io.ausdata/asic-mcp

Overview Schema Source Related Servers Discussions Admin

search_datasets

Search ASIC's curated dataset catalogue by free-text keyword to find relevant registers, including financial advisers, licensees, banned persons, and auditors.

Instructions

Fuzzy-search the curated ASIC dataset catalogue.

The curated set of hand-curated ASIC registers covers Financial Advisers, AFS Licensees, AFS Authorised Representatives, Credit Licensees, Credit Representatives, Banned and Disqualified Persons, Banned and Disqualified Organisations, Registered Liquidators, Registered Company Auditors, SMSF Auditors, Companies, Business Names, and Short Positions. Call list_curated() to get the live list rather than assuming a fixed count — the registry grows over time.

Examples: # Find the financial advisers register results = await search_datasets("financial adviser") # → [{id: 'ASIC_FINANCIAL_ADVISERS', name: 'Financial Advisers Register', ...}]

# Discover what's available on enforcement-related lists
results = await search_datasets("banned")

Returns: List of DatasetSummary (id, name, description, update_frequency, is_curated), ranked by relevance.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of results to return, ranked by relevance.
`query`	Yes	Free-text search query. Matches against dataset IDs, names, descriptions, and curated search keywords. Case-insensitive.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.22Sep 27, 2026

TDQS

A4.1/5.0

Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses the matching surface (IDs, names, descriptions, curated keywords), case-insensitivity, relevance ranking, and the returned DatasetSummary fields. It omits no harm salient for a read-only search, though it never explicitly states the read-only nature.

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 what/where is front-loaded before the catalogue enumeration and code examples, and the examples earn their place by showing expected return shape. The long enumerated list of register types is somewhat bulkier than necessary for an agent that already has list_curated().

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?

With an output schema present, the description needn't explain return fields, and its inclusion of matching scope and ranking behavior is sufficient for correct invocation. Slight gap in not clarifying how results relate to the other sibling tools, but nothing blocking.

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 schema already documents query and limit in full. The description adds only illustrative query examples, not new parameter semantics, so the baseline 3 is correct.

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?

States a specific verb (fuzzy-search) and resource (the curated ASIC dataset catalogue), and immediately differentiates itself from the list_curated sibling by noting that list_curated gives the live list rather than a search. An agent can tell it apart from siblings without opening any schema.

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?

Explicitly routes agents to list_curated() for the live list and demonstrates two concrete query scenarios, giving clear usage context. It does not, however, clarify how this differs from describe_dataset, get_data, or latest, so the sibling guidance is partial rather than complete.

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

Deploy Server