io.ausdata/wgea-mcp
PYPI · WGEA-MCP · SCANNED SEP 20
Query the WGEA in plain English — employer pay gap, workforce composition, leave.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 3 of 35 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 13 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1863 tokens (~310/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the io.ausdata/wgea-mcp server?
io.ausdata/wgea-mcp runs locally as a PyPI package, launched with uvx wgea-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · wgea-mcp
claude mcp add io-ausdata-wgea-mcp -- uvx wgea-mcp
{
"mcpServers": {
"io-ausdata-wgea-mcp": {
"command": "uvx",
"args": [
"wgea-mcp"
]
}
}
} {
"servers": {
"io-ausdata-wgea-mcp": {
"command": "uvx",
"args": [
"wgea-mcp"
]
}
}
} codex mcp add io-ausdata-wgea-mcp -- uvx wgea-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"io-ausdata-wgea-mcp": {
"type": "local",
"command": [
"uvx",
"wgea-mcp"
],
"enabled": true
}
}
} openclaw mcp add io-ausdata-wgea-mcp --command uvx --arg wgea-mcp
mcp_servers:
io-ausdata-wgea-mcp:
command: "uvx"
args: ["wgea-mcp"] {
"McpServers": {
"io-ausdata-wgea-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"wgea-mcp"
]
}
}
} assistant mcp add io-ausdata-wgea-mcp -t stdio -c uvx -a wgea-mcp
{
"mcpServers": {
"io-ausdata-wgea-mcp": {
"command": "uvx",
"args": [
"wgea-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 16 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- Package version: 0.6.13 → 0.6.18 functional
- 15 Sept 26 −3
- Stability: pass → 0.80 functional
- 14 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −1
- Stability: pass → 0.90 functional
- 10 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/wgea-mcp@0.6.18
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 35 packages
| Packages resolved | 35 |
|---|---|
| Stale | 3 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
describe_dataset ~165
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.
| Name | Type | Req | Description |
|---|---|---|---|
| dataset_id | string | yes | Curated dataset ID. Use the search endpoint or search tool to discover, or the list-curated endpoint/tool to enumerate. Case-insensitive. |
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | – |
| dimensions | array | – | – |
| download_url | – | – | – |
| id | string | yes | – |
| is_curated | boolean | yes | – |
| measures | array | – | – |
| name | string | yes | – |
| period_coverage | – | – | – |
| reporting_year_latest | – | – | – |
| source_url | string | yes | – |
| update_frequency | – | – | – |
No examples provided.
get_data ~537
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.
| Name | Type | Req | Description |
|---|---|---|---|
| dataset_id | string | yes | Curated dataset ID. Use the search or list-curated endpoint/tool to discover. |
| end_period | – | – | Inclusive end reporting year. Same format as start_period. |
| filters | – | – | 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. Permissive dimensions (e.g… |
| format | string | – | Response shape. 'records' (default): flat list of observations. 'series': grouped by measure. 'csv': pandas CSV string in `csv` field. |
| max_rows | – | – | Cap on returned rows after filtering. Default 2000. Max 10000. Tighten filters to narrow further. |
| start_period | – | – | Inclusive start reporting year. Format: 'YYYY-YY' (e.g. '2023-24') or 'YYYY' (matched against WGEA's reporting_year column). Bare int years like 2023 are coerced to '2023' automatically. |
| Name | Type | Req | Description |
|---|---|---|---|
| attribution | string | – | – |
| caveat | – | – | – |
| csv | – | – | – |
| dataset_id | string | yes | – |
| dataset_name | string | yes | – |
| did_you_mean | array | – | – |
| download_url | – | – | – |
| period | object | – | Canonical period bounds {start, end} for cross-sister consumers. Populated alongside the wgea-specific reporting_year. For a single reporting year both bounds match; for multi-year spans they bracket… |
| query | object | – | – |
| records | array | – | – |
| reporting_year | – | – | – |
| retrieved_at | string | yes | – |
| row_count | integer | – | – |
| server_version | string | – | – |
| source | string | – | – |
| source_url | string | yes | – |
| stale | boolean | – | – |
| stale_reason | – | – | – |
| truncated_at | – | – | – |
| unit | – | – | – |
No examples provided.
latest ~373
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).
| Name | Type | Req | Description |
|---|---|---|---|
| dataset_id | string | yes | Curated dataset ID. |
| filters | – | – | Same filter shape as get_data. Useful for narrowing to one employer. |
| limit | – | – | Cap on returned rows (portfolio-standard name). Default 2000, max 10000. Mutually exclusive with the legacy `max_rows` alias — supplying both raises ValueError. |
| max_rows | – | – | Legacy alias for `limit` — retained for backward compatibility (wgea-mcp <= 0.4.x). Prefer `limit` for cross-sister consistency with asic-mcp's `latest(..., limit)` parameter. Same semantics as `limi… |
| Name | Type | Req | Description |
|---|---|---|---|
| attribution | string | – | – |
| caveat | – | – | – |
| csv | – | – | – |
| dataset_id | string | yes | – |
| dataset_name | string | yes | – |
| did_you_mean | array | – | – |
| download_url | – | – | – |
| period | object | – | Canonical period bounds {start, end} for cross-sister consumers. Populated alongside the wgea-specific reporting_year. For a single reporting year both bounds match; for multi-year spans they bracket… |
| query | object | – | – |
| records | array | – | – |
| reporting_year | – | – | – |
| retrieved_at | string | yes | – |
| row_count | integer | – | – |
| server_version | string | – | – |
| source | string | – | – |
| source_url | string | yes | – |
| stale | boolean | – | – |
| stale_reason | – | – | – |
| truncated_at | – | – | – |
| unit | – | – | – |
No examples provided.
list_curated ~32
List every curated dataset ID in this version of wgea-mcp. Returns: Sorted list of dataset IDs.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_datasets ~205
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of results to return, ranked by relevance. |
| query | string | yes | Free-text search query. Matches against dataset IDs, names, descriptions, and curated search keywords. Case-insensitive. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
top_n ~551
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.
| Name | Type | Req | Description |
|---|---|---|---|
| dataset_id | string | yes | Curated dataset ID. Use the search or list-curated endpoint/tool to discover. |
| direction | string | – | 'top' returns the N rows with the LARGEST measure values (highest n_employees, biggest n_responses, etc.). 'bottom' returns the SMALLEST. |
| filters | – | – | Optional dimension filters, same shape as get_data. |
| measure | string | yes | Numeric measure column to rank by. WGEA measures are `n_employees` (WORKFORCE_COMPOSITION, WORKFORCE_MANAGEMENT) or `n_responses` (the other five questionnaire datasets). Use the describe endpoint or… |
| n | integer | – | How many top (or bottom) rows to return. |
| reporting_year | – | – | Optional single WGEA reporting year to restrict the ranking to. Format: 'YYYY-YY' (e.g. '2024-25') or 'YYYY' (e.g. '2024'). Defaults to the latest reporting year present in the data so the rank is a… |
| Name | Type | Req | Description |
|---|---|---|---|
| attribution | string | – | – |
| caveat | – | – | – |
| csv | – | – | – |
| dataset_id | string | yes | – |
| dataset_name | string | yes | – |
| did_you_mean | array | – | – |
| download_url | – | – | – |
| period | object | – | Canonical period bounds {start, end} for cross-sister consumers. Populated alongside the wgea-specific reporting_year. For a single reporting year both bounds match; for multi-year spans they bracket… |
| query | object | – | – |
| records | array | – | – |
| reporting_year | – | – | – |
| retrieved_at | string | yes | – |
| row_count | integer | – | – |
| server_version | string | – | – |
| source | string | – | – |
| source_url | string | yes | – |
| stale | boolean | – | – |
| stale_reason | – | – | – |
| truncated_at | – | – | – |
| unit | – | – | – |
No examples provided.
What is the io.ausdata/wgea-mcp server?
io.ausdata/wgea-mcp is listed in the public MCP registry as io.ausdata/wgea-mcp. Query the WGEA in plain English, employer pay gap, workforce composition, leave. This page covers its PyPI package (wgea-mcp).
Is the io.ausdata/wgea-mcp server safe to use?
io.ausdata/wgea-mcp scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.ausdata/wgea-mcp server expose?
io.ausdata/wgea-mcp exposes 6 tools: search_datasets, describe_dataset, get_data, latest, top_n, list_curated. Their descriptions and schemas cost roughly 1,863 tokens of context every time the server is loaded.
Is the io.ausdata/wgea-mcp server still maintained?
io.ausdata/wgea-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.ausdata/wgea-mcp server under?
io.ausdata/wgea-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.