publicdata.au
Search, filter, count and sum Australian government open data, with every version kept.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~2,125Token（工具定義）
~2.3 KB典型回應大小
中等的注意力影響（128k 上下文的 1.66%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"mcp": {
"url": "https://publicdata.au/mcp"
}
}
}遠端端點
https://publicdata.au/mcpstreamable-http它能做什麼
工具清單
工具（8）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search_datasets(query)
Find datasets on publicdata.au by title, publisher or field name. Returns slug, title, publisher, licence, dataset page and the latest download URL.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Words from a title, publisher or field name"
}
},
"required": [
"query"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"title": {
"type": "string"
},
"publisher": {
"type": [
"string",
"null"
]
},
"licence": {
"type": [
"string",
"null"
]
},
"page": {
"type": [
"string",
"null"
]
},
"latest": {
"type": [
"string",
"null"
]
}
},
"required": [
"slug",
"title"
]
}
}
},
"required": [
"results"
]
}🟢get_dataset(slug)
Read one dataset: its Frictionless data package (fields, types, licence, attribution, download URLs) and every version.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Dataset slug from search_datasets"
}
},
"required": [
"slug"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"datapackage": {
"type": "object"
},
"versions": {}
},
"required": [
"datapackage",
"versions"
]
}🟢list_partitions(slug, field)
List the per-value download files of a dataset for one partition field, with the row count and URL of each, to download a slice of the data.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Dataset slug from search_datasets"
},
"field": {
"type": "string",
"description": "A partition field named in the data package, for example crash_year or loc_local_government_area"
}
},
"required": [
"slug",
"field"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"field": {
"type": "string"
},
"version_base": {
"type": "string"
},
"partitions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"value": {},
"rows": {
"type": "integer"
},
"url": {
"type": "string"
}
},
"required": [
"value",
"rows",
"url"
]
}
}
},
"required": [
"field",
"version_base",
"partitions"
]
}🟢query_rows(slug, where, select, order, limit, ...)
Return rows from a dataset, filtered across the whole table by the query API. Returns up to limit rows, the number of rows that match, the offset of the next page, the version answered and the attribution string.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Dataset slug from search_datasets"
},
"where": {
"type": "object",
"description": "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 case-insensitive match where * is the wildcard. A blank cell never matches a scalar, a list or a range.",
"additionalProperties": true
},
"select": {
"type": "array",
"items": {
"type": "string"
},
"description": "Fields to return. Every field when absent."
},
"order": {
"type": "string",
"description": "field.asc or field.desc, comma-separated. The publisher's row order when absent."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500,
"default": 50,
"description": "Rows to return, 1 to 500. 50 when absent."
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0,
"description": "Rows to skip. next_offset in each answer gives the next page."
},
"version": {
"type": "string",
"description": "A version date, YYYY-MM-DD, from get_dataset. The newest version loaded for queries when absent."
}
},
"required": [
"slug"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"version": {
"type": [
"string",
"null"
]
},
"rows": {
"type": "array",
"items": {
"type": "object"
}
},
"matched": {
"type": "integer"
},
"next_offset": {
"type": [
"integer",
"null"
]
},
"query": {
"type": "string"
},
"attribution": {
"type": [
"string",
"null"
]
}
},
"required": [
"version",
"rows",
"matched",
"next_offset",
"query"
]
}🟢count_rows(slug, group_by, metric, where, limit, ...)
Count rows in a dataset, or sum, average, min or max a field, grouped by up to three fields and filtered across the whole table by the query API. Returns groups sorted from largest, the number of rows that match, the version answered and the attribution string.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Dataset slug from search_datasets"
},
"group_by": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 3,
"description": "Fields to group by, for example [\"crash_severity\"]. One total when absent."
},
"metric": {
"type": "string",
"default": "count",
"description": "count, or sum, avg, min or max of a field written as sum.field_name. count when absent."
},
"where": {
"type": "object",
"description": "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 case-insensitive match where * is the wildcard. A blank cell never matches a scalar, a list or a range.",
"additionalProperties": true
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 1000,
"default": 100,
"description": "Groups to return, 1 to 1000. 100 when absent."
},
"version": {
"type": "string",
"description": "A version date, YYYY-MM-DD, from get_dataset. The newest version loaded for queries when absent."
}
},
"required": [
"slug"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"version": {
"type": [
"string",
"null"
]
},
"group_by": {
"type": "array",
"items": {
"type": "string"
}
},
"metric": {
"type": "string"
},
"groups": {
"type": "array",
"items": {
"type": "object"
}
},
"truncated": {
"type": "boolean"
},
"matched": {
"type": "integer"
},
"query": {
"type": "string"
},
"attribution": {
"type": [
"string",
"null"
]
}
},
"required": [
"version",
"group_by",
"metric",
"groups",
"truncated",
"matched",
"query"
]
}🟢diff_versions(slug, from, to)
Compare two versions of a dataset by its key: rows added, removed and changed.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Dataset slug from search_datasets"
},
"from": {
"type": "string",
"description": "Older version date, YYYY-MM-DD"
},
"to": {
"type": "string",
"description": "Newer version date, YYYY-MM-DD"
}
},
"required": [
"slug",
"from",
"to"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object"
}🟢search_catalogue(query, jurisdiction, votable_only)
Search every dataset on Australia's government portals. A row's state says whether it can take a vote; pass its vote key to vote.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Words from a title, description or publisher"
},
"jurisdiction": {
"type": "string",
"enum": [
"cth",
"nsw",
"vic",
"qld",
"wa",
"sa",
"tas",
"act",
"nt"
],
"description": "One government. All when absent."
},
"votable_only": {
"type": "boolean",
"default": false,
"description": "Leave out records that cannot take a vote"
}
},
"required": [
"query"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"catalogue_read": {
"type": "string"
},
"records": {
"type": "integer"
},
"total": {
"type": "integer"
},
"next_offset": {
"type": [
"integer",
"null"
]
},
"rows": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"publisher": {
"type": "string"
},
"publisher_page": {
"type": "string"
},
"jur": {
"type": "string"
},
"url": {
"type": "string"
},
"licence": {
"type": "string"
},
"formats": {
"type": "string"
},
"modified": {
"type": "string"
},
"state": {
"type": "string",
"enum": [
"votable",
"chosen",
"served",
"closed"
]
},
"vote": {
"type": "string"
},
"page": {
"type": "string"
},
"reason": {
"type": [
"string",
"null"
]
}
},
"required": [
"id",
"title",
"state",
"vote"
]
}
}
},
"required": [
"catalogue_read",
"rows"
]
}🟡vote(slug)
Add one vote so a dataset is built sooner. No identity is recorded, and each browser counts once a day.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The vote key of a search_catalogue row, or a backlog slug from /backlog.json"
}
},
"required": [
"slug"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"votes": {
"type": "integer"
}
},
"required": [
"slug",
"votes"
]
}社群
證據
近期觀測
已驗證未記錄版本8 個工具