AusEcon MCP for ABS | RBA | APRA data

Get APRA Data

get_apra_data

Read-onlyIdempotent

Retrieve Australian Prudential Regulation Authority (APRA) data from official XLSX publications. Filter by publication, table, series, and date range to get curated datasets.

Instructions

Expert/source-native APRA public XLSX publication retrieval.

Only curated official APRA publication IDs are accepted; arbitrary URLs are not.

Input Schema

TableJSON Schema

Name	Required	Description
`last_n`	No	Optional limit returning only the most recent N observations per series; metadata.truncated is true when older observations were dropped.
`end_date`	No	Optional ISO date bound in YYYY-MM-DD format.
`table_id`	No	Non-empty dataset or table id.
`series_ids`	No	Optional list of non-empty source-native series IDs to keep after download.
`start_date`	No	Optional ISO date bound in YYYY-MM-DD format.
`publication_id`	Yes	Non-empty dataset or table id.
`include_observation_dimensions`	No	Whether to repeat the full dimension dict on every observation. Off by default because the same dimensions already appear on each series descriptor and are encoded in series_id.

Output Schema

TableJSON Schema

Name	Required	Description
`series`	Yes	Series descriptors keyed by series_id.
`metadata`	Yes	Source, provenance, cache, and retrieval metadata for this response.
`observations`	Yes	Long-form observations keyed by date and series_id.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.11.0Jun 14, 2026

addedInput schema / properties / include_observation_dimensions

Added value: +{
+  "default": false,
+  "description": "Whether to repeat the full dimension dict on every observation. Off by default because the same dimensions already appear on each series descriptor and are encoded in series_id.",
+  "type": "boolean"
+}

addedOutput schema / properties / metadata / properties / derived / properties / alignment_method

Added value: +{
+  "enum": [
+    "locf",
+    "exact_month",
+    "period_intersection",
+    "year_ended_lag"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / metadata / properties / derived / properties / description
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / metadata / properties / derived / required

Previous value: -[
-  "concept",
-  "formula",
-  "operands",
-  "source_concepts",
-  "alignment_frequency",
-  "units",
-  "requested_bounds",
-  "resolved_bounds",
-  "dropped_observations"
-]New value: +[
+  "concept",
+  "description",
+  "formula",
+  "operands",
+  "source_concepts",
+  "alignment_frequency",
+  "alignment_method",
+  "units",
+  "requested_bounds",
+  "resolved_bounds",
+  "dropped_observations"
+]

changedOutput schema / properties / observations / items / required

Previous value: -[
-  "date",
-  "series_id",
-  "value",
-  "dimensions"
-]New value: +[
+  "date",
+  "series_id",
+  "value"
+]

Changed2 schema fields changedv1.8.0Jun 10, 2026

changedInput schema / properties / last_n / description

Previous value: -"Optional positive observation count limit."New value: +"Optional limit returning only the most recent N observations per series; metadata.truncated is true when older observations were dropped."

addedOutput schema / properties / metadata / properties / observations_dropped

Added value: +{
+  "description": "Number of observations removed by last_n selection; truncated is true when this is non-zero.",
+  "minimum": 0,
+  "type": "integer"
+}

Changed4 schema fields changedv1.7.1Jun 9, 2026

addedOutput schema / properties / metadata / properties / apra_url_resolution

Added value: +{
+  "additionalProperties": false,
+  "description": "APRA workbook URL resolution strategy used for this retrieval.",
+  "properties": {
+    "seed_checked_at": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "strategy": {
+      "enum": [
+        "landing_page",
+        "seed_manifest",
+        "catalogue_fallback"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "strategy",
+    "seed_checked_at"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / metadata / properties / framework_breaks

Added value: +{
+  "description": "Known source framework or reporting-definition breaks relevant to the payload.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "date": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "date",
+      "label",
+      "description"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / metadata / properties / selection

Added value: +{
+  "description": "Observation-selection provenance when returned by convenience tools.",
+  "oneOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "direction": {
+          "enum": [
+            "highest",
+            "lowest"
+          ],
+          "type": "string"
+        },
+        "dropped_non_numeric_count": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "n": {
+          "minimum": 1,
+          "type": "integer"
+        },
+        "numeric_observation_count": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "returned_observation_count": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "type": {
+          "enum": [
+            "top_n"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "type",
+        "n",
+        "direction",
+        "numeric_observation_count",
+        "returned_observation_count",
+        "dropped_non_numeric_count"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "n": {
+          "minimum": 1,
+          "type": "integer"
+        },
+        "returned_observation_count": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "series_count": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "type": {
+          "enum": [
+            "latest"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "type",
+        "n",
+        "series_count",
+        "returned_observation_count"
+      ],
+      "type": "object"
+    }
+  ]
+}

addedOutput schema / properties / metadata / properties / warnings

Added value: +{
+  "description": "Plain-English source warnings relevant to the payload.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

First observedv0.1.0May 31, 2026

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds context about source-native XLSX retrieval and the curated-ID restriction, but it does not disclose behaviors like pagination, error handling, or data format beyond what the schema already implies. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short (two sentences) and front-loaded with the core purpose. The phrase 'Expert/source-native' is somewhat vague and could be clearer, but overall it is concise with no redundant filler. It earns a high score for efficiency, though not perfect due to slightly ambiguous jargon.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the rich input schema, output schema presence, and strong annotations, the description is sufficient for a high-level understanding. It communicates the essential purpose and the key input restriction. It lacks explicit guidance on when to prefer this tool over siblings, but the overall context makes it usable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema fully documents each parameter. The description adds one relevant semantic constraint: only curated official APRA publication IDs are accepted, reinforcing the 'publication_id' parameter and excluding arbitrary URLs. However, it does not clarify any other parameters, so it stays at the baseline for full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as 'APRA public XLSX publication retrieval,' specifying the resource (APRA publications) and the action (retrieval). This distinguishes it from sibling tools focused on ABS or RBA data, making its scope unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. It only imposes an input restriction ('Only curated official APRA publication IDs are accepted; arbitrary URLs are not'), which is a constraint rather than usage guidance. Sibling tools are not mentioned, so an agent receives no comparative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server