wgea-mcp

Describe a dataset's filterable dimensions, returnable measures, units, and source. Use this before calling get_data on a new dataset — it tells you the valid filter keys ('employer_name', 'anzsic_division', 'gender', ...), enumerated filter values where they exist (e.g. 'women' → 'Women'), measure aliases ('n_employees'), and the canonical source URL. Returns: DatasetDetail with id, name, description, period_coverage, list of dimensions, list of measures, source_url, and the resolved reporting year label.

Query a curated WGEA dataset and return observations. Examples: # Gender breakdown at Commonwealth Bank resp = await get_data( "WORKFORCE_COMPOSITION", filters={"employer_name": "Commonwealth Bank"}, ) # Promotions to manager by gender at Westpac in 2024-25 resp = await get_data( "WORKFORCE_MANAGEMENT", filters={"employer_name": "Westpac", "movement_type": "Promotions", "manager_category": "Managers"}, ) # Which employers in mining set gender targets? resp = await get_data( "GENDER_EQUALITY_ACTIONS", filters={"anzsic_division": "Mining", "section": "Gender Pay Gap", "response": "Yes"}, ) # Sexual harassment policy responses across financial services resp = await get_data( "HARM_PREVENTION", filters={"anzsic_division": "Financial and Insurance Services", "subsection": "Sexual Harassment"}, ) Returns: DataResponse with records (or csv), unit, reporting_year, row_count, source URL, the actual download_url used, "did you mean?" fuzzy hints if the employer-name filter didn't match exactly, and CC-BY 3.0 AU attribution.

Return rows from the most recent WGEA reporting year for a dataset. Trims to the single latest reporting_year — useful for "what's the current gender breakdown at CBA?" without having to remember WGEA's annual cadence. Examples: # Latest workforce composition at CBA resp = await latest("WORKFORCE_COMPOSITION", filters={"employer_name": "Commonwealth Bank"}) # Cap rows (portfolio-standard name) resp = await latest("WORKFORCE_COMPOSITION", filters={"anzsic_division": "Mining"}, limit=100) # Legacy alias still works resp = await latest("WORKFORCE_COMPOSITION", filters={"anzsic_division": "Mining"}, max_rows=100) Parameter notes: - Prefer `limit` (portfolio-standard; matches asic-mcp's `latest(..., limit)` parameter). - `max_rows` retained as legacy alias. - Supplying both raises ValueError — pick one. - `get_data()` keeps `max_rows` unchanged (separate surface, separate concern).

List every curated dataset ID in this version of wgea-mcp. Returns: Sorted list of dataset IDs.

Fuzzy-search the curated WGEA dataset catalog. All eight curated datasets cover the WGEA Public Data File: per-employer workforce composition, manager movements, gender-equality policy answers, parental-leave + flexible-work policies, harm-prevention policies, employee support, and workplace overview. Examples: # Find datasets about parental leave results = await search_datasets("parental leave") # → [{id: 'PARENTAL_LEAVE_FLEX', ...}] # Find workforce composition by gender results = await search_datasets("women in management") Returns: List of DatasetSummary (id, name, description, update_frequency, is_curated), ranked by relevance.

Return the N rows with the largest (or smallest) value of a measure. Ranks across one WGEA reporting year (the latest by default, or a specific year via `reporting_year=`). This is the most common agent workflow — "show me the top 10 X by Y" — collapsed into a single server-side call: rank-and-slice happens on the server so the agent never has to fetch a full table just to take the top of it. Examples: # 10 employers with the most women managers (latest reporting year) top_n("WORKFORCE_COMPOSITION", "n_employees", n=10, filters={"gender": "Women", "manager_category": "Manager"}) # 5 ANZSIC divisions with the fewest Yes responses on Gender Pay Gap top_n("GENDER_EQUALITY_ACTIONS", "n_responses", n=5, direction="bottom", filters={"section": "Gender Pay Gap", "response": "Yes"}) # Top 5 employers in Mining by total workforce in 2023-24 top_n("WORKFORCE_COMPOSITION", "n_employees", n=5, filters={"anzsic_division": "Mining"}, reporting_year="2023-24") Returns: DataResponse with at most `n` records, sorted by `measure` value in the requested direction. Other fields (reporting_year, unit, attribution) match a regular get_data call.