ABS Data (observed) is an MCP server published by io.github.SamJB123, hosted at abs-data-front-door.aicolab.workers.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 8 tools, including search_tables, describe_table, search_options, get_data, search.
Australian Bureau of Statistics data: 1,227 tables, offering only options confirmed to serve data
Nothing else in the archive shares these values.
Inferred from the host name and headers: what a server runs on, not who runs it.
Find ABS statistical tables (dataflows) by topic words, geography level or frequency. Matches table names, topics and dimension names, and also option labels inside dimensions — a search for 'rent' finds CPI through its INDEX option 'Rents' and reports the match in matchedOptions. Census tables published at several geography levels are collapsed to one result with familyGeographies listing the others (use the geography filter to pick one). Every result has data. When the person describes a situation rather than a dataset, search for each thing it depends on (prices, wages, rents, population...). Start here, then describe_table.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Free text over ids, names, topics, dimensions |
| frequency | string | A annual, S semi-annual, Q quarterly, M monthly, W weekly, D daily |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| geography | string | Restrict to a geography level, e.g. SA2, LGA |
{
"name": "search_tables",
"title": "Search ABS tables",
"description": "Find ABS statistical tables (dataflows) by topic words, geography level or frequency. Matches table names, topics and dimension names, and also option labels inside dimensions — a search for 'rent' finds CPI through its INDEX option 'Rents' and reports the match in matchedOptions. Census tables published at several geography levels are collapsed to one result with familyGeographies listing the others (use the geography filter to pick one). Every result has data. When the person describes a situation rather than a dataset, search for each thing it depends on (prices, wages, rents, population...). Start here, then describe_table.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Free text over ids, names, topics, dimensions"
},
"frequency": {
"enum": [
"A",
"S",
"Q",
"M",
"W",
"D"
],
"type": "string",
"description": "A annual, S semi-annual, Q quarterly, M monthly, W weekly, D daily"
},
"geography": {
"type": "string",
"description": "Restrict to a geography level, e.g. SA2, LGA"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"results",
"total",
"provenance"
],
"properties": {
"total": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name",
"seriesCount",
"frequencies",
"coverage",
"density",
"family",
"geography",
"dimensions",
"topics"
],
"properties": {
"id": {
"type": "string",
"description": "Dataflow id, e.g. CPI"
},
"name": {
"type": [
"string",
"null"
]
},
"family": {
"type": [
"string",
"null"
],
"description": "Census table family, e.g. C21_G01"
},
"topics": {
"type": "array",
"items": {
"type": "string"
}
},
"density": {
"type": [
"number",
"null"
]
},
"coverage": {
"type": "object",
"required": [
"from",
"to"
],
"properties": {
"to": {
"type": [
"string",
"null"
],
"description": "Latest observed period"
},
"from": {
"type": [
"string",
"null"
],
"description": "Earliest observed period, e.g. 2002-Q1"
}
},
"additionalProperties": false
},
"geography": {
"type": [
"string",
"null"
],
"description": "Geography level for family members, e.g. LGA"
},
"dimensions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Dimension ids in key order"
},
"description": {
"type": [
"string",
"null"
],
"description": "ABS's own description, trimmed"
},
"frequencies": {
"type": "array",
"items": {
"enum": [
"A",
"S",
"Q",
"M",
"W",
"D"
],
"type": "string",
"description": "A annual, S semi-annual, Q quarterly, M monthly, W weekly, D daily"
}
},
"seriesCount": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Series confirmed to exist by retrieval"
},
"matchedOptions": {
"type": "array",
"items": {
"type": "object",
"required": [
"dimension",
"code",
"label"
],
"properties": {
"code": {
"type": "string"
},
"label": {
"type": [
"string",
"null"
]
},
"dimension": {
"type": "string"
}
},
"additionalProperties": false
}
},
"familyGeographies": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
}
},
"provenance": {
"type": "object",
"required": [
"runId",
"observedAt"
],
"properties": {
"runId": {
"type": "string"
},
"observedAt": {
"type": "string"
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
"annotations": {
"title": "Search ABS tables",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}A table's dimensions in key order, its coverage dates, and its options. Dimensions with up to 64 options list them inline with labels; larger ones (geography, occupations) say how many and are searchable with search_options.
| Parameter | Type | Description |
|---|---|---|
| table * | string | Dataflow id, e.g. CPI |
{
"name": "describe_table",
"title": "Describe a table",
"description": "A table's dimensions in key order, its coverage dates, and its options. Dimensions with up to 64 options list them inline with labels; larger ones (geography, occupations) say how many and are searchable with search_options.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"table"
],
"properties": {
"table": {
"type": "string",
"minLength": 1,
"description": "Dataflow id, e.g. CPI"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"table",
"dimensions",
"keyFormat",
"exampleUrl",
"provenance"
],
"properties": {
"table": {
"type": "object",
"required": [
"id",
"name",
"seriesCount",
"frequencies",
"coverage",
"density",
"family",
"geography",
"dimensions",
"topics"
],
"properties": {
"id": {
"type": "string",
"description": "Dataflow id, e.g. CPI"
},
"name": {
"type": [
"string",
"null"
]
},
"family": {
"type": [
"string",
"null"
],
"description": "Census table family, e.g. C21_G01"
},
"topics": {
"type": "array",
"items": {
"type": "string"
}
},
"density": {
"type": [
"number",
"null"
]
},
"coverage": {
"type": "object",
"required": [
"from",
"to"
],
"properties": {
"to": {
"type": [
"string",
"null"
],
"description": "Latest observed period"
},
"from": {
"type": [
"string",
"null"
],
"description": "Earliest observed period, e.g. 2002-Q1"
}
},
"additionalProperties": false
},
"geography": {
"type": [
"string",
"null"
],
"description": "Geography level for family members, e.g. LGA"
},
"dimensions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Dimension ids in key order"
},
"description": {
"type": [
"string",
"null"
],
"description": "ABS's own description, trimmed"
},
"frequencies": {
"type": "array",
"items": {
"enum": [
"A",
"S",
"Q",
"M",
"W",
"D"
],
"type": "string",
"description": "A annual, S semi-annual, Q quarterly, M monthly, W weekly, D daily"
}
},
"seriesCount": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Series confirmed to exist by retrieval"
},
"matchedOptions": {
"type": "array",
"items": {
"type": "object",
"required": [
"dimension",
"code",
"label"
],
"properties": {
"code": {
"type": "string"
},
"label": {
"type": [
"string",
"null"
]
},
"dimension": {
"type": "string"
}
},
"additionalProperties": false
}
},
"familyGeographies": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"keyFormat": {
"type": "string",
"description": "Dimension ids joined by '.', the order a selection is serialised in"
},
"dimensions": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"position",
"codelist",
"optionCount"
],
"properties": {
"id": {
"type": "string"
},
"options": {
"type": "array",
"items": {
"type": "object",
"required": [
"code",
"label"
],
"properties": {
"code": {
"type": "string"
},
"label": {
"type": [
"string",
"null"
]
},
"parent": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
},
"codelist": {
"type": [
"string",
"null"
]
},
"position": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"optionCount": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"determinedBy": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
},
"exampleUrl": {
"type": "string",
"format": "uri"
},
"provenance": {
"type": "object",
"required": [
"runId",
"observedAt"
],
"properties": {
"runId": {
"type": "string"
},
"observedAt": {
"type": "string"
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
"annotations": {
"title": "Describe a table",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Find option codes by label text within one dimension of one table — e.g. a suburb name in a geography dimension. Returns codes to use in get_data's select.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string | Match against option codes and labels |
| table * | string | |
| dimension * | string |
{
"name": "search_options",
"title": "Search a dimension's options",
"description": "Find option codes by label text within one dimension of one table — e.g. a suburb name in a geography dimension. Returns codes to use in get_data's select.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"table",
"dimension",
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Match against option codes and labels"
},
"table": {
"type": "string",
"minLength": 1
},
"dimension": {
"type": "string",
"minLength": 1
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"options",
"total",
"provenance"
],
"properties": {
"total": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"options": {
"type": "array",
"items": {
"type": "object",
"required": [
"code",
"label"
],
"properties": {
"code": {
"type": "string"
},
"label": {
"type": [
"string",
"null"
]
},
"parent": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
},
"provenance": {
"type": "object",
"required": [
"runId",
"observedAt"
],
"properties": {
"runId": {
"type": "string"
},
"observedAt": {
"type": "string"
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
"annotations": {
"title": "Search a dimension's options",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch observations. `select` maps dimension ids to option codes or labels (several allowed); omitted dimensions match everything. The selection is verified live against ABS before fetching, so a call that succeeds always returns real data. Returns up to maxRows observations (default 500, most recent 12 periods per series unless a period range is given), a summary, and the URL for the complete pull. If an option or combination does not exist you are asked to choose from the valid ones.
| Parameter | Type | Description |
|---|---|---|
| lastN | integer | Most recent N observations per series; default 12 when no period is given |
| table * | string | |
| firstN | integer | |
| select | object | dimension id -> option code or label (or several). Omitted dimensions match everything. |
| maxRows | integer | Cap on returned observations |
| endPeriod | string | |
| startPeriod | string | e.g. 2020, 2020-Q1, 2020-03 |
{
"name": "get_data",
"title": "Get data",
"description": "Fetch observations. `select` maps dimension ids to option codes or labels (several allowed); omitted dimensions match everything. The selection is verified live against ABS before fetching, so a call that succeeds always returns real data. Returns up to maxRows observations (default 500, most recent 12 periods per series unless a period range is given), a summary, and the URL for the complete pull. If an option or combination does not exist you are asked to choose from the valid ones.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"table"
],
"properties": {
"lastN": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Most recent N observations per series; default 12 when no period is given"
},
"table": {
"type": "string",
"minLength": 1
},
"firstN": {
"type": "integer",
"maximum": 1000,
"minimum": 1
},
"select": {
"type": "object",
"default": {},
"description": "dimension id -> option code or label (or several). Omitted dimensions match everything.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"minItems": 1
}
]
}
},
"maxRows": {
"type": "integer",
"default": 500,
"maximum": 2000,
"minimum": 1,
"description": "Cap on returned observations"
},
"endPeriod": {
"type": "string"
},
"startPeriod": {
"type": "string",
"description": "e.g. 2020, 2020-Q1, 2020-03"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"table",
"key",
"seriesMatched",
"rows",
"rowsReturned",
"truncated",
"periodRange",
"fullDataUrl",
"availabilityUrl",
"provenance"
],
"properties": {
"key": {
"type": "string",
"description": "The resolved selection as an SDMX key"
},
"rows": {
"type": "array",
"items": {
"type": "object",
"required": [
"series",
"period",
"value"
],
"properties": {
"unit": {
"type": [
"string",
"null"
]
},
"value": {
"type": [
"number",
"null"
]
},
"period": {
"type": "string"
},
"series": {
"type": "string",
"description": "The series key, e.g. 1.10001.10.50.Q"
},
"status": {
"type": [
"string",
"null"
]
}
},
"additionalProperties": false
}
},
"table": {
"type": "string"
},
"truncated": {
"type": "boolean"
},
"provenance": {
"type": "object",
"required": [
"runId",
"observedAt"
],
"properties": {
"runId": {
"type": "string"
},
"observedAt": {
"type": "string"
}
},
"additionalProperties": false
},
"fullDataUrl": {
"type": "string",
"format": "uri"
},
"periodRange": {
"type": "object",
"required": [
"from",
"to"
],
"properties": {
"to": {
"type": [
"string",
"null"
],
"description": "Latest observed period"
},
"from": {
"type": [
"string",
"null"
],
"description": "Earliest observed period, e.g. 2002-Q1"
}
},
"additionalProperties": false
},
"rowsReturned": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"seriesMatched": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"availabilityUrl": {
"type": "string",
"format": "uri"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get data",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Run JavaScript against the whole catalogue document — every table, its dimensions, coverage and small-dimension options — in an isolated sandbox with no network. Use it to answer questions the fixed verbs make awkward: 'which tables have both an SA2 geography and a quarterly frequency?', 'list every dimension name and how often it appears', 'find codelists whose labels mention rent'. Your code runs inside an async function with `catalogue` in scope; `return` a JSON-serialisable value; console.log output is captured. // The `catalogue` object available in search(): interface Catalogue { provenance: { runId: string; observedAt: string }; corpus: { tables: number; seriesConfirmed: number; seriesImpliedByMetadata: number; density: number }; tables: Record<string, { // keyed by table id, e.g. catalogue.tables.CPI id: string; name: string|null; description: string|null; seriesCount: number; frequencies: string[]; coverage: { from: string|null; to: string|null }; density: number|null; family: string|null; geography: string|null; topics: string[]; dimensions: { id: string; position: number; codelist: string|null; optionCount: number; literal: boolean }[]; }>; options: { literal: Record<string, Record<string, string|null>>; // codelist id -> { code: label } for small codelists (<=64 options) branded: Record<string, number>; // large codelists -> option count (use abs.searchOptions in execute) }; }
| Parameter | Type | Description |
|---|---|---|
| code * | string | JavaScript. `catalogue` is in scope. Must return a value. |
{
"name": "search",
"title": "Search the catalogue by writing code",
"description": "Run JavaScript against the whole catalogue document — every table, its dimensions, coverage and small-dimension options — in an isolated sandbox with no network. Use it to answer questions the fixed verbs make awkward: 'which tables have both an SA2 geography and a quarterly frequency?', 'list every dimension name and how often it appears', 'find codelists whose labels mention rent'. Your code runs inside an async function with `catalogue` in scope; `return` a JSON-serialisable value; console.log output is captured.\n\n// The `catalogue` object available in search():\ninterface Catalogue {\n provenance: { runId: string; observedAt: string };\n corpus: { tables: number; seriesConfirmed: number; seriesImpliedByMetadata: number; density: number };\n tables: Record<string, { // keyed by table id, e.g. catalogue.tables.CPI\n id: string; name: string|null; description: string|null; seriesCount: number;\n frequencies: string[]; coverage: { from: string|null; to: string|null }; density: number|null;\n family: string|null; geography: string|null; topics: string[];\n dimensions: { id: string; position: number; codelist: string|null; optionCount: number; literal: boolean }[];\n }>;\n options: {\n literal: Record<string, Record<string, string|null>>; // codelist id -> { code: label } for small codelists (<=64 options)\n branded: Record<string, number>; // large codelists -> option count (use abs.searchOptions in execute)\n };\n}",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"maxLength": 20000,
"minLength": 1,
"description": "JavaScript. `catalogue` is in scope. Must return a value."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"ok",
"logs"
],
"properties": {
"ok": {
"type": "boolean"
},
"logs": {
"type": "array",
"items": {
"type": "string"
}
},
"error": {
"type": "string"
},
"result": {},
"truncated": {
"type": "boolean"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Search the catalogue by writing code",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Run JavaScript in an isolated sandbox whose only capability is `abs`, a client with the same four verbs as this server (searchTables, describeTable, searchOptions, getData) and the same guarantees: every selection is verified against ABS before fetching. Use it for multi-series or multi-table analysis — fetch several series, compute growth rates, rank capitals, join tables — and `return` only the computed result, so large payloads never reach the conversation. No network beyond `abs`. Budgets: 10s CPU, 50 calls, 25s wall clock, 200KB result. Your code runs inside an async function; use `await`; console.log is captured. // The `abs` object available in execute(): interface Abs { searchTables(input: { query?: string; geography?: string; frequency?: "A"|"S"|"Q"|"M"|"W"|"D"; limit?: number }): Promise<{ results: TableSummary[]; total: number }>; describeTable(table: string): Promise<{ table: TableSummary; dimensions: { id: string; position: number; optionCount: number; options?: { code: string; label: string|null }[] }[]; keyFormat: string }>; searchOptions(input: { table: string; dimension: string; query: string; limit?: number }): Promise<{ options: { code: string; label: string|null; parent?: string|null }[]; total: number }>; getData(input: { table: string; select?: Record<string, string|string[]>; startPeriod?: string; endPeriod?: string; lastN?: number; firstN?: number; maxRows?: number }): Promise<{ key: string; rows: { series: string; period: string; value: number|null; unit?: string|null }[]; rowsReturned: number; truncated: boolean; seriesMatched: number; fullDataUrl: string }>; } interface TableSummary { id: string; name: string|null; seriesCount: number; frequencies: string[]; coverage: { from: string|null; to: string|null }; dimensions: string[]; family: string|null; geography: string|null; matchedOptions?: { dimension: string; code: string; label: string|null }[] } // getData throws an Error whose message is JSON: { reason, dimension, message, validOptions?, alternatives? } — catch it, read validOptions, correct and retry.
| Parameter | Type | Description |
|---|---|---|
| code * | string | JavaScript. `abs` is in scope. Must return a value. |
{
"name": "execute",
"title": "Fetch and analyse data by writing code",
"description": "Run JavaScript in an isolated sandbox whose only capability is `abs`, a client with the same four verbs as this server (searchTables, describeTable, searchOptions, getData) and the same guarantees: every selection is verified against ABS before fetching. Use it for multi-series or multi-table analysis — fetch several series, compute growth rates, rank capitals, join tables — and `return` only the computed result, so large payloads never reach the conversation. No network beyond `abs`. Budgets: 10s CPU, 50 calls, 25s wall clock, 200KB result. Your code runs inside an async function; use `await`; console.log is captured.\n\n// The `abs` object available in execute():\ninterface Abs {\n searchTables(input: { query?: string; geography?: string; frequency?: \"A\"|\"S\"|\"Q\"|\"M\"|\"W\"|\"D\"; limit?: number }):\n Promise<{ results: TableSummary[]; total: number }>;\n describeTable(table: string):\n Promise<{ table: TableSummary; dimensions: { id: string; position: number; optionCount: number; options?: { code: string; label: string|null }[] }[]; keyFormat: string }>;\n searchOptions(input: { table: string; dimension: string; query: string; limit?: number }):\n Promise<{ options: { code: string; label: string|null; parent?: string|null }[]; total: number }>;\n getData(input: { table: string; select?: Record<string, string|string[]>; startPeriod?: string; endPeriod?: string; lastN?: number; firstN?: number; maxRows?: number }):\n Promise<{ key: string; rows: { series: string; period: string; value: number|null; unit?: string|null }[]; rowsReturned: number; truncated: boolean; seriesMatched: number; fullDataUrl: string }>;\n}\ninterface TableSummary { id: string; name: string|null; seriesCount: number; frequencies: string[]; coverage: { from: string|null; to: string|null }; dimensions: string[]; family: string|null; geography: string|null; matchedOptions?: { dimension: string; code: string; label: string|null }[] }\n// getData throws an Error whose message is JSON: { reason, dimension, message, validOptions?, alternatives? } — catch it, read validOptions, correct and retry.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"maxLength": 20000,
"minLength": 1,
"description": "JavaScript. `abs` is in scope. Must return a value."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"ok",
"logs"
],
"properties": {
"ok": {
"type": "boolean"
},
"logs": {
"type": "array",
"items": {
"type": "string"
}
},
"error": {
"type": "string"
},
"result": {},
"truncated": {
"type": "boolean"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Fetch and analyse data by writing code",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Open a feedback form for the person, prefilled with your draft, so they can report a problem or suggest an improvement to this ABS connector — or flag something wrong in ABS's own data. Use it whenever the person wants to give feedback, or agrees when you offer after something went wrong. Fill in what you know from the conversation: kind, a one-line summary in their words, details, and the tool, table, selection and error involved. Never include personal information about anyone, and never fill in a contact email the person did not give you. This tool sends nothing: on hosts that show interactive views the person reviews, edits and sends the form themselves; elsewhere, follow the `next` field.
| Parameter | Type | Description |
|---|---|---|
| kind | string | bug: something broke; data: a figure or label looks wrong; missing: an expected table or option is absent; idea: an improvement; docs: unclear guidance; praise: it worked well; other |
| tool | string | The tool involved, e.g. get_data |
| about | string | connector: this connector or its site; abs: ABS's own data or API (so it can be passed on to ABS) |
| error | string | The error reason or message returned, if any |
| table | string | The ABS table id involved, e.g. CPI |
| contact | string | Only if the person chose to give an email address for a reply. Never guess or fill one in. |
| details | string | What happened and what was expected. No personal information about anyone. |
| summary | string | One line, in the person's own words |
| assistant | string | The AI tool in use, e.g. Claude, ChatGPT, Copilot |
| selection | string | The selection or query involved, as JSON or the SDMX key |
| shareWithAbs | boolean | Only true if the person agreed this may be passed on to ABS, contact address included |
{
"name": "feedback_form",
"title": "Open a feedback form",
"description": "Open a feedback form for the person, prefilled with your draft, so they can report a problem or suggest an improvement to this ABS connector — or flag something wrong in ABS's own data. Use it whenever the person wants to give feedback, or agrees when you offer after something went wrong. Fill in what you know from the conversation: kind, a one-line summary in their words, details, and the tool, table, selection and error involved. Never include personal information about anyone, and never fill in a contact email the person did not give you. This tool sends nothing: on hosts that show interactive views the person reviews, edits and sends the form themselves; elsewhere, follow the `next` field.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"kind": {
"enum": [
"bug",
"data",
"missing",
"idea",
"docs",
"praise",
"other"
],
"type": "string",
"description": "bug: something broke; data: a figure or label looks wrong; missing: an expected table or option is absent; idea: an improvement; docs: unclear guidance; praise: it worked well; other"
},
"tool": {
"type": "string",
"maxLength": 64,
"description": "The tool involved, e.g. get_data"
},
"about": {
"enum": [
"connector",
"abs"
],
"type": "string",
"default": "connector",
"description": "connector: this connector or its site; abs: ABS's own data or API (so it can be passed on to ABS)"
},
"error": {
"type": "string",
"maxLength": 1000,
"description": "The error reason or message returned, if any"
},
"table": {
"type": "string",
"maxLength": 64,
"description": "The ABS table id involved, e.g. CPI"
},
"contact": {
"type": "string",
"format": "email",
"pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
"maxLength": 254,
"description": "Only if the person chose to give an email address for a reply. Never guess or fill one in."
},
"details": {
"type": "string",
"maxLength": 5000,
"description": "What happened and what was expected. No personal information about anyone."
},
"summary": {
"type": "string",
"maxLength": 200,
"minLength": 3,
"description": "One line, in the person's own words"
},
"assistant": {
"type": "string",
"maxLength": 80,
"description": "The AI tool in use, e.g. Claude, ChatGPT, Copilot"
},
"selection": {
"type": "string",
"maxLength": 1000,
"description": "The selection or query involved, as JSON or the SDMX key"
},
"shareWithAbs": {
"type": "boolean",
"default": false,
"description": "Only true if the person agreed this may be passed on to ABS, contact address included"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"draft",
"next"
],
"properties": {
"next": {
"type": "string"
},
"draft": {
"type": "object",
"properties": {
"kind": {
"enum": [
"bug",
"data",
"missing",
"idea",
"docs",
"praise",
"other"
],
"type": "string",
"description": "bug: something broke; data: a figure or label looks wrong; missing: an expected table or option is absent; idea: an improvement; docs: unclear guidance; praise: it worked well; other"
},
"tool": {
"type": "string",
"maxLength": 64,
"description": "The tool involved, e.g. get_data"
},
"about": {
"enum": [
"connector",
"abs"
],
"type": "string",
"default": "connector",
"description": "connector: this connector or its site; abs: ABS's own data or API (so it can be passed on to ABS)"
},
"error": {
"type": "string",
"maxLength": 1000,
"description": "The error reason or message returned, if any"
},
"table": {
"type": "string",
"maxLength": 64,
"description": "The ABS table id involved, e.g. CPI"
},
"contact": {
"type": "string",
"format": "email",
"pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
"maxLength": 254,
"description": "Only if the person chose to give an email address for a reply. Never guess or fill one in."
},
"details": {
"type": "string",
"maxLength": 5000,
"description": "What happened and what was expected. No personal information about anyone."
},
"summary": {
"type": "string",
"maxLength": 200,
"minLength": 3,
"description": "One line, in the person's own words"
},
"assistant": {
"type": "string",
"maxLength": 80,
"description": "The AI tool in use, e.g. Claude, ChatGPT, Copilot"
},
"selection": {
"type": "string",
"maxLength": 1000,
"description": "The selection or query involved, as JSON or the SDMX key"
},
"shareWithAbs": {
"type": "boolean",
"default": false,
"description": "Only true if the person agreed this may be passed on to ABS, contact address included"
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
"annotations": {
"title": "Open a feedback form",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Send feedback about this ABS connector (or a report about ABS's own data) to its maintainers. Only call this after the person has seen the exact text and said to send it — prefer feedback_form, which lets them edit it first. Use about='abs' for wrong figures or broken behaviour in ABS's own data or API; set shareWithAbs only if the person agreed it may be passed on to ABS. Never include personal information about anyone, and include a contact email only if the person gave one for a reply. Returns a reference like FB-7Q2K9C to give the person.
| Parameter | Type | Description |
|---|---|---|
| kind * | string | bug: something broke; data: a figure or label looks wrong; missing: an expected table or option is absent; idea: an improvement; docs: unclear guidance; praise: it worked well; other |
| tool | string | The tool involved, e.g. get_data |
| about | string | connector: this connector or its site; abs: ABS's own data or API (so it can be passed on to ABS) |
| error | string | The error reason or message returned, if any |
| table | string | The ABS table id involved, e.g. CPI |
| contact | string | Only if the person chose to give an email address for a reply. Never guess or fill one in. |
| details | string | What happened and what was expected. No personal information about anyone. |
| summary * | string | One line, in the person's own words |
| assistant | string | The AI tool in use, e.g. Claude, ChatGPT, Copilot |
| selection | string | The selection or query involved, as JSON or the SDMX key |
| shareWithAbs | boolean | Only true if the person agreed this may be passed on to ABS, contact address included |
{
"name": "submit_feedback",
"title": "Send feedback to the maintainers",
"description": "Send feedback about this ABS connector (or a report about ABS's own data) to its maintainers. Only call this after the person has seen the exact text and said to send it — prefer feedback_form, which lets them edit it first. Use about='abs' for wrong figures or broken behaviour in ABS's own data or API; set shareWithAbs only if the person agreed it may be passed on to ABS. Never include personal information about anyone, and include a contact email only if the person gave one for a reply. Returns a reference like FB-7Q2K9C to give the person.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"kind",
"summary"
],
"properties": {
"kind": {
"enum": [
"bug",
"data",
"missing",
"idea",
"docs",
"praise",
"other"
],
"type": "string",
"description": "bug: something broke; data: a figure or label looks wrong; missing: an expected table or option is absent; idea: an improvement; docs: unclear guidance; praise: it worked well; other"
},
"tool": {
"type": "string",
"maxLength": 64,
"description": "The tool involved, e.g. get_data"
},
"about": {
"enum": [
"connector",
"abs"
],
"type": "string",
"default": "connector",
"description": "connector: this connector or its site; abs: ABS's own data or API (so it can be passed on to ABS)"
},
"error": {
"type": "string",
"maxLength": 1000,
"description": "The error reason or message returned, if any"
},
"table": {
"type": "string",
"maxLength": 64,
"description": "The ABS table id involved, e.g. CPI"
},
"contact": {
"type": "string",
"format": "email",
"pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
"maxLength": 254,
"description": "Only if the person chose to give an email address for a reply. Never guess or fill one in."
},
"details": {
"type": "string",
"maxLength": 5000,
"description": "What happened and what was expected. No personal information about anyone."
},
"summary": {
"type": "string",
"maxLength": 200,
"minLength": 3,
"description": "One line, in the person's own words"
},
"assistant": {
"type": "string",
"maxLength": 80,
"description": "The AI tool in use, e.g. Claude, ChatGPT, Copilot"
},
"selection": {
"type": "string",
"maxLength": 1000,
"description": "The selection or query involved, as JSON or the SDMX key"
},
"shareWithAbs": {
"type": "boolean",
"default": false,
"description": "Only true if the person agreed this may be passed on to ABS, contact address included"
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"receivedAt",
"message"
],
"properties": {
"id": {
"type": "string",
"description": "Reference for this submission, e.g. FB-7Q2K9C"
},
"message": {
"type": "string"
},
"receivedAt": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Send feedback to the maintainers",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}ABS Data: the Australian Bureau of Statistics' public data, fetched live. People describe what they care about, not which dataset: work out which tables bear on their question, then search_tables → describe_table → search_options (for long lists) → get_data. A failed selection names the valid options; use them, don't guess. Quote numbers only from get_data, say where they come from, and explain caveats in the person's terms. For feedback use feedback_form; never call submit_feedback without their OK. More: Code Mode `search` runs code over the whole catalogue document and `execute` runs multi-series analysis in a sandbox. Resources: abs://guide (how to use this server), abs://table/{id}, abs://findings (how ABS's published metadata compares with its data). Prompts: suburb_dossier, compare_capitals, report_issue, explain_metadata_gap. Small-area series are volatile; read multi-year totals, not single years.
Names, descriptions and schemas were written by the server and are shown as data.