Server definition

Hash: sha256:230f1e2edd870994ece9595ac0dd35d407b264872cacd499c97660759a6a1154
What it is: What a remote MCP server returned when asked what it offers: 10 tools

The blob, as servednamed by its sha256

{
  "instructions": "Australian government open data, republished at URLs that never change. Find a dataset with search_datasets, read its fields with list_fields, then answer from the whole table with query_rows or count_rows. A dataset that is not served yet can be found with search_catalogue and voted for with upvote_dataset. Every answer names the version it came from and the publisher's attribution string. When you show the data to a person, use the attribution string, say it came from publicdata.au and link to the version the answer came from, https://publicdata.au/d/<slug>/v/<version>/. Use of this server is under https://publicdata.au/terms/.",
  "tools": [
    {
      "description": "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.\nField names and values for group_by and where come from list_fields.\nsum and avg need a numeric or true-or-false field. min and max take any field.\nversion must be one of the two newest versions.\nGroups come back largest first, and truncated means raise limit or narrow where. An unknown field or version returns an error naming it.\nEach call costs two of the 60 queries each address may make in 10 seconds.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "group_by": {
            "description": "Fields to group by, for example [\"crash_severity\"]. One total when absent.",
            "items": {
              "type": "string"
            },
            "maxItems": 3,
            "type": "array"
          },
          "limit": {
            "default": 100,
            "description": "Groups to return, 1 to 1000. 100 when absent.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "metric": {
            "default": "count",
            "description": "count, or sum, avg, min or max of a field written as sum.field_name. count when absent.",
            "type": "string"
          },
          "slug": {
            "description": "Dataset slug from search_datasets",
            "type": "string"
          },
          "version": {
            "description": "A version date, YYYY-MM-DD, from get_dataset. The newest version loaded for queries when absent.",
            "type": "string"
          },
          "where": {
            "additionalProperties": true,
            "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.",
            "type": "object"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "count_rows",
      "outputSchema": {
        "properties": {
          "attribution": {
            "description": "The publisher's attribution string, to show with any answer",
            "type": [
              "string",
              "null"
            ]
          },
          "group_by": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "groups": {
            "description": "One object per group, holding the group_by fields and the metric value, largest first",
            "items": {
              "type": "object"
            },
            "type": "array"
          },
          "matched": {
            "description": "Rows in the whole table that match where",
            "type": "integer"
          },
          "metric": {
            "type": "string"
          },
          "query": {
            "description": "The query API URL that gives the same answer",
            "type": "string"
          },
          "truncated": {
            "description": "True when more groups exist than limit",
            "type": "boolean"
          },
          "version": {
            "description": "The version answered",
            "type": [
              "string",
              "null"
            ]
          }
        },
        "required": [
          "version",
          "group_by",
          "metric",
          "groups",
          "truncated",
          "matched",
          "query"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "from": {
            "description": "Older version date, YYYY-MM-DD",
            "type": "string"
          },
          "slug": {
            "description": "Dataset slug from search_datasets",
            "type": "string"
          },
          "to": {
            "description": "Newer version date, YYYY-MM-DD",
            "type": "string"
          }
        },
        "required": [
          "slug",
          "from",
          "to"
        ],
        "type": "object"
      },
      "name": "diff_versions",
      "outputSchema": {
        "properties": {
          "added": {
            "type": "integer"
          },
          "added_keys": {
            "type": "array"
          },
          "changed": {
            "type": "integer"
          },
          "changed_keys": {
            "type": "array"
          },
          "dataset": {
            "type": "string"
          },
          "examples": {
            "description": "Up to ten changed rows, each with its key and the fields that changed from and to",
            "type": "array"
          },
          "from": {
            "description": "Older version date",
            "type": "string"
          },
          "key": {
            "description": "Key fields compared on. Empty when none is declared",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "note": {
            "description": "Present when no key is declared and only row counts are compared",
            "type": "string"
          },
          "removed": {
            "type": "integer"
          },
          "removed_keys": {
            "type": "array"
          },
          "rows_from": {
            "type": "integer"
          },
          "rows_to": {
            "type": "integer"
          },
          "schema": {
            "description": "Fields added, removed and retyped between the versions",
            "type": "object"
          },
          "to": {
            "description": "Newer version date",
            "type": "string"
          },
          "truncated": {
            "description": "True when a key list stops at its cap",
            "type": "boolean"
          },
          "unchanged": {
            "type": "integer"
          }
        },
        "required": [
          "dataset",
          "from",
          "to",
          "rows_from",
          "rows_to",
          "key",
          "schema"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.\nFor field names use list_fields. To answer a question from the rows use query_rows or count_rows, which need no download.\nslug is lowercase letters, digits and hyphens, the part after /d/ in a dataset page URL, such as au-road-deaths.\nThe 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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Dataset slug from search_datasets",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "get_dataset",
      "outputSchema": {
        "properties": {
          "datapackage": {
            "description": "The Frictionless data package: description, licence, attribution string, source, and resources with the URL, format and size of the whole file in each format",
            "type": "object"
          },
          "versions": {
            "description": "Every version with its date, the date its data is as at, row count, source hash and fetch time"
          }
        },
        "required": [
          "datapackage",
          "versions"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.\nTo add a vote use upvote_dataset. To read a dataset that is already served use search_datasets.\nVotes on catalogue records that no entry has claimed yet come back apart, under the vote key search_catalogue uses.\nThe whole backlog comes back in one answer, with no paging, and the call costs nothing against the rate limit.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "required": [],
        "type": "object"
      },
      "name": "list_backlog",
      "outputSchema": {
        "properties": {
          "catalogue_votes": {
            "description": "Votes on catalogue records no register entry has claimed yet, most first",
            "items": {
              "properties": {
                "vote": {
                  "description": "The record's vote key, which search_catalogue finds",
                  "type": "string"
                },
                "votes": {
                  "type": "integer"
                }
              },
              "required": [
                "vote",
                "votes"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "entries": {
            "description": "Register entries that are not live yet, most votes first",
            "items": {
              "properties": {
                "blocked_reason": {
                  "description": "Why a blocked entry cannot be built yet",
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "publisher": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "slug": {
                  "description": "The key upvote_dataset takes",
                  "type": "string"
                },
                "source": {
                  "description": "The publisher's own page for the data",
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "status": {
                  "description": "backlog and assessing wait for votes, building is under way, blocked cannot be built yet",
                  "enum": [
                    "backlog",
                    "assessing",
                    "building",
                    "blocked"
                  ],
                  "type": "string"
                },
                "summary": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "title": {
                  "type": "string"
                },
                "votes": {
                  "type": "integer"
                }
              },
              "required": [
                "slug",
                "title",
                "status",
                "votes"
              ],
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "entries",
          "catalogue_votes"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.\nslug is lowercase letters, digits and hyphens, the part after /d/ in a dataset page URL, such as au-road-deaths.\nThe 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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "Dataset slug from search_datasets",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "list_fields",
      "outputSchema": {
        "properties": {
          "attribution": {
            "description": "The publisher's attribution string, to show with any answer",
            "type": [
              "string",
              "null"
            ]
          },
          "fields": {
            "description": "Each field's name, type and publisher's description, with min and max for numbers and dates and values when it holds few",
            "items": {
              "properties": {
                "description": {
                  "type": "string"
                },
                "max": {},
                "min": {},
                "name": {
                  "type": "string"
                },
                "type": {
                  "type": "string"
                },
                "values": {
                  "type": "array"
                }
              },
              "required": [
                "name",
                "type"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "key": {
            "description": "Fields that identify a row, compared on by diff_versions. Empty when none is declared",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "licence": {
            "type": [
              "string",
              "null"
            ]
          },
          "partition_by": {
            "description": "Fields list_partitions accepts",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "publisher": {
            "type": [
              "string",
              "null"
            ]
          },
          "rows": {
            "description": "Rows in that version",
            "type": "integer"
          },
          "slug": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "version": {
            "description": "The version the fields describe",
            "type": "string"
          }
        },
        "required": [
          "slug",
          "version",
          "fields",
          "key",
          "partition_by"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "field": {
            "description": "A partition field named in the data package, for example crash_year or loc_local_government_area",
            "type": "string"
          },
          "slug": {
            "description": "Dataset slug from search_datasets",
            "type": "string"
          }
        },
        "required": [
          "slug",
          "field"
        ],
        "type": "object"
      },
      "name": "list_partitions",
      "outputSchema": {
        "properties": {
          "field": {
            "type": "string"
          },
          "partitions": {
            "description": "One entry per value: the value, its row count and the URL of a JSON file with every row holding it",
            "items": {
              "properties": {
                "rows": {
                  "type": "integer"
                },
                "url": {
                  "type": "string"
                },
                "value": {}
              },
              "required": [
                "value",
                "rows",
                "url"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "version_base": {
            "description": "The version these files belong to",
            "type": "string"
          }
        },
        "required": [
          "field",
          "version_base",
          "partitions"
        ],
        "type": "object"
      }
    },
    {
      "description": "Read individual rows of a served dataset, filtered across the whole table. For totals and breakdowns use count_rows.\nField names and values for where, select and order come from list_fields.\nFilters hold at most 90 values per call, and a list value cannot contain a comma.\nversion must be one of the two newest versions.\nPage with offset until next_offset is null. An unknown field or version returns an error naming it.\nEach call costs two of the 60 queries each address may make in 10 seconds.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "limit": {
            "default": 50,
            "description": "Rows to return, 1 to 500. 50 when absent.",
            "maximum": 500,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "Rows to skip. next_offset in each answer gives the next page.",
            "minimum": 0,
            "type": "integer"
          },
          "order": {
            "description": "field.asc or field.desc, comma-separated. The publisher's row order when absent.",
            "type": "string"
          },
          "select": {
            "description": "Fields to return. Every field when absent.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "slug": {
            "description": "Dataset slug from search_datasets",
            "type": "string"
          },
          "version": {
            "description": "A version date, YYYY-MM-DD, from get_dataset. The newest version loaded for queries when absent.",
            "type": "string"
          },
          "where": {
            "additionalProperties": true,
            "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.",
            "type": "object"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "query_rows",
      "outputSchema": {
        "properties": {
          "attribution": {
            "description": "The publisher's attribution string, to show with any answer",
            "type": [
              "string",
              "null"
            ]
          },
          "matched": {
            "description": "Rows in the whole table that match where",
            "type": "integer"
          },
          "next_offset": {
            "description": "offset for the next page, or null on the last",
            "type": [
              "integer",
              "null"
            ]
          },
          "query": {
            "description": "The query API URL that gives the same answer",
            "type": "string"
          },
          "rows": {
            "description": "The rows, with the fields in select or every field",
            "items": {
              "type": "object"
            },
            "type": "array"
          },
          "version": {
            "description": "The version answered",
            "type": [
              "string",
              "null"
            ]
          }
        },
        "required": [
          "version",
          "rows",
          "matched",
          "next_offset",
          "query"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.\nUse it when search_datasets finds nothing, to find where a dataset is published, or to pick one for upvote_dataset.\nquery matches every word against the title, summary and publisher, as search_datasets does.\nA page holds 20 records, those that can take a vote first. Pass next_offset as offset for the next page, up to 5000.\nEach call costs three of the 60 queries each address may make in 10 seconds.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "jurisdiction": {
            "description": "One government. All when absent.",
            "enum": [
              "cth",
              "nsw",
              "vic",
              "qld",
              "wa",
              "sa",
              "tas",
              "act",
              "nt"
            ],
            "type": "string"
          },
          "offset": {
            "default": 0,
            "description": "Rows to skip. next_offset in each answer gives the next page.",
            "maximum": 5000,
            "minimum": 0,
            "type": "integer"
          },
          "query": {
            "description": "Words from a title, description or publisher",
            "type": "string"
          },
          "votable_only": {
            "default": false,
            "description": "Leave out records that cannot take a vote",
            "type": "boolean"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_catalogue",
      "outputSchema": {
        "properties": {
          "catalogue_read": {
            "description": "Date the portal lists were read",
            "type": "string"
          },
          "next_offset": {
            "description": "offset for the next page, or null on the last",
            "type": [
              "integer",
              "null"
            ]
          },
          "records": {
            "type": "integer"
          },
          "rows": {
            "items": {
              "properties": {
                "formats": {
                  "type": "string"
                },
                "id": {
                  "type": "string"
                },
                "jur": {
                  "type": "string"
                },
                "licence": {
                  "type": "string"
                },
                "modified": {
                  "type": "string"
                },
                "page": {
                  "type": "string"
                },
                "publisher": {
                  "type": "string"
                },
                "publisher_page": {
                  "type": "string"
                },
                "reason": {
                  "description": "Why a closed record cannot be built",
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "state": {
                  "description": "votable or chosen takes a vote, served is already readable, closed cannot be built",
                  "enum": [
                    "votable",
                    "chosen",
                    "served",
                    "closed"
                  ],
                  "type": "string"
                },
                "summary": {
                  "type": "string"
                },
                "title": {
                  "type": "string"
                },
                "url": {
                  "description": "The record on the publisher's portal",
                  "type": "string"
                },
                "vote": {
                  "description": "The key upvote_dataset takes",
                  "type": "string"
                }
              },
              "required": [
                "id",
                "title",
                "state",
                "vote"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "total": {
            "description": "Records that match",
            "type": "integer"
          }
        },
        "required": [
          "catalogue_read",
          "rows"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.\nEvery 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.\nUp to 50 matches come back in one answer, with no paging. If nothing matches, try fewer or broader words, then search_catalogue.\nEach call costs one of the 60 queries each address may make in 10 seconds.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "query": {
            "description": "Words from a title, publisher or field name",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_datasets",
      "outputSchema": {
        "properties": {
          "results": {
            "description": "Matches, best first when the search index is loaded",
            "items": {
              "properties": {
                "latest": {
                  "description": "URL of the newest version's whole file",
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "licence": {
                  "description": "Licence id, such as CC-BY-4.0",
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "page": {
                  "description": "The dataset page on publicdata.au",
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "publisher": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "slug": {
                  "description": "The id every other tool takes",
                  "type": "string"
                },
                "title": {
                  "type": "string"
                }
              },
              "required": [
                "slug",
                "title"
              ],
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "results"
        ],
        "type": "object"
      }
    },
    {
      "description": "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.\nslug is a vote key from search_catalogue, such as act-3u5a-ve4j, or a list_backlog slug.\nA dataset that is served, being built or closed returns an error saying it is not open for votes.\nNo 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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "slug": {
            "description": "The vote key of a search_catalogue row, or a slug from /backlog.json",
            "type": "string"
          }
        },
        "required": [
          "slug"
        ],
        "type": "object"
      },
      "name": "upvote_dataset",
      "outputSchema": {
        "properties": {
          "slug": {
            "type": "string"
          },
          "votes": {
            "description": "The dataset's vote total after this call",
            "type": "integer"
          }
        },
        "required": [
          "slug",
          "votes"
        ],
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:230f1e2edd870994ece9595ac0dd35d407b264872cacd499c97660759a6a1154 | sha256sum