ilostat-mcp-server

Overview

Labour statistics from ILOSTAT, the International Labour Organization's statistical database, read from two keyless ILO APIs: the ILOSTAT data API (rplumber.ilo.org) and the ILO SDMX API (sdmx.ilo.org). Find an indicator, read its unit and breakdown codes, pull observations for countries, regions, and income groups, compare areas, and build a headline labour-market profile. Every value is marked as reported, modelled estimate, or projection. Large results stage as dataframes you query with SQL. Runs as a stdio process or a local Streamable HTTP server.

Tools

ilostat_dataframe_drop is off unless ILOSTAT_DATAFRAME_DROP_ENABLED=true, and CANVAS_PROVIDER_TYPE=none turns off all three dataframe tools.

Related MCP server: Sozio Thin

Capability reference

ilostat_search_indicators tool

• Plain-language query (every term must match a word or word prefix; case, accents, and labour/labor folded) plus frequency, database, subject, breakdown, and aggregates_only filters; omit query to browse by filters

• Up to 50 hits per page (default 10), continued with next_cursor; each hit is one indicator with a dataset_id per frequency, coverage years, n_ref_area, last_update, and has_aggregates, and facets count the whole match set

• An unrecognized database, subject, or breakdown code fails as unknown_filter_code

ilostat_describe_indicator tool

• One dataset_id (UNE_DEAP_SEX_AGE_RT_A) or a bare indicator code, which describes every frequency; an unknown code returns found: false with guidance

• Definition, unit and its multiplier, frequency variants, breakdowns (sex codes, plus classif1 / classif2 codes with totals marked is_total), default_slice, covered ref_areas, basis_rule, and up to 20 related_datasets

• Breakdowns, unit, and areas come from the SDMX API; when it can't answer, structure_status is unavailable and those fields are absent rather than the call failing

ilostat_query_indicator tool

• 1–3 dataset_ids, filtered by ref_areas (up to 300) and/or an area_group, sex, classif1, classif2, sources, and period: one exact time, or a time_from / time_to year window, latest_only, or both

• source_selection is best by default (the preferred source per area and period), all, or secondary; rows carry source, obs_status, notes, and basis, decoded in legend, and applied_filters echoes every parameter sent

• A result past the inline preview stages in full as a df_<id> dataframe; an unfiltered request larger than ILOSTAT_MAX_ROWS fails as request_too_broad, and a filtered one that streams past it as result_too_large

ilostat_get_country_profile tool

• One ref_area with annual data, an ISO3 country (KEN) or an X-coded aggregate (X01 World, regions, income groups), and sex (SEX_T by default, SEX_M, or SEX_F)

• Nine headline indicators (labour force participation, employment-to-population ratio, unemployment, youth unemployment, youth NEET, informal employment, employment, labour income share, working poverty), each with its latest reported value and, separately, its latest non-projected modelled estimate

• A missing reported value stays missing and is listed in reported_missing; aggregates carry modelled values only

ilostat_compare_geographies tool

• One dataset_id and one slice (sex, classif1, classif2, defaulting to the dataset's totals); areas from ref_areas (up to 300), an area_group, or both, and at least one is required

• period puts every area at one period; without it, each area gets its latest value within lookback_years (default 10), projections excluded unless include_projections; change_years (1–30) adds each value's change over that span

• Rows carry rank, value, period, basis, and source; areas without a value land in missing with a reason, and comparability reports mixed_periods, basis_counts, and distinct_sources

ilostat_list_reference tool

• topic: ref_areas, area_groups, databases, subjects, sexes, classifications, classification_types, sources, obs_status, notes, or frequencies

• A text filter or up to 100 exact codes (misses in not_found; exact area_groups lookups list member countries); ref_area narrows sources, and classification_type narrows classifications

• Up to 500 entries per page (default 50), continued with next_cursor

ilostat_dataframe_describe tool

• Pass one df_XXXXX_XXXXX, or omit name to list every staged dataframe, newest first. Listing is off under HTTP with auth none, where every caller shares one canvas: there a dataframe is reached by its exact name only

• Each entry carries the producing source_tool and its query_params, datasets, coverage, basis_counts, attribution, created_at / expires_at, row_count, and the column_schema to write SQL against

ilostat_dataframe_query tool

• One DuckDB SELECT (joins, aggregates, window functions, CTEs) over df_<id> tables, up to 20,000 characters; writes, DDL, multi-statement SQL, file-reading functions, and system catalogs are rejected

• row_limit caps the rows materialized (default 1,000, max 10,000; row_count_capped flags a hit) and preview the rows returned inline; BIGINT values arrive as strings

• register_as stores the full result as a new dataframe with a fresh TTL, so analyses chain; a result over 1,000,000 rows is refused as register_as_too_large, and evicted names any older dataframes dropped to make room

ilostat_dataframe_drop tool

• Drops one staged dataframe by name before its TTL; idempotent, with dropped: false when nothing matched

• Listed only when ILOSTAT_DATAFRAME_DROP_ENABLED=true and dataframes are on; it is the only destructive tool

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

ILOSTAT-specific:

• Two keyless ILO APIs: the ILOSTAT data API serves the catalog, the code dictionaries, and observations; the ILO SDMX API serves each dataset's breakdown codes, default slice, and unit

• The catalog (both tables of contents and 13 code dictionaries) is held in memory and rechecked every ILOSTAT_CATALOG_REFRESH_HOURS; every code a tool takes is validated against it before a request goes upstream

• One request pacer per upstream host; a 429 or challenge page starts a cooldown and reaches the caller as a retryable upstream_busy carrying retryAfter

• Data responses of up to 5,000 rows are cached for ILOSTAT_CACHE_TTL_SECONDS

• Dataframes on by default: a query or comparison larger than ILOSTAT_PREVIEW_CHARS stages in full as a DuckDB df_<id> table that lives for ILOSTAT_DATASET_TTL_SECONDS. A tenant holds at most 1,000,000 staged rows in 100 dataframes, so a new table can evict the oldest ones before their TTL, and the response names them in evicted. With CANVAS_PROVIDER_TYPE=none, or in the .mcpb bundle (which ships without DuckDB's native binding), results stop at the inline preview and say so

• ILOSTAT data and metadata are published under the ILO Open Access policy as CC BY 4.0; every data response carries an attribution to keep with the numbers

Agent-friendly output:

• Basis on every value: each row is reported, modelled_estimate, or projection, and results carry basis_counts. The country profile returns reported and modelled values in separate fields and never fills one from the other

• Provenance and decoding: rows keep source, obs_status, and note codes with a legend that decodes them, and query and comparison responses echo applied_filters, defaults included

• Misses as data: an unknown dataset returns found: false with guidance, and compared areas without a value land in missing with a typed reason

• Typed errors: failures carry a reason (unknown_code, request_too_broad, upstream_busy, …) and a recovery hint

Getting started

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "ilostat-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/ilostat-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "ilostat-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/ilostat-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "ilostat-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/ilostat-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).

• No API key or account: both ILO APIs are open.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/ilostat-mcp-server.git

2. Navigate into the directory:

cd ilostat-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# every variable is optional; see Configuration below

Configuration

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run the production version:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:http
  # or
  bun run start:stdio

• Run checks and tests:

  bun run devcheck  # Lints, formats, type-checks, and more
  bun run test      # Runs the test suite

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic

• Use ctx.log for logging, ctx.state for storage

• Register new tools in buildToolDefinitions() in src/mcp-server/tools/definitions/index.ts

• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details. The ILOSTAT data the tools return belongs to the International Labour Organization and is published under CC BY 4.0; cite ILOSTAT and the dataset ID.