Query the WGEA in plain English — employer pay gap, workforce composition, leave.
The io.ausdata/wgea-mcp MCP server “Query the WGEA in plain English” for employer pay gap, workforce composition, and leave. It is distributed as a PyPI package (wgea-mcp) and is categorized under topics including australia, gender-equality, and model-context-protocol (MCP).
MCP server for the Workplace Gender Equality Agency (WGEA) public data file. Plain-English access to per-employer workforce composition, gender-equality policy answers, parental leave, flexible work, and harm-prevention data — every WGEA-reporting employer in Australia (~9,600 employers), every year, from a single uvx command.
Hosted access? For cross-source queries, webhooks, an always-on REST API, and a uniform response envelope across all 9 sources, see ausdata.io — free tier available (500 calls/mo, no card).
text
"What's the gender breakdown at Commonwealth Bank?"
"Which mining companies set gender targets in 2024-25?"
"Workforce composition by occupation at Qantas"
"Sexual harassment policy responses across financial services"
"Promotions to manager by gender at Atlassian"
claude mcp add wgea --command uvx --args -- --upgrade wgea-mcp
What it exposes
Six tools, all plain-English in, structured out:
Tool
Purpose
search_datasets
Fuzzy-search the curated catalog by keyword
describe_dataset
List a dataset's filterable dimensions and returnable measures
get_data
Query with filters, period range, output format
latest
Restrict to the latest reporting year. Row cap parameter is limit (portfolio-standard); max_rows retained as legacy alias.
top_n
Rank rows by a numeric measure (e.g. n_employees) and return the top (or bottom) N for one reporting year.
list_curated
Enumerate the curated dataset IDs
Every response is the same shape — dataset_id, dataset_name, query, reporting_year, unit, row_count, records, source_url, download_url, did_you_mean, attribution, stale flag, server_version.
Curated datasets (8)
ID
What it is
Source
HEADLINE_GAP
Industry gender pay gap mid-points by ANZSIC division + national rollup
EGPG xlsx on wgea.gov.au (aggregated server-side)
WORKFORCE_COMPOSITION
Per-employer headcount by occupation × manager category × gender
wgea_workforce_composition_<year>.csv
WORKFORCE_MANAGEMENT
Manager movements (promotions, hires, resignations) by gender
Sexual harassment + domestic-violence policy responses
wgea_questionnaire_harm_prevention_<year>.csv
EMPLOYEE_SUPPORT
Carer leave, EAP, mental-health programs
wgea_questionnaire_employee_support_<year>.csv
WORKPLACE_OVERVIEW
Board composition, governing-body diversity, CEO + KMP demographics
wgea_questionnaire_workplace_overview_<year>.csv
The headline gender pay-gap %.HEADLINE_GAP (added in 0.6.0) carries the industry mid-points WGEA publishes annually in its Employer Gender Pay Gaps Report — e.g. Mining 18.9%, Financial and Insurance Services 21.4%, "All employers" national mid-point 11.2% (2024-25 reporting year). Numbers match WGEA's published Figure 4 to within rounding. For the workforce-weighted national aggregate (~21.1% private sector) WGEA states in its public materials, see the WGEA Data Explorer — that figure requires payroll data WGEA holds before public release and is not derivable from the published employer-level xlsx.
Reliability — 2-tier URL resolution
WGEA publishes the public data file annually under a single CKAN package on data.gov.au. Each annual release gets a fresh resource UUID:
Live CKAN — package_show?id=wgea-dataset returns every resource; the newest "WGEA Data — Public Data File" wins. Cached 6h.
Bundled seed manifest — when CKAN is unreachable, fall back to data/seed_urls.json shipped in the wheel. The response is flagged stale: true with an honest reason.
Net effect: a fresh uvx wgea-mcp always gets the current reporting year; a 12-month-old install still works because the seed manifest is refreshed and --upgrade pulls a new wheel.
Fuzzy employer-name search
Pass any abbreviation, alias, or substring and rapidfuzz resolves it:
You type
Resolved to
"CBA"
Commonwealth Bank of Australia
"Commonwealth Bank"
Commonwealth Bank of Australia
"NAB"
National Australia Bank Limited
"Westpac"
Westpac Banking Corporation
"Woolies" / "woolworths"
Woolworths Group Limited
"Atlassian"
Atlassian Pty Ltd
"qantas"
Qantas Airways Limited
When nothing exact matches, did_you_mean carries the top-5 closest legal names so the agent can ask the user to pick.
Attribution
Data sourced from the Workplace Gender Equality Agency. Licensed under Creative Commons Attribution 3.0 Australia (CC BY 3.0 AU). wgea-mcp is MIT-licensed; WGEA's data carries the upstream CC-BY 3.0 AU licence, echoed in every response's attribution field.
Per-employer reporting is a deliberate disclosure under the Workplace Gender Equality Act 2012 — redistribution is explicitly intended.
Sister MCPs (Australian Public Data portfolio)
Want all 9 sources behind one REST API? The hosted gateway at ausdata.io adds cross-source joins, full history, webhooks, and HMAC-signed responses on top of these MCPs — free tier (500 calls/mo, no card).
abs-mcp — Australian Bureau of Statistics (CPI, unemployment, ERP, building approvals)
rba-mcp — Reserve Bank of Australia (cash rate, lending stats, exchange rates)
ato-mcp — Australian Taxation Office (tax stats, ACNC charities)
apra-mcp — Australian Prudential Regulation Authority (banking, insurance, super)
aihw-mcp — Australian Institute of Health and Welfare
asic-mcp — Australian Securities and Investments Commission (company registers)
aemo-mcp — Australian Energy Market Operator (NEM dispatch, spot prices, generation)
au-weather-mcp — Open-Meteo (Bureau of Meteorology aggregator)
wgea-mcp — this one. Workplace gender equality.
aus-identity — Postcode / state / ABN normalisation helper used by all sisters
Development
bash
git clone https://github.com/Bigred97/wgea-mcp.git
cd wgea-mcp
uv venv
uv pip install -e ".[dev]"
pytest # unit tests
pytest -m live # integration tests against data.gov.au (downloads the ~71 MB ZIP)
