional] New resource “sa-dogs-cats-owners”
- [functional] New resource “sa-dogs-cats-registered-animals”
- [functional] New resource “sa-drivers-licences-by-postcode”
- [functional] New resource “sa-family-domestic-abuse-offences”
- [functional] New resource “sa-fire-history”
- [functional] New resource “sa-food-enforcement-food-service”
- [functional] New resource “sa-food-enforcement-food-transporter”
- [functional] New resource “sa-food-enforcement-processor-manufacturer”
- [functional] New resource “sa-food-enforcement-retail”
- [functional] New resource “sa-heritage-places”
- [functional] New resource “sa-high-school-zones”
- [functional] New resource “sa-liquor-gaming-licences-2018”
- [functional] New resource “sa-metro-median-house-prices”
- [functional] New resource “sa-mobile-camera-location-codes”
- [functional] New resource “sa-police-expiation-offences”
- [functional] New resource “sa-primary-school-zones”
- [functional] New resource “sa-private-hospitals”
- [functional] New resource “sa-private-rents-by-postcode”
- [functional] New resource “sa-private-rents-by-suburb”
- [functional] New resource “sa-public-hospitals”
- [functional] New resource “sa-public-housing-dwellings”
- [functional] New resource “sa-public-housing-households”
- [functional] New resource “sa-public-housing-new-households”
- [functional] New resource “sa-registered-vehicles-by-body-type”
- [functional] New resource “sa-registered-vehicles-by-colour”
- [functional] New resource “sa-registered-vehicles-by-postcode”
- [functional] New resource “sa-reservoir-volumes”
- [functional] New resource “sa-river-murray-flood-100gl”
- [functional] New resource “sa-river-murray-flood-120gl”
- [functional] New resource “sa-river-murray-flood-130gl”
- [functional] New resource “sa-river-murray-flood-140gl”
- [functional] New resource “sa-river-murray-flood-160gl”
- [functional] New resource “sa-river-murray-flood-180gl”
- [functional] New resource “sa-river-murray-flood-200gl”
- [functional] New resource “sa-river-murray-flood-2022”
- [functional] New resource “sa-river-murray-flood-250gl”
- [functional] New resource “sa-river-murray-flood-300gl”
- [functional] New resource “sa-river-murray-flood-341gl”
- [functional] New resource “sa-school-enrolments-by-type”
- [functional] New resource “sa-suburb-boundaries”
- [functional] New resource “sa-traffic-volumes”
- [functional] New resource “tas-accredited-building-practitioners-2017”
- [functional] New resource “tas-deaths-1803-1939”
- [functional] New resource “tas-rental-bonds-closed-2016-11”
- [functional] New resource “tas-rental-bonds-lodged-2016-11”
- [functional] New resource “vic-air-quality-hourly”
- [functional] New resource “vic-ambulance-response-times-by-lga”
- [functional] New resource “vic-ambulance-response-times-by-town”
- [functional] New resource “vic-ballarat-lightning-observations”
- [functional] New resource “vic-beach-report-enterococci”
- [functional] New resource “vic-beach-report-sites”
- [functional] New resource “vic-cfa-incident-responses”
- [functional] New resource “vic-consumer-enforcement-outcomes”
- [functional] New resource “vic-deaths-registered-by-month”
- [functional] New resource “vic-driver-licence-transfers-from-victoria”
- [functional] New resource “vic-driver-licence-transfers-to-victoria”
- [functional] New resource “vic-gaming-expenditure-by-venue”
- [functional] New resource “vic-gaming-expenditure-by-venue-history”
- [functional] New resource “vic-golden-plains-animal-registrations”
- [functional] New resource “vic-greater-dandenong-registered-dogs”
- [functional] New resource “vic-heritage-register”
- [functional] New resource “vic-important-dates”
- [functional] New resource “vic-land-tax-by-municipality”
- [functional] New resource “vic-land-transfer-duty-by-postcode”
- [functional] New resource “vic-liquor-licences”
- [functional] New resource “vic-marriages-registered-by-month”
- [functional] New resource “vic-measles-exposure-sites”
- [functional] New resource “vic-median-unit-prices-by-suburb”
- [functional] New resource “vic-median-vacant-land-prices-by-suburb”
- [functional] New resource “vic-melbourne-water-daily-storage”
- [functional] New resource “vic-metro-train-station-patronage”
- [functional] New resource “vic-mfb-fire-station-locations”
- [functional] New resource “vic-mobile-road-safety-camera-locations”
- [functional] New resource “vic-new-vehicle-registrations-monthly”
- [functional] New resource “vic-prison-locations”
- [functional] New resource “vic-regional-train-station-patronage”
- [functional] New resource “vic-registered-events-by-calendar-year”
- [functional] New resource “vic-registered-events-by-financial-year”
- [functional] New resource “vic-road-safety-camera-fines-by-site”
- [functional] New resource “vic-school-locations”
- [functional] New resource “vic-school-zones-primary-2027”
- [functional] New resource “vic-school-zones-year7-2027”
- [functional] New resource “vic-southern-grampians-animal-registrations”
- [functional] New resource “vic-stream-restrictions”
- [functional] New resource “vic-traffic-infringements-vs-official-warnings”
- [functional] New resource “vic-traffic-volume-aadt-2019”
- [functional] New resource “vic-unclaimed-money-claims”
- [functional] New resource “vic-unclaimed-money-payments”
- [functional] New resource “vic-vehicle-registrations-by-model”
- [functional] New resource “vic-vehicle-registrations-by-postcode”
- [functional] New resource “wa-dpird-weather-stations”
- [functional] New resource “wa-public-housing-dwelling-age-by-suburb”
- [functional] New resource “wa-public-libraries”
- [functional] New resource “wa-slwa-obituaries-index”
- [functional] New resource “wa-traffic-digest”
- [functional] New resource “wa-wave-stations-current”
- [functional] New resource “wa-wave-stations-historic”
- [functional] Server version: 2.19.0 → 2.20.3

### 2026-10-02 (score 78, 0)

- [functional] New resource “abs-federal-electoral-divisions-2025”
- [functional] New resource “abs-lga-2025”
- [functional] New resource “abs-postal-areas-2021”
- [functional] New resource “abs-sa2-2021”
- [functional] New resource “abs-state-electoral-divisions-2025”
- [functional] New resource “abs-suburbs-localities-2021”
- [functional] Server version: 2.13.3 → 2.19.0

### 2026-10-01 (score 78, +1)

- [functional improvement] Schema quality: fail → pass
- [functional] New resource “acnc-register”
- [functional] New resource “au-domestic-homicide-victims”
- [functional] New resource “au-fdv-hospitalisations”
- [functional] New resource “au-fdv-victims-recorded-crime”
- [functional] New resource “au-homelessness-services-monthly”
- [functional] New resource “au-shark-incidents”
- [functional] New resource “au-suicide-deaths-by-age”
- [functional] New resource “au-suicide-deaths-by-state”
- [functional] New resource “au-water-storages”
- [functional] New resource “nt-fuel-prices-history”
- [functional] New resource “rba-cash-rate”
- [functional] New resource “rba-indicator-lending-rates”
- [functional] New resource “rba-money-market-daily”
- [functional] New resource “rba-paid-deposit-rates”
- [functional] New resource “rba-retail-deposit-rates”
- [functional] New resource “rogs-corrective-services”
- [functional] New resource “rogs-homelessness-services”
- [functional] New resource “rogs-youth-justice”
- [functional] New resource “vic-median-house-prices-by-suburb”
- [functional] New resource “vic-water-storage-levels”
- [functional] New resource “vic-water-storages”
- [functional] Server version: 2.2.1 → 2.13.3

### 2026-09-30 (score 77, 0)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 2.1.0 → 2.2.1

### 2026-09-29 (score 77)

First indexed and scored.

## MCP tools (10)

### `search_datasets` (~142 tokens)

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 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.

Input parameters:

- `query` (string, required): Words from a title, publisher or field name

Output parameters:

- `results` (array): Matches, best first when the search index is loaded

### `get_dataset` (~154 tokens)

Read a dataset

Read a served dataset's data package and full version history. Use it to download the whole table, check the licence, or find version dates for diff_versions and the version parameter.
For field names use list_fields. To answer a question from the rows use query_rows or count_rows, which need no download.
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.

Input parameters:

- `slug` (string, required): Dataset slug from search_datasets

Output parameters:

- `datapackage` (object): The Frictionless data package: description, licence, attribution string, source, and resources with the URL, format and size of the whole file in each format
- `versions`: Every version with its date, the date its data is as at, row count, source hash and fetch time

### `list_fields` (~157 tokens)

List a dataset's 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_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.

Input parameters:

- `slug` (string, required): Dataset slug from search_datasets

Output parameters:

- `attribution` (string|null): The publisher's attribution string, to show with any answer
- `fields` (array): Each field's name, type and publisher's description, with min and max for numbers and dates and values when it holds few
- `key` (array): Fields that identify a row, compared on by diff_versions. Empty when none is declared
- `licence` (string|null)
- `partition_by` (array): Fields list_partitions accepts
- `publisher` (string|null)
- `rows` (integer): Rows in that version
- `slug` (string)
- `title` (string)
- `version` (string): The version the fields describe

### `list_partitions` (~151 tokens)

List partition files

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. To answer a question use query_rows or count_rows instead, and for the whole table 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.

Input parameters:

- `field` (string, required): A partition field named in the data package, for example crash_year or loc_local_government_area
- `slug` (string, required): Dataset slug from search_datasets

Output parameters:

- `field` (string)
- `partitions` (array): One entry per value: the value, its row count and the URL of a JSON file with every row holding it
- `version_base` (string): The version these files belong to

### `query_rows` (~331 tokens)

Query rows

Read individual rows of a served dataset, filtered across the whole table. For totals and breakdowns use count_rows.
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 must be one of the two newest versions.
Page with offset 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.

Input parameters:

- `limit` (integer): Rows to return, 1 to 500. 50 when absent.
- `offset` (integer): Rows to skip. next_offset in each answer gives the next page.
- `order` (string): field.asc or field.desc, comma-separated. The publisher's row order when absent.
- `select` (array): Fields to return. Every field when absent.
- `slug` (string, required): Dataset slug from search_datasets
- `version` (string): A version date, YYYY-MM-DD, from get_dataset. The newest version loaded for queries when absent.
- `where` (object): 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":…

Output parameters:

- `attribution` (string|null): The publisher's attribution string, to show with any answer
- `matched` (integer): Rows in the whole table that match where
- `next_offset` (integer|null): offset for the next page, or null on the last
- `query` (string): The query API URL that gives the same answer
- `rows` (array): The rows, with the fields in select or every field
- `version` (string|null): The version answered

### `count_rows` (~345 tokens)

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. 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 must be one of the two newest versions.
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.

Input parameters:

- `group_by` (array): Fields to group by, for example ["crash_severity"]. One total when absent.
- `limit` (integer): Groups to return, 1 to 1000. 100 when absent.
- `metric` (string): count, or sum, avg, min or max of a field written as sum.field_name. count when absent.
- `slug` (string, required): Dataset slug from search_datasets
- `version` (string): A version date, YYYY-MM-DD, from get_dataset. The newest version loaded for queries when absent.
- `where` (object): 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":…

Output parameters:

- `attribution` (string|null): The publisher's attribution string, to show with any answer
- `group_by` (array)
- `groups` (array): One object per group, holding the group_by fields and the metric value, largest first
- `matched` (integer): Rows in the whole table that match where
- `metric` (string)
- `query` (string): The query API URL that gives the same answer
- `truncated` (boolean): True when more groups exist than limit
- `version` (string|null): The version answered

### `diff_versions` (~154 tokens)

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. 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. The call costs nothing against the rate limit.

Input parameters:

- `from` (string, required): Older version date, YYYY-MM-DD
- `slug` (string, required): Dataset slug from search_datasets
- `to` (string, required): Newer version date, YYYY-MM-DD

Output parameters:

- `added` (integer)
- `added_keys` (array)
- `changed` (integer)
- `changed_keys` (array)
- `dataset` (string)
- `examples` (array): Up to ten changed rows, each with its key and the fields that changed from and to
- `from` (string): Older version date
- `key` (array): Key fields compared on. Empty when none is declared
- `note` (string): Present when no key is declared and only row counts are compared
- `removed` (integer)
- `removed_keys` (array)
- `rows_from` (integer)
- `rows_to` (integer)
- `schema` (object): Fields added, removed and retyped between the versions
- `to` (string): Newer version date
- `truncated` (boolean): True when a key list stops at its cap
- `unchanged` (integer)

### `search_catalogue` (~200 tokens)

Search government portals

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.

Input parameters:

- `jurisdiction` (string): One government. All when absent.
- `offset` (integer): Rows to skip. next_offset in each answer gives the next page.
- `query` (string, required): Words from a title, description or publisher
- `votable_only` (boolean): Leave out records that cannot take a vote

Output parameters:

- `catalogue_read` (string): Date the portal lists were read
- `next_offset` (integer|null): offset for the next page, or null on the last
- `records` (integer)
- `rows` (array)
- `total` (integer): Records that match

### `list_backlog` (~112 tokens)

List the build 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 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.

Output parameters:

- `catalogue_votes` (array): Votes on catalogue records no register entry has claimed yet, most first
- `entries` (array): Register entries that are not live yet, most votes first

### `upvote_dataset` (~158 tokens)

Vote for a 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 that is served, being built or closed returns an error saying it is not open for votes.
No identity is recorded, and a second vote from the same caller on the same day adds nothing. The call costs nothing against the rate limit.

Input parameters:

- `slug` (string, required): The vote key of a search_catalogue row, or a slug from /backlog.json

Output parameters:

- `slug` (string)
- `votes` (integer): The dataset's vote total after this call

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/au-publicdata-mcp/publicdata#diagnostics

## Score history

- 2026-10-03: 79
- 2026-10-02: 78
- 2026-10-01: 78
- 2026-09-30: 77
- 2026-09-29: 77

## Common questions

### What is the publicdata.au MCP server?

publicdata.au is an MCP server listed in the public MCP registry as au.publicdata/mcp. Search, filter, count and sum Australian government open data, with every version kept. This page covers its hosted endpoint (https://publicdata.au/mcp).

### Is the publicdata.au MCP server safe to use?

publicdata.au scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the publicdata.au MCP server expose?

publicdata.au exposes 10 tools: search_datasets, get_dataset, list_fields, list_partitions, query_rows, and 5 more. Their descriptions and schemas cost roughly 1,904 tokens of context every time the server is loaded.

### Does the publicdata.au MCP server require authentication?

No. We connected to publicdata.au without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the publicdata.au MCP server still maintained?

publicdata.au is still listed as active in the MCP registry. We last reached this channel on 3 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://publicdata.au/mcp
- Website: https://publicdata.au/agents/#mcp
- Changelog RSS feed: https://verifymcp.io/servers/au-publicdata-mcp/publicdata.xml
- Changelog JSON feed: https://verifymcp.io/servers/au-publicdata-mcp/publicdata.json
- HTML version of this page: https://verifymcp.io/servers/au-publicdata-mcp/publicdata