MCP.so
Sign In

ILO Labour Statistics (ILOSTAT) MCP Server

@Sidney da Silva Pereira Bissoli

Basic information

Transport

streamable-http

Authentication

None

Category

Data & Analytics

Author

Sidney da Silva Pereira Bissoli

Submitted by

Sidney da Silva Pereira Bissoli

About ILO Labour Statistics (ILOSTAT) MCP Server

ILO labour statistics (ILOSTAT) via MCP: search indicators and pull labour data by country, year, sex and age over the official SDMX API — with source, data vintage, retrieval timestamp and licence on every response.

#ilostat#ilo#international labour organization#labour statistics#labor statistics#employment#unemployment#wages#sdmx#oit#estatisticas do trabalho#mercado de trabalho#official statistics#open data#mcp server

Connection details

https://ilo.sidneybissoli.com/mcp

Setup

claude mcp add ilo-labour-statistics-ilostat --transport http https://ilo.sidneybissoli.com/mcp

ILO Labour Statistics (ILOSTAT) MCP Server tools

6

Search the ILOSTAT catalogue of ~1,200 indicator dataflows by keywords in the name or id (e.g. "unemployment rate sex age"). All terms must match (AND, case-insensitive), so start with 2–3 English words and drop terms if you get 0 results. Everyday and US wording is resolved to the ILO's own (labor→labour, wages/salary→earnings, informality→informal, gender→sex, productivity→output per worker); when that happens the response says so in vocabulary_notes. Results are ranked by ILO relevance weight, not by match count. Reading the id tells you the shape: suffix _RT = rate/ratio, _NB = number (usually thousands); dataflows whose second token starts with 2 (e.g. DF_UNE_2EAP_…) are ILO modelled estimates with full country/year coverage, the others are reported national data. Returns dataflow ids to use with ilo_get_data / ilo_get_indicator_metadata. Searches the local catalogue only — it does not return statistical values (use ilo_get_data), does not search dimension codes such as countries (use ilo_list_dimension_values) and does not cover non-ILO sources.

Structure of one ILOSTAT dataflow: dimensions (in SDMX key order), their codelists, the time dimension, the source's default selection and the data vintage (last update at the ILO). Use before ilo_get_data to know which filters exist. Does not return statistical values and does not list the codes themselves (use ilo_list_dimension_values).

Valid codes (id + label) of one dimension of an ILOSTAT dataflow — e.g. the country/area codes of REF_AREA (ISO 3166-1 alpha-3 such as BRA, plus X-codes for aggregates such as X01 World) or the categories of SEX (SEX_T/SEX_M/SEX_F) and AGE. Use `search` to resolve a name to a code (e.g. search "Brazil") instead of paging through hundreds of codes; codelists are shared across dataflows, so a code found here is valid wherever the same codelist is used. Use to build correct ilo_get_data filters. Does not return statistical values, does not say which codes actually have data for a given dataflow, and is not applicable to the time dimension (filter it via start_period/end_period in ilo_get_data).

Statistical observations from one ILOSTAT dataflow, filtered by dimension codes (filters, e.g. {"REF_AREA": ["BRA","ARG"], "SEX": "SEX_T"}) and period (start_period/end_period, e.g. "2015"/"2024"). REF_AREA is required, maximum 30 areas per call — for broad panels, split areas into batches and/or paginate by period. Unfiltered dimensions return all their categories. Does not aggregate, convert or otherwise transform values (raw ILOSTAT data only): read each value with the unit and multiplier the ILO states in its row attributes (UNIT_MEASURE, UNIT_MULT — e.g. UNIT_MULT 3 = thousands). Read TIME_PERIOD with the FREQ column (annual, quarterly or monthly) and OBS_STATUS when present (break in series, estimated or provisional value). Values are the current release, dated by data_vintage (the dataflow LAST_UPDATE): the ILO revises published figures and re-estimates modelled series (_2 ids) at each release, past years included. Does not search indicators (use ilo_search_indicators).

Searches the ILOSTAT labour statistics (≈1,200 SDMX dataflows: employment, unemployment, wages, working time, informality, SDG labour indicators) catalog and returns up to 10 matching documents as { id, title, url }, ordered by relevance (an empty list means nothing matched). This tool exists for the OpenAI Deep Research contract: ChatGPT deep research, company knowledge and research workflows over the Responses API require exactly the tools `search` and `fetch`. Pass one of the returned ids to `fetch` to read the document. For direct questions and for data (values, series, rankings) prefer the `ilo_*` tools, which return the actual data with provenance — this is a catalog index, not a data query. Query: natural language or keywords, Portuguese or English; accents and case are ignored. Behavior: read-only and idempotent — the catalog comes from the public source and is cached in memory.

Returns the full document for an id obtained from `search`, as { id, title, text, url, metadata }: `text` is the readable content (Markdown) and `url` the canonical public page to cite. Companion of `search` in the OpenAI Deep Research contract, over the ILOSTAT labour statistics (≈1,200 SDMX dataflows: employment, unemployment, wages, working time, informality, SDG labour indicators) catalog. Only ids returned by `search` are valid; an unknown id returns an error. The `ilo_*` tools remain the tools for data queries. Behavior: read-only and idempotent — a live GET against the public source when the document needs it.

Overview

What is ILO Labour Statistics (ILOSTAT) MCP Server?

A provenance-first MCP server for ILOSTAT, the statistical database of the International Labour Organization. It gives an AI assistant direct access to global labour data — unemployment, employment, wages, hours, informality — over the ILO's public SDMX API.

No installation, no account, no API key. Point a client at the hosted endpoint and ask.

Independent project: an unofficial, community-built client of the ILO's public data. Not affiliated with or endorsed by the ILO.

How to use it

Hosted — nothing to install:

https://ilo.sidneybissoli.com/mcp

Local, for Claude Desktop, Cursor and other MCP clients:

{
  "mcpServers": {
    "ilo-mcp-server": {
      "command": "npx",
      "args": ["-y", "ilo-mcp-server"]
    }
  }
}

Key features

Four tools, deliberately

  • ilo_search_indicators — find an indicator by what it measures, not by its SDMX code
  • ilo_get_indicator_metadata — what a series actually contains, before pulling it
  • ilo_list_dimension_values — the valid values for each dimension (country, sex, age band, classification), so a query is built from the real domain instead of guessed
  • ilo_get_data — the observations, filtered by country, period and dimensions

Small on purpose: every tool a server exposes costs context in every client session. Four cover ILOSTAT without sprawling into one tool per question.

Three guided prompts, for the questions people actually bring

  • compare countries on the same indicator
  • build a country labour profile
  • trace an indicator's trend over time

Provenance on every response — source URL, data vintage, retrieval timestamp and the licence terms of the data. When the source is an international organisation, a figure that can't be cited is a figure that can't be used.

Use cases

  • "What is youth unemployment in Brazil, and how does it compare with Argentina and Chile?"
  • "Show the trend in informal employment in Colombia over the last decade."
  • "What is the gender wage gap in the OECD countries ILOSTAT covers?"
  • "Build a labour profile for Portugal: employment, unemployment, hours, informality."
  • "Qual a taxa de desemprego juvenil no Brasil segundo a OIT?"
  • Comparative labour research needing figures traceable to the issuing body
  • Journalism and policy work where the licence of the data matters as much as the number

Frequently asked questions

1

Do I need an API key?

No. ILOSTAT's SDMX API is public, and this server requires no key or account. Use the hosted endpoint, or run it locally with `npx`.

2

Where does the data come from?

Directly from the ILO's public SDMX endpoint (`sdmx.ilo.org`), at query time. Every response carries the source URL, the data vintage, the retrieval timestamp and the licence terms.

3

Is this an official ILO product?

No. It is an independent, community-built client of the ILO's public data, not affiliated with or endorsed by the ILO.

4

How is this different from Rilostat or calling the SDMX API directly?

Those hand you the series; you still have to know which indicator you want and which dimension values are valid. Here the discovery is part of the interface — search by meaning, read the metadata, list the real dimension values, then pull. And each answer arrives with its provenance and licence attached, rather than as bare rows.

5

Why only four tools?

Because a large catalogue is a cost, not a feature: every exposed tool consumes context in every session of every client. Four cover the ILOSTAT workflow — discover, inspect, constrain, retrieve — and the three prompts cover the common shapes on top of them.

6

Is it open source?

Yes, MIT. Repository: https://github.com/SidneyBissoli/ilo-mcp-server

7

What is the ILO Labour Statistics (ILOSTAT) remote MCP server?

The ILO Labour Statistics (ILOSTAT) remote MCP server is a hosted Model Context Protocol endpoint at https://ilo.sidneybissoli.com/mcp, so AI assistants can connect to it without installing or running anything locally.

8

How do I connect to the ILO Labour Statistics (ILOSTAT) MCP server?

Add the endpoint https://ilo.sidneybissoli.com/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.

9

Does the ILO Labour Statistics (ILOSTAT) MCP server require authentication?

No. ILO Labour Statistics (ILOSTAT)'s MCP server does not require authentication — you can connect directly with the endpoint URL.

10

Which transport does the ILO Labour Statistics (ILOSTAT) MCP server use?

ILO Labour Statistics (ILOSTAT) exposes a streamable-http endpoint, the transport used by remote MCP servers and supported by all major MCP clients.

Comments