# io.github.cyanheads/ilostat-mcp-server

> Search ILOSTAT labour indicators, query and compare series, build country profiles, run SQL.

- name: io.github.cyanheads/ilostat-mcp-server
- version: 0.2.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Filostat-mcp-server
- tools: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Filostat-mcp-server/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ilostat-mcp-server": {
      "type": "http",
      "url": "https://ilostat.caseyjhand.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% +updated-5d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 8 of 8 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: ilostat_search_indicators (destructiveHint); ilostat_describe_indicator (destructiveHint); ilostat_get_country_profile (destructiveHint); …
- pass `tools.token_cost`: about 5,128 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 7 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @cyanheads/ilostat-mcp-server@0.2.0, @cyanheads/ilostat-mcp-server@0.2.0

- tools: 8, about 5,128 tokens to load them all
- tool set hash: 01e02748541b8ab06cca2cbe26ab68c0
- tools last changed: 2026-10-15T21:11:16.889Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.cyanheads/ilostat-mcp-server.svg)](https://protogrid.dev/servers/io.github.cyanheads/ilostat-mcp-server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-15 `ilostat_dataframe_describe` changed (description, outputSchema)
  - before: Describe the df_<id> dataframes staged by ilostat_query_indicator and ilostat_compare_geographies or stored by ilostat_dataframe_query register_as: the tool and parameters that produced each, the datasets it holds (label, unit, last update), coverage, basis counts, attribution, creation and expiry times, row count, and column schema. Pass name for one dataframe. Without it, every staged dataframe is listed, except on a deployment whose callers share one canvas, where listing is off and only the exact name works. Read the schema here before writing SQL for ilostat_dataframe_query.
  - after: Describe the df_<id> dataframes staged by ilostat_query_indicator and ilostat_compare_geographies or stored by ilostat_dataframe_query register_as: the tool and parameters that produced each, the datasets it holds (label, last update, and the unit with its measure, type, and multiplier — values stay in the published scale the multiplier names), coverage, basis counts, attribution, creation and expiry times, row count, and column schema. Pass name for one dataframe. Without it, every staged dataframe is listed, except on a deployment whose callers share one canvas, where listing is off and only the exact name works. Read the schema here before writing SQL for ilostat_dataframe_query.
- 2026-10-15 `ilostat_dataframe_query` changed (description, inputSchema, outputSchema)
  - before: Run a single-statement SELECT against the df_<id> dataframes staged by ilostat_query_indicator and ilostat_compare_geographies or stored by an earlier register_as. Inspect a dataframe with ilostat_dataframe_describe first; its column schema is what the SQL has to match. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, and file-reading table functions are rejected, and system catalogs (information_schema, pg_catalog, sqlite_master, duckdb_*) are denied. Breakdown versions overlap (AGE_YTHADULT_*, AGE_AGGREGATE_*, AGE_10YRBANDS_*), so filter to one version before summing. Optional register_as stores the result as a new dataframe with a fresh TTL.
  - after: Run a single-statement SELECT against the df_<id> dataframes staged by ilostat_query_indicator and ilostat_compare_geographies or stored by an earlier register_as. Inspect a dataframe with ilostat_dataframe_describe first; its column schema is what the SQL has to match. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, file references, file-reading table functions, and functions that read engine settings or name a table from a string are rejected, and system catalogs (information_schema, pg_catalog, sqlite_master, duckdb_*) are denied. Breakdown versions overlap (AGE_YTHADULT_*, AGE_AGGREGATE_*, AGE_10YRBANDS_*), so filter to one version before summing. Optional register_as stores the result as a new dataframe with a fresh TTL.
- 2026-10-15 `ilostat_list_reference` changed (inputSchema, outputSchema)
- 2026-10-15 `ilostat_compare_geographies` changed (description, outputSchema)
  - before: Compare reference areas on one ILOSTAT dataset and one slice — a sex code plus breakdown codes, defaulting to the dataset's totals — giving each area's value at a common period or at its latest non-projected period, optional change over N years, and a rank, with each value's period, source, status, and basis (reported, modelled_estimate, or projection). Areas without a value are listed separately with the reason, and the response flags mixed periods and mixed bases rather than hiding them. Select areas by code list, by group (X01 for every country, an ILO region or subregion, or a World Bank income group), or both; X-coded aggregates require a dataset with aggregates.
  - after: Compare reference areas on one ILOSTAT dataset and one slice — a sex code plus breakdown codes, defaulting to the dataset's totals — giving each area's value at a common period or at its latest non-projected period, optional change over N years, and a rank, with each value's period, source, status, and basis (reported, modelled_estimate, or projection). A change carries the earlier value's source, basis, status, and notes, and flags whether the source or basis differs or the series breaks between the two values. Areas without a value are listed separately with the reason, and the response flags mixed periods and mixed bases rather than hiding them. Select areas by code list, by group (X01 for every country, an ILO region or subregion, or a World Bank income group), or both; X-coded aggregates require a dataset with aggregates.
- 2026-10-15 `ilostat_query_indicator` changed (description, inputSchema, outputSchema)
  - before: Fetch observations for up to 3 ILOSTAT datasets, filtered by reference area or area group, sex, breakdown codes (classif1, classif2), source, and period. Rows keep their source, observation status, decoded notes, and a basis — reported, modelled_estimate, or projection — and the response echoes every filter applied, including the best-source default. Codes are checked against ILOSTAT's dictionaries before the request is sent: ilostat_list_reference lists valid codes and ilostat_describe_indicator lists the codes a dataset actually uses. A result larger than the inline preview is staged in full as a df_<id> dataframe for SQL through ilostat_dataframe_describe and ilostat_dataframe_query when this deployment enables dataframes. A request with no filters at all is refused when the dataset exceeds the row ceiling, and a filtered request that still exceeds it is refused with guidance to narrow it.
  - after: Fetch observations for up to 3 ILOSTAT datasets per call, filtered by reference area or area group, sex, breakdown codes (classif1, classif2), source, and period; datasets past the first 3 come back as remaining_dataset_ids for another call. Rows keep their source, observation status, decoded notes, and a basis — reported, modelled_estimate, or projection — and the response echoes every filter applied, including the best-source default. Codes are checked against ILOSTAT's dictionaries before the request is sent: ilostat_list_reference lists valid codes and ilostat_describe_indicator lists the codes a dataset actually uses. A result larger than the inline preview is staged in full as a df_<id> dataframe for SQL through ilostat_dataframe_describe and ilostat_dataframe_query when this deployment enables dataframes. A request with no filters at all is refused when the dataset exceeds the row ceiling, and a filtered request that still exceeds it is refused with guidance to narrow it.
- 2026-10-15 `ilostat_describe_indicator` changed (outputSchema)
- 2026-10-15 `ilostat_search_indicators` changed (description, inputSchema, outputSchema)
  - before: Search ILOSTAT's catalog of labour-statistics indicators by plain-language terms and filters. Each hit is one indicator with its datasets — one per available frequency (annual, quarterly, monthly) — plus breakdowns, coverage years, number of reference areas, source database, and last update; pass a dataset ID to ilostat_describe_indicator for its units and breakdown codes, then to ilostat_query_indicator or ilostat_compare_geographies for values. Every search term must match a word or word prefix in the indicator's label, subject, database, breakdown names, code, or definition; British and American spellings (labour/labor) match alike. Facet counts reflect all applied filters.
  - after: Search ILOSTAT's catalog of labour-statistics indicators by plain-language terms and filters. Each hit is one indicator with its datasets — one per available frequency (annual, quarterly, monthly) — plus breakdowns, coverage years, number of reference areas, source database, and last update; pass a dataset ID to ilostat_describe_indicator for its units and breakdown codes, then to ilostat_query_indicator or ilostat_compare_geographies for values. Every search term must match a word or word prefix in the indicator's label, subject, database, breakdown names, code, or definition; a term that matches no word or word prefix anywhere in the catalog matches the words sharing its stem instead (informality finds informal, unionization finds union), and the notice names it. British and American spellings (labour/labor) match alike. The measure filter lists every indicator of one measured quantity, as ilostat_describe_indicator's related indicators count them. Facet counts reflect all applied filters.

Full history: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Filostat-mcp-server/changes

## Dependencies

- npm @cyanheads/ilostat-mcp-server@0.2.0: unknown
- npm @cyanheads/ilostat-mcp-server@0.2.0: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://ilostat.caseyjhand.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm @cyanheads/ilostat-mcp-server@0.2.0
- npm @cyanheads/ilostat-mcp-server@0.2.0

## Tools (8)

- `ilostat_compare_geographies`: Compare reference areas on one ILOSTAT dataset and one slice — a sex code plus breakdown codes, defaulting to the dataset's totals — giving each area's value at a common period or at its latest non-projected period, optional change over N years, and a rank, with each value's period, source, status, and basis (reported, modelled_estimate, or projection). A change carries the earlier value's source, basis, status, and notes, and flags whether the source or basis differs or the series breaks between the two values. Areas without a value are listed separately with the reason, and the response flags mixed periods and mixed bases rather than hiding them. Select areas by code list, by group (X01 for every country, an ILO region or subregion, or a World Bank income group), or both; X-coded aggregates require a dataset with aggregates.
- `ilostat_dataframe_describe`: Describe the df_<id> dataframes staged by ilostat_query_indicator and ilostat_compare_geographies or stored by ilostat_dataframe_query register_as: the tool and parameters that produced each, the datasets it holds (label, last update, and the unit with its measure, type, and multiplier — values stay in the published scale the multiplier names), coverage, basis counts, attribution, creation and expiry times, row count, and column schema. Pass name for one dataframe. Without it, every staged dataframe is listed, except on a deployment whose callers share one canvas, where listing is off and only the exact name works. Read the schema here before writing SQL for ilostat_dataframe_query.
- `ilostat_dataframe_query`: Run a single-statement SELECT against the df_<id> dataframes staged by ilostat_query_indicator and ilostat_compare_geographies or stored by an earlier register_as. Inspect a dataframe with ilostat_dataframe_describe first; its column schema is what the SQL has to match. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, file references, file-reading table functions, and functions that read engine settings or name a table from a string are rejected, and system catalogs (information_schema, pg_catalog, sqlite_master, duckdb_*) are denied. Breakdown versions overlap (AGE_YTHADULT_*, AGE_AGGREGATE_*, AGE_10YRBANDS_*), so filter to one version before summing. Optional register_as stores the result as a new dataframe with a fresh TTL.
- `ilostat_describe_indicator`: Explain one ILOSTAT dataset before comparing numbers: its definition, unit and multiplier, frequency variants and coverage, the sex and breakdown codes in use across its frequencies (the total code of each breakdown marked), the reference areas it covers, whether it carries World/regional/income-group aggregates, and how its observations are classed as reported, modelled, or projected. Accepts a dataset ID (UNE_DEAP_SEX_AGE_RT_A) or a bare indicator code (UNE_DEAP_SEX_AGE_RT), which describes every frequency. An unknown code returns found: false with guidance.
- `ilostat_get_country_profile`: Build a headline labour-market profile for one reference area: labour force participation, employment-to-population ratio, unemployment and youth unemployment rates, youth NEET rate, informal employment rate, employment level, labour income share, and working poverty rate. Each indicator shows its latest reported value (from a national or institutional source, with its source and notes) and, separately, its latest ILO modelled estimate that is not a projection, each with its dataset, period, and status — a missing reported value stays missing and is never filled from the model. Accepts a country (ISO3, e.g. KEN) or an X-coded aggregate (X01 World, regions, income groups), for which only modelled values exist.
- `ilostat_list_reference`: Decode ILOSTAT's code vocabulary: reference areas (ISO3 countries and X-coded aggregates, with World Bank income group and ILO region), the groups that area_group accepts (X01 for every country, ILO regions and subregions, World Bank income groups; exact-code lookups list their member countries), databases, subjects, sex codes, breakdown codes for classif1/classif2 with their classification types, per-country data sources, observation status flags, note codes, and frequencies. Filter by text or look up exact codes; long topics page with a cursor. These are ILOSTAT-wide vocabularies; ilostat_describe_indicator lists the sex and breakdown codes one dataset actually uses.
- `ilostat_query_indicator`: Fetch observations for up to 3 ILOSTAT datasets per call, filtered by reference area or area group, sex, breakdown codes (classif1, classif2), source, and period; datasets past the first 3 come back as remaining_dataset_ids for another call. Rows keep their source, observation status, decoded notes, and a basis — reported, modelled_estimate, or projection — and the response echoes every filter applied, including the best-source default. Codes are checked against ILOSTAT's dictionaries before the request is sent: ilostat_list_reference lists valid codes and ilostat_describe_indicator lists the codes a dataset actually uses. A result larger than the inline preview is staged in full as a df_<id> dataframe for SQL through ilostat_dataframe_describe and ilostat_dataframe_query when this deployment enables dataframes. A request with no filters at all is refused when the dataset exceeds the row ceiling, and a filtered request that still exceeds it is refused with guidance to narrow it.
- `ilostat_search_indicators`: Search ILOSTAT's catalog of labour-statistics indicators by plain-language terms and filters. Each hit is one indicator with its datasets — one per available frequency (annual, quarterly, monthly) — plus breakdowns, coverage years, number of reference areas, source database, and last update; pass a dataset ID to ilostat_describe_indicator for its units and breakdown codes, then to ilostat_query_indicator or ilostat_compare_geographies for values. Every search term must match a word or word prefix in the indicator's label, subject, database, breakdown names, code, or definition; a term that matches no word or word prefix anywhere in the catalog matches the words sharing its stem instead (informality finds informal, unionization finds union), and the notice names it. British and American spellings (labour/labor) match alike. The measure filter lists every indicator of one measured quantity, as ilostat_describe_indicator's related indicators count them. Facet counts reflect all applied filters.