io.ausdata/asic-mcp

Overview Schema Source Related Servers Discussions Admin

get_data

Query curated ASIC register datasets to retrieve matching rows for financial advisers, licensees, banned persons, filtered by status, state, name, or date.

Instructions

Query a curated ASIC register dataset and return matching rows.

Examples: # All currently registered financial advisers in NSW resp = await get_data( "ASIC_FINANCIAL_ADVISERS", filters={"current_status": "current", "state": "nsw"}, )

# AFS licensees whose legal name contains "Macquarie"
resp = await get_data(
    "ASIC_AFS_LICENSEE",
    filters={"licensee_name": "Macquarie"},
)

# Persons banned or disqualified after 2024
resp = await get_data(
    "ASIC_BANNED_PERSONS",
    start_period="2024-01-01",
)

# Full authorisation text for one AFS licensee
resp = await get_data(
    "ASIC_AFS_LICENSEE",
    filters={"licensee_name": "Macquarie Bank Limited"},
    include_full_authorisation=True,
)

Returns: DataResponse with records (or csv), unit, period bounds, row_count, source URL, and CC-BY 3.0 AU attribution.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`format`	No	Response shape. 'records' (default): flat list of observations. 'series': grouped by measure. 'csv': pandas CSV string in `csv` field.	records
`filters`	No	Dimension filters. Keys are plain-English aliases from the dataset's describe_dataset response. Values are matched against the source data; pass a list to OR across values. Examples: {'current_status': 'current'}, {'state': 'nsw'}, {'licensee_name': ['Westpac Banking Corporation', 'NAB']}. MCP clients that cannot send a native object may pass this as a JSON-encoded string instead, e.g. '{"state": "nsw"}'.
`dataset_id`	Yes	Curated dataset ID. Use the search or list-curated endpoint/tool to discover.
`end_period`	No	Inclusive end date. Same format as start_period.
`start_period`	No	Inclusive start date for time-bounded register fields (date of registration, date banned, etc.). Format: 'YYYY', 'YYYY-MM', or 'YYYY-MM-DD'. Bare int years like 2020 are coerced to '2020' automatically.
`include_full_authorisation`	No	ASIC_AFS_LICENSEE only. The `authorisation` field carries 2-3 KB of license boilerplate per record (which financial services and products the licensee may deal in). To keep responses under the portfolio's 10k-token target, that field is truncated to ~200 chars by default with a [truncated] suffix. Pass True to receive the full text — useful when verifying scope conditions for a specific licensee. Ignored for the other ASIC datasets.

Output Schema

TableJSON Schema

Name	Required	Default
`csv`	No
`unit`	No
`query`	No
`stale`	No
`period`	No
`source`	No	Australian Securities and Investments Commission (ASIC), via data.gov.au
`records`	No
`row_count`	No
`dataset_id`	Yes
`source_url`	Yes
`attribution`	No	Source: Australian Securities and Investments Commission, licensed under Creative Commons Attribution 3.0 Australia (CC BY 3.0 AU) — https://creativecommons.org/licenses/by/3.0/au/. Data accessed via data.gov.au. © Commonwealth of Australia.
`dataset_name`	Yes
`retrieved_at`	Yes
`stale_reason`	No
`truncated_at`	No
`server_version`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.22Sep 27, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description carries the burden, and 'Query... return matching rows' implies a read-only operation but never states it outright. It does add useful behavioral detail (CC-BY attribution, source URL, row_count, and the authorisation truncation rationale), though some of that overlaps the schema. No auth, rate-limit, or pagination behavior is disclosed.

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?

A tight one-line purpose statement is front-loaded, followed by four compact examples that each illustrate a distinct capability. The examples are longer than strictly necessary but each earns its place by showing a different parameter combination.

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?

For a six-parameter query tool with an output schema and 100% schema coverage, the description supplies the practical context an agent needs (discovery pointer, example filter usage, truncation caveat). The Returns section partially duplicates the output schema, so there is minor redundancy rather than a gap.

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 baseline is 3. The examples reinforce real filter keys and the start_period/end_period pairing, but they largely restate what the schema already documents thoroughly rather than adding new semantics.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ('Query a curated ASIC register dataset and return matching rows'), and the four worked examples make the scope concrete. It stops short of naming or contrasting siblings like search_datasets or describe_dataset, so an agent still has to infer routing, but the purpose itself is unambiguous.

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

Usage Guidelines4/5

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

The examples effectively demonstrate the range of valid invocations (filters, period bounds, include_full_authorisation) and the dataset_id schema note points to the discovery tools. There is no explicit when-not-to-use or a stated 'call describe_dataset first' workflow, so it is clear context rather than full routing guidance.

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

Deploy Server